Closes https://github.com/langchain4j/langchain4j/issues/2329
* Will use observations and micrometer metrics to generate telemetry
based on the `ChatModelListener` lifecycle.
* Observations will handle request durations and tracing.
* There is a Micrometer DistributionSummary responsible to record token
usage.
This PR was based on @Sus4nne original PR
https://github.com/langchain4j/langchain4j/pull/2384 and later
https://github.com/langchain4j/langchain4j/pull/4556
PR https://github.com/langchain4j/langchain4j/pull/4556 can be developed
and merged independently.
I chose to implement the PR using Observation API conventions because
I'm using this as a reference implementation for later instrumentation
work for Quarkus.
CC @jonatan-ivanov, @dliubarskyi
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
After wiring a springboot app I was able to se traces:
<img width="1183" height="443" alt="image"
src="https://github.com/user-attachments/assets/e8d585c5-8766-4711-9991-9faa5739d95c"
/>
and metrics:
```log
# HELP gen_ai_client_operation_duration_active_seconds
# TYPE gen_ai_client_operation_duration_active_seconds summary
gen_ai_client_operation_duration_active_seconds_count{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="unknown",outcome="SUCCESS"} 0
gen_ai_client_operation_duration_active_seconds_sum{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="unknown",outcome="SUCCESS"} 0.0
# HELP gen_ai_client_operation_duration_active_seconds_max
# TYPE gen_ai_client_operation_duration_active_seconds_max gauge
gen_ai_client_operation_duration_active_seconds_max{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="unknown",outcome="SUCCESS"} 0.0
# HELP gen_ai_client_operation_duration_seconds
# TYPE gen_ai_client_operation_duration_seconds summary
gen_ai_client_operation_duration_seconds_count{error="none",gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",outcome="SUCCESS"} 2
gen_ai_client_operation_duration_seconds_sum{error="none",gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",outcome="SUCCESS"} 3.384050045
# HELP gen_ai_client_operation_duration_seconds_max
# TYPE gen_ai_client_operation_duration_seconds_max gauge
gen_ai_client_operation_duration_seconds_max{error="none",gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",outcome="SUCCESS"} 2.115592691
# HELP gen_ai_client_token_usage_tokens Measures the quantity of used tokens
# TYPE gen_ai_client_token_usage_tokens summary
gen_ai_client_token_usage_tokens_count{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="input"} 2
gen_ai_client_token_usage_tokens_sum{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="input"} 508.0
gen_ai_client_token_usage_tokens_count{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="output"} 2
gen_ai_client_token_usage_tokens_sum{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="output"} 53.0
# HELP gen_ai_client_token_usage_tokens_max Measures the quantity of used tokens
# TYPE gen_ai_client_token_usage_tokens_max gauge
gen_ai_client_token_usage_tokens_max{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="input"} 273.0
gen_ai_client_token_usage_tokens_max{gen_ai_operation_name="chat",gen_ai_provider_name="OPEN_AI",gen_ai_request_model="gpt-4o-mini",gen_ai_response_model="gpt-4o-mini-2024-07-18",gen_ai_token_type="output"} 27.0
```
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
Update embedding stores table with new integrations(Hibernate) and
format the table.
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
This is a follow up of the new parallel mapper feature introduced
[here](https://github.com/langchain4j/langchain4j/pull/4616) addressing
all the outstanding tasks listed
[here](https://github.com/langchain4j/langchain4j/pull/4616#pullrequestreview-3854224237).
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
None yet
## Change
<!-- Please describe the changes you made. -->
Add a new `EmbeddingStore` implementation based on Hibernate ORM and its
hibernate-vector module.
* Could make existing SQL specifc Langchain4j `EmbeddingStore`
integrations obsolete
* Makes more SQL vector stores available due to Hibernate ORM supporting
them
* Could make existing NoSQL Langchain4j `EmbeddingStore` integrations
obsolete when we get further with our Hibernate NoSQL efforts
* Allows more vector distance operations and vector types thanks to
Hibernate ORM supporting them
* Allows more convenient data model customizations by defining fields on
entity classes
* Allows evolving existing entity classes into a source for
`EmbeddingStore` API
* Another benefit is that when users use entities, they can then also
use HQL to write custom and more complex vector/hybrid-search queries if
needed
Thanks to the abstraction, this integration would free Langchaing4j
developers from maintainance of all those separate `EmbeddingStore`
implementations and focus on just a single integration, with our help.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
see https://github.com/langchain4j/langchain4j-examples/pull/187
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [x] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Updated Playwright documentation with additional examples and
formatting.
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes#4602
## Change
This adds a builder method to the `MistralAiChatModelBuilder` to
configure strict JSON schema for response format, as is done in the
OpenAI implementation.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes#4279
## Change
Implement Optional parameter as alternative to `@P(required)`
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4615
## Change
<!-- Please describe the changes you made. -->
Provided an implementation for a declarative Multi Instance Parallel
agent.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Adds support for the subsidiary SSE channel as desribed in
https://modelcontextprotocol.io/specification/2025-11-25/basic/transports#listening-for-messages-from-the-server
`quarkus-mcp-server` calls it "subsidiary", the spec doesn't have any
name for it, so I went with subsidiary too.
I went with it being disabled by default because I don't think it is
something that will be used very often, and it's somewhat experimental,
so better stay on the safe side.
FYI @mkouba
Added a security warning regarding high-risk code execution in
production environments.
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
Add docs for
https://github.com/langchain4j/langchain4j-community/pull/479
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
This is one last rework of the HTML report generation for agentic
systems, which includes:
- Complete decoupling of the AgentMonitor from the report generator
- Possibility to generate the report only for a specific execution
(identified through the memoryID)
- Possibility to generate the topology of the agentic system only,
starting from the AgentInstance and without any execution
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Change
Implements Tool Search Tool feature initially introduced by
[Anthropic](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool).
### Tool Search
When working with a large number of tools,
sending all tools on every request can significantly increase token
usage and reduce model performance.
To address this, LangChain4j provides a tool search mechanism
that allows tools to be discovered dynamically by the LLM itself,
instead of being exposed upfront.
The core idea is simple:
- Initially, the LLM is exposed to one or more special tool-search tools
- The LLM can call these tools to search for relevant tools
- Once relevant tools are found, they are included in subsequent
requests to the LLM
This enables scalable, token-efficient, and model-driven tool discovery.
#### How Tool Search Works
A tool search flow typically looks like this:
1. Initial request:
- The LLM sees only tool-search tools (not the full tool set)
2. Tool search
- The LLM calls a tool-search tool, describing what kind of tool it
needs
- The tool-search strategy matches the request against available tools
4. Tool exposure
- Matching tools are added to the next request to the LLM
5. Tool execution
- The LLM can now call the found tools normally
Previously found tools are accumulated across multiple tool-search
calls.
Each time the LLM invokes the tool-search tool,
the newly matched tools are added to the existing set of tools visible
to the LLM (they are merged, not replaced).
This means the list of tools visible to the LLM can grow over time.
Found tools remain visible to the LLM until their corresponding
`ToolExecutionResultMessage`
is evicted from the `ChatMemory`, and at least until the end of the AI
Service invocation.
If `ChatMemory` is not configured, the found tools remain visible to the
LLM
only until the end of the AI service invocation.
#### ToolSearchStrategy
Tool search is implemented via the `ToolSearchStrategy` interface:
```java
@Experimental
public interface ToolSearchStrategy {
List<ToolSpecification> getToolSearchTools(InvocationContext invocationContext);
ToolSearchResult search(ToolSearchRequest toolSearchRequest);
}
```
A `ToolSearchStrategy` is responsible for:
- Exposing tool-search tools to the LLM
- Executing tool search requests generated by the LLM
- Returning matching tool names, which will then be resolved and exposed
LangChain4j currently provides 2 out-of-the-box implementations:
- `SimpleToolSearchStrategy` – keyword-based matching
- `VectorToolSearchStrategy` – semantic search using embeddings
See Javadoc of these classes for more details.
You can also implement custom strategies.
#### Configuring Tool Search in AI Services
Tool search is configured at the AI Service level:
```java
Assistant assistant = AiServices.builder(Assistant.class)
.chatModel(chatModel)
.chatMemory(chatMemory)
.tools(tools) // tool search works for static tools
.toolProvider(mcpToolProvider) // tool search works for tools provided dynamically (e.g., MCP)
.toolSearchStrategy(new SimpleToolSearchStrategy())
.build();
```
Once configured:
- The LLM no longer sees all tools upfront
- Tool discovery becomes an explicit, model-driven step
- Token usage is reduced, especially with large tool sets
#### When to Use Tool Search
Tool search is especially useful when:
- You have many tools (dozens or hundreds)
- Tools are domain-specific or rarely used
- Tool availability depends on context, user, or permissions
- You want the LLM to reason about which tools it needs, instead of
guessing from a long list
If you have only a small number of tools, or all tools are always
relevant,
using regular approach may be simpler.
#### Always Visible Tools
When tool search is enabled, tools are normally hidden from the LLM
until they are discovered via a tool-search call.
However, in some cases you may want certain tools to always be visible
to the LLM.
Typical use cases:
- Core tools that should always be accessible
- Frequently used tools where search overhead is unnecessary
- Utility tools
LangChain4j supports this via the `ALWAYS_VISIBLE` tool search behavior.
##### How It Works
When a tool is marked as `ALWAYS_VISIBLE`:
- It is exposed to the LLM in the very first request
- It does not require discovery via tool search
- It remains visible throughout the AI Service invocation
- It is not included in searchable tool candidates
All other tools continue to follow the normal tool-search flow.
##### Using `@Tool` Annotation
You can mark a tool as always visible via the @Tool annotation:
```java
@Tool(searchBehavior = ALWAYS_VISIBLE)
String getWeather(String city) {
return weatherService.getWeather(city);
}
```
##### Using `McpToolProvider`
When using MCP tools (via `McpToolProvider`), always-visible tools can
be configured via `alwaysVisibleToolNames`:
```java
McpToolProvider.builder()
.mcpClients(mcpClient)
.alwaysVisibleToolNames("getWeather")
.build();
```
##### Using `ToolSpecification`
If you configure tools programmatically, you can mark them as always
visible using `metadata`:
```java
ToolSpecification toolSpecification = ToolSpecification.builder()
.name("getWeather")
.parameters(JsonObjectSchema.builder()
.addStringProperty("city")
.required("city")
.build())
.metadata(Map.of(ToolSpecification.METADATA_SEARCH_BEHAVIOR, SearchBehavior.ALWAYS_VISIBLE))
.build();
```
#### Notes and Limitations
NOTE: Tool search relies on the LLM’s ability to understand when and how
to search for tools.
The effectiveness of this feature depends heavily on the chosen model.
NOTE: Tool search is currently marked as experimental and may evolve in
future releases.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/2329 partly
It adds metrics for the chat model interaction only.
## Change
This adds a specialised ChatModelListener which utilises a Micrometer
Meterregistry to expose metrics about the ChatModelResponse/Request. It
exposes metrics in line with the OpenTelemetry Semantic Conventions for
Generative AI.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable) Will do later
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
Document the reasoning support for Magistral models added in PR #4474.
Add a new "Thinking / Reasoning" section covering returnThinking and
sendThinking parameters with a code example. Also mark Thinking
(Reasoning) as supported in the comparison table.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
This pull request improves and simplifies the human-in-the-loop agent
based on the feedback received during the workshops that we gave at
JFokus and VoxxedDays Ticino. This new implementation also better fits
the validations performed by the Quarkus extension, by removing a no
longer necessary annotation and thus providing the actual return type of
the agent directly in the method annotated with `@HumanInTheLoop`.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Problem Description
Fix an issue where tool call IDs are duplicated when using
OpenAI-compatible APIs (such as DeepSeek and Qwen) with streaming
responses.
Some OpenAI-compatible APIs behave differently from the official OpenAI
API when streaming tool calls:
OpenAI standard behavior:
The tool call ID is sent incrementally across chunks
(e.g. chunk1 = "abc", chunk2 = "abc" → final ID = "abcabc")
Some compatible APIs behavior:
The full tool call ID is repeated in every chunk
(e.g. chunk1 = "abc", chunk2 = "abc" → expected ID = "abc", not
"abcabc")
This causes tool call IDs to be incorrectly accumulated and duplicated
when using APIs such as DeepSeek and Qwen.
Solution
Introduce a new configuration option accumulateToolCallId in
OpenAiStreamingChatModel to control how tool call IDs are handled during
streaming:
Default value: true
Preserves compatibility with the official OpenAI streaming behavior
Set to false:
Suitable for APIs like DeepSeek and Qwen, where each chunk sends the
full tool call ID
In this mode, the ID from each chunk replaces the previous value instead
of being accumulated
Code Example
StreamingChatModel model = OpenAiStreamingChatModel.builder()
.baseUrl("https://api.deepseek.com/v1")
.apiKey(apiKey)
.modelName("deepseek-chat")
.accumulateToolCallId(false) // Disable ID accumulation
.build();
Changes
Added the accumulateToolCallId configuration field to
OpenAiStreamingChatModel
Implemented corresponding handling logic in
OpenAiStreamingResponseBuilder
Updated official documentation to explain the purpose and usage
scenarios of this option
Related Issue
Fixes#4528
Documentation
Documentation has been updated:
docs/docs/integrations/language-models/openai-compatible.md
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
## Issue
Follow-up to #4487
## Change
This PR adds documentation for the `UserMessage` caching feature for the
Anthropic integration, as requested by the maintainers in PR #4487.
It adds a new "Caching User Messages" section to the Anthropic
documentation with a code example showing how to apply the
`cache_control` attribute.
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Updates the Google AI Gemini integration documentation to cover the new
Media Resolution features introduced in PR #4457.
- Added configuration examples for Global Media Resolution and Per-Part
Media Resolution.
- Added a new "Media Resolution" section detailing how to control image
resolution, including support for Gemini 3's `DetailLevel`.
- Documented the mapping between `ImageContent.DetailLevel` and Gemini's
resolution levels.
- Added a note specifying that `ULTRA_HIGH` resolution is required for
specific use cases such as computer use.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behavior)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root
[pom.xml](cci:7://file:///d:/Projects/langchain4j/pom.xml:0:0-0:0) and
[langchain4j-bom/pom.xml](cci:7://file:///d:/Projects/langchain4j/langchain4j-bom/pom.xml:0:0-0:0)
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3775
## Change
<!-- Please describe the changes you made. -->
Simply integrated Apache HttpClient 5 and modified the timeout in the
HttpClientTimeoutIT class within the langchain4j-http-client test
methods to 1 second. Since Apache HttpClient 5's asynchronous timeout
cannot accurately implement a 250-millisecond timeout, the effect can
only be achieved by increasing the timeout duration.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#1599
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
#3252
## Change
This PR adds support for OpenAI's **Responses API** (`/v1/responses`
endpoint) with two implementations:
### 1. Non-official implementation (`langchain4j-open-ai` module)
- **Class**: `OpenAiResponsesStreamingChatModel`
- Uses manual HTTP client with JSON serialization
- Provides full control over request/response handling
- Includes `OpenAiResponsesValidator` for parameter validation
### 2. Official implementation (`langchain4j-open-ai-official` module)
- **Class**: `OpenAiOfficialResponsesStreamingChatModel`
- Uses official OpenAI Java SDK v4.1.0
- Leverages SDK's built-in features and updates
- Includes `ResponseCancellationHandler` for stream cancellation
### Key Features
- **Streaming-only implementation**: Currently only streaming versions
are implemented (non-streaming could be added in the future)
- **Tool execution**: Full support for function calling with proper tool
execution flow
- **Cancellation**: Streaming responses can be cancelled via
`StreamingHandle.cancel()`
- **Validation**: Both implementations validate parameters with
fail-fast approach and clear error messages
- **Listener support**: Full integration with `ChatModelListener` for
request/response monitoring
- **Metadata**: Complete response metadata including token usage, model
name, finish reason
### Implementation Choices
- **Non-official**: For users who prefer manual control, minimal
dependencies, or need custom HTTP client configuration
- **Official**: For users who want SDK-maintained compatibility and
automatic updates
**Why `OpenAIClient` instead of `OpenAIClientAsync`?**
The official SDK's `OpenAIClient` provides a synchronous streaming API
that returns a `Stream<ResponseEvent>`. This is actually more suitable
for our use case than `OpenAIClientAsync` because:
1. We process events sequentially in order
2. We need to handle backpressure naturally via stream iteration
3. The async client would add unnecessary complexity for event
processing
4. We already handle async behavior at the LangChain4j level via
`CompletableFuture`
### Current Implementation Support
- ✅ Text content via `TextContent`
- ✅ Images via `ImageContent` (base64-encoded)
- ✅ Images via public URLs
- ❌ Audio content (not yet implemented)
- ❌ Video content (not yet implemented)
- ❌ Document/file attachments (not yet implemented)
### Files Added
**langchain4j-open-ai module (4 files):**
1. `OpenAiResponsesStreamingChatModel.java` - Main implementation
2. `OpenAiResponsesValidator.java` - Parameter validation
3. `OpenAiResponsesStreamingChatModelIT.java` - Integration tests
4. `OpenAiResponsesStreamingChatModelListenerIT.java` - Listener tests
**langchain4j-open-ai-official module (5 files):**
1. `OpenAiOfficialResponsesStreamingChatModel.java` - Main
implementation
2. `ResponseCancellationHandler.java` - Cancellation support
3. `OpenAiOfficialResponsesStreamingChatModelIT.java` - Integration
tests
4. `OpenAiOfficialResponsesStreamingAiServiceIT.java` - AI Service tests
5. `OpenAiOfficialResponsesStreamingChatModelListenerIT.java` - Listener
tests
## General checklist
- [X] There are no breaking changes
- [X] I have added unit and integration tests for my change
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
## Checklist for adding a new LLM integration
- [X] I have added a `OpenAiResponsesStreamingChatModel` and
`OpenAiOfficialResponsesStreamingChatModel` that implement
`StreamingChatModel`
- [X] I have added a `OpenAiResponsesStreamingChatModelIT` and
`OpenAiOfficialResponsesStreamingChatModelIT` that extend from
`StreamingChatModelIT`
- [X] I have added a `OpenAiResponsesStreamingChatModelListenerIT` and
`OpenAiOfficialResponsesStreamingChatModelListenerIT` that extend from
`StreamingChatModelListenerIT`
- [X] I have added a `OpenAiOfficialResponsesStreamingAiServiceIT` that
extends from `StreamingAiServicesIT`
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes#4517
## Change
- Add a focused tutorial page: `tutorials/mcp-stdio-server` (how to
build a Java MCP stdio server using `langchain4j-community-mcp-server`).
- Add a short note + link from the existing MCP tutorial
(`tutorials/mcp`).
## How to verify (end-to-end)
- Build the example server from langchain4j/langchain4j-examples#181.
- Configure it in Claude Desktop using the JSON snippet from
`docs/docs/tutorials/mcp-stdio-server.md`.
- Ask Claude: "Please calculate 1234 + 5678 using the calculator tool."
## Notes
- Docs-only change (no code changes / no tests).
- Context: #4371 and langchain4j/langchain4j-community#527
## Issue
Closes#4391
## Change
This PR adds a short clarification to the RAG documentation explaining
that retrieval can be treated as a tool-like, conditional capability.
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes#1666
## Changes
This PR adds hybrid search and full text search capabilities to the
langchain4j-elasticsearch module by following the same approach chosen
by AzureAI search, creating a common abstract interface and adding an
extension of `ContentRetriever` (as [discussed in the
issue](https://github.com/langchain4j/langchain4j/issues/1666#issuecomment-2405520929),
the third approach).
In details:
- Creates a common interface `AbstractElasticsearchEmbeddingStore`,
makes `ElasticsearchEmbeddingStore` extend it.
- Creates a new class `ElasticsearchContentRetriever` which extends
`AbstractElasticsearchEmbeddingStore`
- Adds new configurations for full text search and hybrid search
(`ElasticsearchConfigurationFullText`,
`ElasticsearchConfigurationHybrid`)
Positives of this approach: no breaking changes,
`ElasticsearchEmbeddingStore` keeps all previous functionalities and can
also be used with the new configurations, also it's coherent with the
other existing implementations of `ContentRetriever`.
Negatives of this approach: `ElasticsearchEmbeddingStore` and
`ElasticsearchContentRetriever` can basically be used interchangeably,
but `ElasticsearchContentRetriever` is more high level and easier to
use. Deprecating `ElasticsearchEmbeddingStore` in the future could be
beneficial in term of usability.
## Additional Changes
### Bugfix
Version 9.2 of Elasticsearch (server) introduces a breaking change: by
default, vector fields are no longer returned by vector type queries for
performance reasons ([full explanation and
details](https://www.elastic.co/search-labs/blog/elasticsearch-exclude-vectors-from-source)).
This means that using langchain4j with its hardcoded queries, users of
the 9.2 server would have no way of making the Elasticsearch server
return the full response complete with vectors (except recreating the
index manually with the proper setting). To solve this:
- The null check for the vector field that was present in method
`toMatches` has been removed, since many vector search cases actually
have no use for the vectors to be returned.
- A new optional parameter `includeVectorResponse` has been added to
`AbstractElasticsearchEmbeddingStore`, so that users can choose to
include the vectors in the response.
### Telemetry
To help us track usage of the langchain4j library, a user-agent header
has been added to the ElasticsearchClient instance.
## Additional Info
I'm open to discuss this approach and make changes if necessary of
course (disclosure: I work for Elastic).
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Co-authored-by: David Pilato <david@pilato.fr>
## Issue
Closes#4274Closes#4273
---
## Change
This PR adds listener-based observability hooks for RAG components,
similar to the existing `ChatModelListener` pattern, so that
`EmbeddingModel`, `EmbeddingStore` and `ContentRetriever` are no longer
“black boxes”.
---
### What’s included
#### EmbeddingStore observability
- Added `EmbeddingStoreListener` API in `langchain4j-core`:
- `EmbeddingStoreListener` with `onRequest/onResponse/onError`
- `EmbeddingStoreRequestContext`, `EmbeddingStoreResponseContext`,
`EmbeddingStoreErrorContext`
- `EmbeddingStoreOperation` to identify the operation being observed
(e.g., ADD, ADD_ALL, SEARCH, REMOVE, etc.)
- Added `EmbeddingStore#addListener(...)` and
`EmbeddingStore#addListeners(...)` default methods returning an
observing store wrapper.
- Implemented a generic wrapper `ObservingEmbeddingStore` that delegates
to the real store and fires listeners around operations.
#### ContentRetriever observability
- Added `ContentRetrieverListener` API in `langchain4j-core`:
- `ContentRetrieverListener` with `onRequest/onResponse/onError`
- `ContentRetrieverRequestContext`, `ContentRetrieverResponseContext`,
`ContentRetrieverErrorContext`
- Added `ContentRetriever#addListener(...)` and
`ContentRetriever#addListeners(...)` default methods returning an
observing retriever wrapper.
- Implemented `ObservingContentRetriever` to intercept `retrieve(Query)`
and dispatch events.
- **Important:** `ContentRetriever#addListeners` uses
`Collection<ContentRetrieverListener>` to avoid Java type-erasure
signature clashes for implementations that also implement
`EmbeddingStore` (e.g., `AzureAiSearchContentRetriever`).
#### EmbeddingModel observability
- Added `EmbeddingModelListener` API in `langchain4j-core`:
- `EmbeddingModelListener` with `onRequest/onResponse/onError`
- `EmbeddingModelRequestContext`, `EmbeddingModelResponseContext`,
`EmbeddingModelErrorContext`
- Added `EmbeddingModel#addListener(...)` and
`EmbeddingModel#addListeners(...)` default methods returning an
observing model wrapper.
- Implemented `ObservingEmbeddingModel` which intercepts `embedAll(...)`
(the core method all embeddings flow through) and fires listeners around
the delegate call.
- **Note:** `EmbeddingModel#addListeners` uses
`Iterable<EmbeddingModelListener>` to reduce the risk of future
type-erasure clashes with other interfaces.
### How it works (wrapper/decorator approach)
Instead of modifying each individual model/store/retriever
implementation (MongoDB, Pinecone, Azure AI Search, etc.), the change
introduces **generic wrappers** that implement the same interfaces and
delegate to the real implementation:
- `ObservingEmbeddingStore` wraps any `EmbeddingStore`
- `ObservingContentRetriever` wraps any `ContentRetriever`
- `ObservingEmbeddingModel` wraps any `EmbeddingModel`
Users enable observability by calling:
- `EmbeddingStore#addListener(s)` which returns an observing
`EmbeddingStore`
- `ContentRetriever#addListener(s)` which returns an observing
`ContentRetriever`
- `EmbeddingModel#addListener(s)` which returns an observing
`EmbeddingModel`
This ensures:
- **No provider-specific duplication** (single implementation works
across all integrations)
- **No breaking changes** for existing store/retriever implementations
(no required code changes)
- **Consistent behavior** with `ChatModelListener`:
- listeners are invoked in list order
- listeners are invoked synchronously
- listener exceptions are logged and ignored so they do not break user
calls
- `attributes` map allows passing data across request/response/error and
across listeners
---
### Why wrapper/decorator was chosen
Unlike `ChatModel`, which has a central default method
(`ChatModel#chat`) that can be instrumented once, `EmbeddingStore` and
`ContentRetriever` are “thin” interfaces without a single shared
orchestration method. The wrapper/decorator approach provides a
non-invasive, reusable interception point that can be applied to any
implementation without requiring per-provider wrappers or modifying
every integration.
### Note on Azure AI Search compilation conflict
Some integrations (e.g., Azure AI Search retriever) implement/extend
both `EmbeddingStore` and `ContentRetriever`. To avoid Java type erasure
signature clashes, `ContentRetriever#addListeners` uses a
`Collection<ContentRetrieverListener>` while
`EmbeddingStore#addListeners` uses a `List<EmbeddingStoreListener>`.
This keeps the API ergonomic (still accepts `List.of(...)`) and avoids
conflicts for implementations that inherit both interfaces.
### Tests
Added unit tests in `langchain4j-core` mirroring `ChatModelListenerTest`
coverage:
- listener invocation order
- listener exception handling (ignored/logged)
- attributes propagation across listeners
- `onError` invocation when delegate throws
- null/empty listener lists handling
---
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Lucas Gois <lucas.gois@digibee.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
This introduces a concept of `McpCallContext` that contains information
about the context around an invocation to an MCP server. This context is
injected into the newly added MCP header providers.
Building on top of that, I added support for MCP listeners that can be
invoked before and after calls to MCP servers. They also inject a
`McpCallContext`.
Further building on top of that, I've been working on Micrometer metrics
support for MCP clients, this will live in the Quarkus extension and
will be based on top of MCP listeners. I am drafting that, I'd like to
get feedback on this part first before continuing the metrics thing
because it builds on top of it.
Closes#4241
## Issue
Closes#4423
## Change
This adds an `errors` field to the `BatchSuccess` record where erroneous
responses are stored. I personally would've preferred to do this in the
same manner as done in the Anthropic PR: Wrapping responses in
`IndividualResponse<ChatResponse>` which can then be Success or Error
using sealed interfaces. I opted to do it like this to not break
existing implementations (even though it's marked `@Experimental`).
Let me know what you prefer for the API to be, I'll make sure to change
the Anthropic Batch PR as well to follow the same design as is decided
here.
Current:
```java
if (result instanceof BatchSuccess<ChatResponse> success) {
System.out.println("Batch completed!");
System.out.println("Successful: " + success.responses().size());
System.out.println("Failed: " + success.errors().size());
// Process successful responses
int index = 0;
for (ChatResponse response : success.responses()) {
System.out.println("Response " + index++ + ": " + response.aiMessage().text());
}
// Process errors
for (var error : success.errors()) {
System.err.println("Error [code=" + error.code() + "]: " + error.message());
}
}
```
Alternative:
```java
if (result instanceof BatchSuccess<ChatResponse> success) {
System.out.println("Batch completed with " + success.results().size() + " results");
for (IndividualResult<ChatResponse> individualResult : success.results()) {
switch (individualResult) {
case IndividualResultSuccess<ChatResponse> s ->
System.out.println("Success: " + s.response().aiMessage().text());
case IndividualResultError<ChatResponse> e ->
System.err.println("Error [code=" + e.code() + "]: " + e.message());
}
}
}
```
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core]
## Change
<!-- Please describe the changes you made. -->
- Implemented ModelCatalog support for watsonx.ai
- Updated watsonx.ai SDK dependency to version 0.18.0
- Enhanced documentation
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4459Closes#4385
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Change
This PR provides extended support for OpenSearch embedding store based
on the ElasticSearch implementation. OpenSearch is a fork of
ElasticSearch so the capabilities are pretty the same.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [x] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## What does this PR do?
Adds a set of RAG (Retrieval Augmented Generation) examples to the
pgvector embedding store documentation.
## What is the current behavior?
The current documentation shows only very basic `PgVectorEmbeddingStore`
setup with connection parameters. It doesn't show how we can use
pgvector in an end-to-end RAG workflow, which is the primary use case
for most users.
## What is the new behavior?
Added a new "Complete RAG Example with PGVector" section that
demonstrates:
### 1. Document Ingestion (Indexing Stage)
- Loading documents (PDF, TXT, etc.)
- Splitting into chunks with optimal parameters
- Generating embeddings
- Storing in pgvector
### 2. Querying (Retrieval Stage)
- Embedding user questions
- Similarity search in pgvector
- Building context from retrieved segments
- Injecting context into LLM prompts
### 3. Production Considerations
Based on real-world production usage:
- Connection pooling with HikariCP DataSource
- IVFFlat index optimization for large datasets (>100k embeddings)
- JSONB metadata storage for better query performance
- Chunk size tuning recommendations (200-300 vs 500-800 tokens)
- Error handling best practices
### 4. Spring Boot Integration
- Reference to complete Spring Boot example (to be added in
langchain4j-examples repo)
## Why is this change important?
This change fills a critical gap in the documentation. Many users
struggle to connect the basic setup example with building a complete RAG
system. This example provides:
1. **End-to-end workflow**: Shows both indexing and retrieval stages
2. **Production-ready patterns**: Based on real enterprise usage
3. **Performance optimization**: Guidance on indexing and metadata
storage
4. **Best practices**: Error handling, connection pooling, chunk sizing
## How has this been tested?
The code examples are based on production RAG implementations using
LangChain4j + pgvector. All code snippets follow the existing
LangChain4j API patterns.
This PR adds documentation for the S3 Vectors embedding store, following
up on the implementation merged in langchain4j/langchain4j-community#536
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes # https://github.com/langchain4j/langchain4j/issues/4192
## Change
Supplementary documentation is available at
docs/docs/integrations/embedding-stores/amazon-s3-vectors.md
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Progresses #4379
## Change
Added documentation for Nano Banana, will add some examples early next
week.
## General checklist
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Doesn't close an issue, just updating docs -> reference:
https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: Nitinram <nitinram@Nitinrams-MacBook-Pro.local>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Fixes#4365
Add support for AiServiceRequestIssuedEvent and corresponding listener
functionality
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4177
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Change
Added `onPartialToolCall` callbacks to the `TokenStream` interface,
enabling AI Services to consume partial tool call arguments as they
stream from the LLM.
This feature complements the existing `onPartialToolCall` support in
`StreamingChatResponseHandler` (added in v1.8.0) by exposing it through
the higher-level `TokenStream` API used in AI Services.
### Implementation Details:
**TokenStream.java**
- Added two overloaded `onPartialToolCall` methods:
- `onPartialToolCall(Consumer<PartialToolCall>)` - simple callback
- `onPartialToolCall(BiConsumer<PartialToolCall,
PartialToolCallContext>)` - with context for streaming cancellation
- Both methods are marked `@Experimental` and `@since 1.12.0`
**AiServiceTokenStream.java**
- Added handler fields and invocation counters
- Implemented callback registration methods
- Added validation to ensure only one variant is used at a time
- Updated handler instantiation to pass callbacks
**AiServiceStreamingResponseHandler.java**
- Added handler fields and constructor parameters
- Implemented `onPartialToolCall` interface methods from
`StreamingChatResponseHandler`
- Updated recursive handler creation for tool execution loops
**AiServiceTokenStreamTest.java**
- Added tests for validation of multiple invocations
- Added tests for mutual exclusion between overloaded methods
### Supported Providers:
Works automatically with providers that already implement partial tool
call streaming:
- Anthropic
- OpenAI
- Azure OpenAI
### Example usage
```java
assistant.chat("What's the weather?")
.onPartialToolCall(partialToolCall -> {
System.out.print(partialToolCall.partialArguments());
})
.onCompleteResponse(response -> System.out.println("Done"))
.onError(Throwable::printStackTrace)
.start();
````
> **Simple callback variant** — prints partial tool-call argument chunks
as they stream (suitable for progressive assembly / UI updates).
```java
assistant.chat("What's the weather?")
.onPartialToolCall((partialToolCall, partialToolCallContext) -> {
System.out.print(partialToolCall.partialArguments());
})
.onCompleteResponse(response -> System.out.println("Done"))
.onError(Throwable::printStackTrace)
.start();
````
> **Context-aware variant** — same streaming partial arguments, plus
access to `PartialToolCallContext` for stream control (e.g.,
cancellation) when needed.
### Manual / integration evidence
The screenshots below show partial tool-call chunks being emitted and
consumed during streaming (both callback variants).
> Callback receives streamed partial arguments while the model is still
producing output.
> Partial arguments are delivered in multiple chunks and can be
progressively assembled/forwarded.
> Context-enabled callback variant works as expected (e.g., allowing
cancellation / stream control).
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [x] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3519
## Change
Allows to use streaming chat models with agents. Check the section added
in the agents documentation to find how this works.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
Oceanbase's vector storage adaptation PR has been merged,The
documentation should be supplemented in the langchain4j main
repo:https://github.com/langchain4j/langchain4j-community/pull/509
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4358
## Change
<!-- Please describe the changes you made. -->
Supplementary documentation is available at
docs/docs/integrations/embedding-stores/oceanbase.md
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: xxsc0529 <xxsc0529@oceanbase.com>
## Issue
Closes#4324
## Change
Added Examples section to `azure-acads.md` and removed broken link from
`SessionsREPLTool.java` Javadoc.
- Added Examples section to
`docs/docs/integrations/code-execution-engines/azure-acads.md` with link
to `SessionsREPLToolTest` following the pattern used in
`graalvm-polyglot.md`
- Removed lines 38-39 from `SessionsREPLTool.java` containing reference
to non-existent example repository path
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
- Introduce `storeRetrievedContentInChatMemory` flag in context
- When true (default), store the final userMessage (after RAG,
guardrails, output format) in ChatMemory
- When false, store only originalUserMessage in ChatMemory while still
sending the augmented userMessage to the LLM
- Keep existing behavior as default to avoid breaking changes
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3498
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3999
## Change
<!-- Please describe the changes you made. -->
- Added `jsonSchemaNode` to `ResponseFormat` to allow passing JSON
schemas as arbitrary JsonNode objects instead of only JsonSchema
subclasses.
- Added `asJsonNode()` to `JsonRawSchema` to transform a raw JSON schema
string into a JsonNode for Gemini’s native schema format.
- Added `responseJsonSchema` to `GeminiGenerationConfig` to forward raw
JSON schema objects directly to the Gemini API.
- Extended `SchemaMapper` to support `JsonRawSchema` enabling raw
schemas to bypass structural mapping and be delivered unmodified.
- Updated Gemini model request builder to attach either a structured
schema (`responseSchema`) or raw schema (`responseJsonSchema`).
- Added integration tests verifying end-to-end support for raw schemas
and updated existing tests accordingly.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Giannis Christodoulou <gchristo@redhat.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes#3073
## Change
springboot-integration add automatic Component ToolProvider
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Added ChatRequest as additional param of AiServiceResponseReceivedEvent.
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3986
## Change
In order to have better observability options when listing to
`AiServiceResponseReceivedEvent`s, I added the `ChatRequest` next to the
already existing `ChatResponse` in the event. This enables the listener
to track LLM request-response round-trips in the context of an AIService
invocation (represented by `InvocationContext`).
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Stanley Schragl <stanley.schragl@partner.bmw.de>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Change
<!-- Please describe the changes you made. -->
- Upgraded `watsonx-ai` dependency to version `0.16.0`
- Added custom `HttpClient`configuration support via builder pattern
- Enhanced watsonx integration documentation
- Removed `WatsonxExecutorProvider` class
- Added comprehensive test coverage for custom `HttpClient`
functionality
- Refactored and cleaned up integration tests
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Follow-up to https://github.com/langchain4j/langchain4j/pull/4211
## Change
Include anthropic server tools results in AnthropicContent and then map
them into the attributes of AiMessage when enabled in ChatModel.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases (existing tests
cover negative cases)
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
I want to deprecate the `langchain4j-github-models` module (which I
created), in favor of the `langchain4j-openai-official` module (which I
also created).
Here is why:
- The `langchain4j-github-models` uses the Azure Inference API which
isn't as well maintained as the OpenAi Java SDK, and is limited to Azure
(the OpenAI Java SDK works everywhere, including on competing platforms,
which is better for our end-users)
- If you are using Microsoft Foundry (the new name for Azure OpenAi) or
OpenAi (which is operated by Microsoft), underneath it's the exact same
thing as GitHub Models: we might as well have the same SDK to connect to
all of those.
- I would also like to focus on less modules, this would allow better
quality from my side.
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4174
## Change
<!-- Please describe the changes you made. -->
Added structured output support for Anthropic models.
- Introduced `responseFormat()` and `supportedCapabilities()` methods
for `AnthropicChatModel` and `AnthropicStreamingChatModel`.
- Modeled JSON schemas in Anthropic requests via
`AnthropicResponseFormat`.
- Added a helper method in `AnthropicMapper` (`toAnthropicMap()`) to map
to the JSON schema format expected by the Anthropic API. Some features
(such as unions and complex types in enums) are still not supported, so
using the traditional `JsonSchemaUtils.toMap()` does not work for
certain edge cases.
- Removed `supportsJsonResponseFormat*()` methods from
`AnthropicChatModelIT` and `AnthropicStreamingChatModelIT`, and ensured
all tests pass, as requested in the issue description. Some tests had to
be overridden, since structured outputs are still a beta feature in
Anthropic so models require a special configuration.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#2410Closes#3871
Replaces #2411
## Change
<!-- Please describe the changes you made. -->
Allows to set custom `ChatRequestParameters` when calling chat method on
`AiServices` interface.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Implements #
https://github.com/quarkiverse/quarkus-langchain4j/issues/1987#issuecomment-3627491222
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes#2600 (partially - extends PDF support with URL capability)
## Change
Add support for sending PDFs via URL to the Anthropic API, in addition
to the existing base64 support.
This enhancement aligns with [Anthropic's PDF Support
API](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support)
that accepts PDFs through URL sources:
```json
{
"type": "document",
"source": {
"type": "url",
"url": "https://example.com/document.pdf"
}
}
```
### Changes
- **AnthropicPdfContentSource**: Added `url` field and factory methods
`fromUrl()` and `fromBase64()`
- **AnthropicPdfContent**: Added factory methods `fromUrl()` and
`fromBase64()`
- **AnthropicMapper**: Updated to check for URL before falling back to
base64
### Usage
```java
// URL-based PDF (NEW)
UserMessage.from(PdfFileContent.from(URI.create("https://example.com/doc.pdf")))
// Base64 PDF (existing - unchanged)
UserMessage.from(PdfFileContent.from(base64Data, "application/pdf"))
```
### Integration Test Evidence
**Test:** `should_accept_pdf_from_url`
| Validation | Status |
|------------|--------|
| PDF URL correctly mapped to Anthropic API format | ✅ |
| Request sent with `"type": "url"` source | ✅ |
| Claude API responded with accurate document analysis | ✅ |
> ⚠️ **Note:** Integration tests with Google Cloud credentials are
expected to fail for fork PRs due to GitHub's security restrictions on
secrets.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
N/A
## Checklist for adding new embedding store integration
N/A
## Checklist for changing existing embedding store integration
N/A
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4098
## Change
This pull request provides a first implementation of the observability
features requested here
https://github.com/langchain4j/langchain4j/issues/4098
On top of it also introduces a way to monitor agents as discussed here
https://github.com/langchain4j/langchain4j/discussions/4008
The following explanation, copied from the updated documentation,
provides a recap of how this works.
### Observability
Tracking and logging the agents' invocations can be crucial for
debugging and understanding the aggregate behavior of the whole agentic
system in which those agents participate. For this reason, the
`langchain4j-agentic` module allows to register an `AgenticListener`
through the `listener` method of the agent builders, that is notified of
all agents invocations and their results, and it is defined as follows:
```java
public interface AgenticListener {
default void beforeAgentInvocation(AgentRequest agentRequest) { }
default void afterAgentInvocation(AgentResponse agentResponse) { }
default void onAgentInvocationError(AgentInvocationError agentInvocationError) { }
default void onAgenticScopeCreated(AgenticScope agenticScope) { }
default void onAgenticScopeDestroyed(AgenticScope agenticScope) { }
}
```
Note that all methods of this interface have a default empty
implementation, so that it is possible to implement only the methods of
interest. This will also allow to add new methods in future releases
without breaking existing implementations.
For instance the following configuration of the `CreativeWriter` agent
will log to the console when it is invoked and what is the story it
generated.
```java
CreativeWriter creativeWriter = AgenticServices.agentBuilder(CreativeWriter.class)
.chatModel(baseModel())
.outputKey("story")
.listener(new AgenticListener() {
@Override
public void beforeAgentInvocation(AgentRequest request) {
System.out.println("Invoking CreativeWriter with topic: " + request.inputs().get("topic"));
}
@Override
public void afterAgentInvocation(AgentResponse response) {
System.out.println("CreativeWriter generated this story: " + response.output());
}
})
.build();
```
These listener methods receive as argument respectively an
`AgentRequest` and an `AgentResponse` that provide useful information
about the agent invocation, like its name, the inputs it received and
the output it produced, together with the instance of the `AgenticScope`
used for that invocation. Note that these methods are invoked in the
same thread used to also perform the agent invocation, so they are
synchronous with it and should not perform long blocking operations.
Listeners are composable, meaning that you can register multiple
listeners to the same agent, by invoking the `listener` method more than
once, and they will be notified in the order they were registered. They
are also hierarchical, meaning that they are inherited by subagents, so
that if you register a listener to a top level agent, that listener will
also be notified of the invocations of all its subagents at any level
and composed with all listeners that these subagents could have
registered on their own.
### Monitoring
Leveraging the observability features provided by the `AgenticListener`
interface, the `langchain4j-agentic` module also provides a built-in
implementation of this interface, named `AgenticMonitor`, having the
goal of recording all agents invocations in an in-memory tree structure,
allowing to inspect the sequence of invocations and their results during
or after the execution of the agentic system. This monitor can be
registered as a listener to the root agent of the agentic system using
the `listener` method of the agent builder.
To provide a more comprehensive example, let's reconsider the loop
workflow intended to generate and iteratively refine a story until it
meets the required style quality, and register a few listeners on it,
including an `AgenticMonitor`.
```java
AgenticMonitor monitor = new AgenticMonitor();
CreativeWriter creativeWriter = AgenticServices.agentBuilder(CreativeWriter.class)
.listener(new AgenticListener() {
@Override
public void beforeAgentInvocation(AgentRequest request) {
System.out.println("Invoking CreativeWriter with topic: " + request.inputs().get("topic"));
}
})
.chatModel(baseModel())
.outputKey("story")
.build();
StyleEditor styleEditor = AgenticServices.agentBuilder(StyleEditor.class)
.chatModel(baseModel())
.outputKey("story")
.build();
StyleScorer styleScorer = AgenticServices.agentBuilder(StyleScorer.class)
.name("styleScorer")
.chatModel(baseModel())
.outputKey("score")
.build();
UntypedAgent styleReviewLoop = AgenticServices.loopBuilder()
.subAgents(styleScorer, styleEditor)
.maxIterations(5)
.exitCondition(agenticScope -> agenticScope.readState("score", 0.0) >= 0.8)
.build();
UntypedAgent styledWriter = AgenticServices.sequenceBuilder()
.subAgents(creativeWriter, styleReviewLoop)
.listener(new AgenticListener() {
@Override
public void afterAgentInvocation(AgentResponse response) {
if (response.agentName().equals("styleScorer")) {
System.out.println("Current score: " + response.output());
}
}
})
.listener(monitor)
.outputKey("story")
.build();
```
Here a first listener is registered directly on the `creativeWriter`
agent, so that it logs the request topic for the story to be generated
only when that agent is invoked. A second listener is registered on the
top level `styledWriter` agent, so that it will be also invoked for all
subagents in the hierarchy of that agent at any level. That is why the
`afterAgentInvocation` method of that listener checks if the agent being
invoked is the `styleScorer`, and only in that case it logs the current
score assigned to the style of the generated story.
Finally, the `AgenticMonitor` instance is also registered, and
automatically composed with the other 2 listeners, as a further listener
to the `styledWriter` top level agent, so that it can track all agents
invocations in the whole agentic system.
When invoking the `styledWriter` agent as follows:
```java
Map<String, Object> input = Map.of(
"topic", "dragons and wizards",
"style", "comedy");
String story = styledWriter.invoke(input);
```
the `AgenticMonitor` records all agents invocations in a tree structure
that also keeps track of the start time, finish time, duration, inputs
and output of each agent call. At this point it is possible to retrieve
the recorded executions from the monitor and for instance print it to
the console for inspection.
```java
MonitoredExecution execution = monitor.successfulExecutions().get(0);
System.out.println(execution);
```
so it will reveal the nested sequence of agents invocations necessary to
generate and refine the story, like it follows:
```
AgentCall{agent=Sequential, startTime=2025-12-04T17:23:45.684601233, finishTime=2025-12-04T17:25:31.310476077, duration=105625 ms, inputs={style=comedy, topic=dragons and wiz...}, output=In the shadowy ...}
|=> AgentCall{agent=generateStory, startTime=2025-12-04T17:23:45.687031946, finishTime=2025-12-04T17:23:53.216629832, duration=7529 ms, inputs={topic=dragons and wiz...}, output=In the shadowed...}
|=> AgentCall{agent=reviewLoop, startTime=2025-12-04T17:23:53.218004760, finishTime=2025-12-04T17:25:31.310442197, duration=98092 ms, inputs={score=0.85, topic=dragons and wiz..., style=comedy, story=In the shadowy ...}, output=null}
|=> AgentCall{agent=scoreStyle, startTime=2025-12-04T17:23:53.218606335, finishTime=2025-12-04T17:23:58.900747685, duration=5682 ms, inputs={style=comedy, story=In the shadowed...}, output=0.25}
|=> AgentCall{agent=editStory, startTime=2025-12-04T17:23:58.901041911, finishTime=2025-12-04T17:24:58.130857588, duration=59229 ms, inputs={style=comedy, story=In the shadowed...}, output=In the shadowy ...}
|=> AgentCall{agent=scoreStyle, startTime=2025-12-04T17:24:58.130980855, finishTime=2025-12-04T17:25:31.310076714, duration=33179 ms, inputs={style=comedy, story=In the shadowy ...}, output=0.85}
```
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
- Update to the Azure SDK 1.3.3, which fixes several transitive
dependencies vulnerabilities (specifically with Azure Identity)
- Update the OpenAI Official SDK to its latest version
- Started to modify the naming from Azure OpenAi to Microsoft Foundry
(the new official name)
- Replaced Dall-e 3.0 (which will be discontinued soon) by
gpt-image-1-mini
Document the usage of the CommandLineExecutionEngine for local code
execution with examples and Maven dependency.
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Add docs for
https://github.com/langchain4j/langchain4j-community/tree/main/code-execution-engines/langchain4j-community-code-execution-engine-local
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
The documentation lists only four chat message types, but there are
actually five: the missing one is CustomMessage, a newer type supported
in some models like Ollama. This causes confusion or mismatch in the
docs.
[//]: # (dependabot-start)
⚠️ **Dependabot is rebasing this PR** ⚠️
Rebasing might not happen immediately, so don't worry if this takes some
time.
Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.
---
[//]: # (dependabot-end)
Bumps [node-forge](https://github.com/digitalbazaar/forge) from 1.3.1 to
1.3.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/digitalbazaar/forge/blob/main/CHANGELOG.md">node-forge's
changelog</a>.</em></p>
<blockquote>
<h2>1.3.2 - 2025-11-25</h2>
<h3>Security</h3>
<ul>
<li><strong>HIGH</strong>: ASN.1 Validator Desynchronization
<ul>
<li>An Interpretation Conflict (CWE-436) vulnerability in node-forge
versions
1.3.1 and below enables remote, unauthenticated attackers to craft ASN.1
structures to desynchronize schema validations, yielding a semantic
divergence that may bypass downstream cryptographic verifications and
security decisions.</li>
<li>Reported by Hunter Wodzenski.</li>
<li>CVE ID: <a
href="https://www.cve.org/CVERecord?id=CVE-2025-12816">CVE-2025-12816</a></li>
<li>GHSA ID: <a
href="https://github.com/digitalbazaar/forge/security/advisories/GHSA-5gfm-wpxj-wjgq">GHSA-5gfm-wpxj-wjgq</a></li>
</ul>
</li>
<li><strong>HIGH</strong>: ASN.1 Unbounded Recursion
<ul>
<li>An Uncontrolled Recursion (CWE-674) vulnerability in node-forge
versions
1.3.1 and below enables remote, unauthenticated attackers to craft deep
ASN.1 structures that trigger unbounded recursive parsing. This leads to
a
Denial-of-Service (DoS) via stack exhaustion when parsing untrusted DER
inputs.</li>
<li>Reported by Hunter Wodzenski.</li>
<li>CVE ID: <a
href="https://www.cve.org/CVERecord?id=CVE-2025-66031">CVE-2025-66031</a></li>
<li>GHSA ID: <a
href="https://github.com/digitalbazaar/forge/security/advisories/GHSA-554w-wpv2-vw27">GHSA-554w-wpv2-vw27</a></li>
</ul>
</li>
<li><strong>MODERATE</strong>: ASN.1 OID Integer Truncation
<ul>
<li>An Integer Overflow (CWE-190) vulnerability in node-forge versions
1.3.1
and below enables remote, unauthenticated attackers to craft ASN.1
structures containing OIDs with oversized arcs. These arcs may be
decoded
as smaller, trusted OIDs due to 32-bit bitwise truncation, enabling the
bypass of downstream OID-based security decisions.</li>
<li>Reported by Hunter Wodzenski.</li>
<li>CVE ID: <a
href="https://www.cve.org/CVERecord?id=CVE-2025-66030">CVE-2025-66030</a></li>
<li>GHSA ID: <a
href="https://github.com/digitalbazaar/forge/security/advisories/GHSA-65ch-62r8-g69g">GHSA-65ch-62r8-g69g</a></li>
</ul>
</li>
</ul>
<h3>Fixed</h3>
<ul>
<li>[asn1] Fix for vulnerability identified by CVE-2025-12816 PKCS#12
MAC
verification bypass due to missing macData enforcement and improper
asn1.validate routine.</li>
<li>[asn1] Add <code>fromDer()</code> max recursion depth check.
<ul>
<li>Add a <code>asn1.maxDepth</code> global configurable maximum depth
of 256.</li>
<li>Add a <code>asn1.fromDer()</code> per-call <code>maxDepth</code>
option.</li>
<li><strong>NOTE</strong>: The default maximum is assumed to be higher
than needed for valid
data. If this assumption is false then this could be a breaking change.
Please file an issue if there are use cases that need a higher
maximum.</li>
<li><strong>NOTE</strong>: The per-call <code>maxDepth</code> parameter
has not been exposed up through
all of the API stack due to the complexities involved. Please file an
issue
if there are use cases that require this instead of changing the default
maximum.</li>
</ul>
</li>
<li>[asn1] Improve OID handling.
<ul>
<li>Error on parsed OID values larger than <code>2**32 - 1</code>.</li>
<li>Error on DER OID values larger than <code>2**53 - 1 </code>.</li>
</ul>
</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="235ad3e70e"><code>235ad3e</code></a>
Release 1.3.2.</li>
<li><a
href="2598244117"><code>2598244</code></a>
Update changelog.</li>
<li><a
href="0032dd0be8"><code>0032dd0</code></a>
Fix typos.</li>
<li><a
href="d75e08d255"><code>d75e08d</code></a>
Run new security test.</li>
<li><a
href="a5ce91d03d"><code>a5ce91d</code></a>
Update changelog formatting.</li>
<li><a
href="4652de6ddd"><code>4652de6</code></a>
Cleanups.</li>
<li><a
href="eb932d94fb"><code>eb932d9</code></a>
Fix typo.</li>
<li><a
href="db6954ba4b"><code>db6954b</code></a>
Fix style.</li>
<li><a
href="afbf7d8e08"><code>afbf7d8</code></a>
Align error message style.</li>
<li><a
href="6607445859"><code>6607445</code></a>
Revert minor changes.</li>
<li>Additional commits viewable in <a
href="https://github.com/digitalbazaar/forge/compare/v1.3.1...v1.3.2">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain4j/langchain4j/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Added instructions for enabling Java 21 preview features for Jlama.
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Bumps
[mdast-util-to-hast](https://github.com/syntax-tree/mdast-util-to-hast)
from 13.2.0 to 13.2.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/syntax-tree/mdast-util-to-hast/releases">mdast-util-to-hast's
releases</a>.</em></p>
<blockquote>
<h2>13.2.1</h2>
<h4>Fix</h4>
<ul>
<li>ab3a795 Fix support for spaces in class names</li>
</ul>
<h4>Types</h4>
<ul>
<li>efb5312 Refactor to use <code>@import</code>s</li>
<li>a5bc210 Add declaration maps</li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/syntax-tree/mdast-util-to-hast/compare/13.2.0...13.2.1">https://github.com/syntax-tree/mdast-util-to-hast/compare/13.2.0...13.2.1</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="174795b21f"><code>174795b</code></a>
13.2.1</li>
<li><a
href="3d05b3a715"><code>3d05b3a</code></a>
Update Node in Actions</li>
<li><a
href="ab3a79570a"><code>ab3a795</code></a>
Fix support for spaces in class names</li>
<li><a
href="efb5312310"><code>efb5312</code></a>
Refactor to use <code>@import</code>s</li>
<li><a
href="a5bc210f1a"><code>a5bc210</code></a>
Add declaration maps</li>
<li><a
href="b54955d4e1"><code>b54955d</code></a>
Add <code>.tsbuildinfo</code> to <code>.gitignore</code></li>
<li>See full diff in <a
href="https://github.com/syntax-tree/mdast-util-to-hast/compare/13.2.0...13.2.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain4j/langchain4j/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Julien Dubois <julien.dubois@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
Allow to optionally define agentic system variables in a strongly typed
way binding each variable to a class implementing the new `AgentState`
interface.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
- Add example links back to YugabyteDB embedding store documentation
- Examples are now available in langchain4j-examples repository
- Includes examples for basic usage, metadata filtering, PostgreSQL
driver, and Smart driver
Related PR: https://github.com/langchain4j/langchain4j-examples/pull/175
Reverts changes from:
5d837a7649
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [X] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [X] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
Fix https://github.com/langchain4j/langchain4j/issues/4118
## Change
- Added Duration duration() method to GuardrailExecutedEvent interface
and builder
- Implemented duration field in DefaultGuardrailExecutedEvent
- Modified AbstractGuardrailExecutor to measure execution time using
System.nanoTime()
- Duration is automatically captured around guardrail validation and
included in fired events
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Change
Noticed GoogleAiEmbeddingModel documentation was missing and the PaLM
models are removed: https://ai.google.dev/palm_docs/palm
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
## Issue
Progresses #3916
## Change
Added `GoogleAiGeminiBatchChatModel` and implemented 3 of the 6 APIs.
### APIs:
* `createBatchInline` - Creates a new batch job that returns a PENDING
operation/result. This can later be retrieved with
`retrievedBatchResults`.
[Documentation](https://ai.google.dev/gemini-api/docs/batch-api#create-batch-job)
* `retrieveBatchResults` - Retrieve a batch job for the given name. This
can return a BatchError(Whoops, something went wrong), BatchIncomplete
(Meaning it's still pending or running) or a BatchIncomplete which
contains the parsed results.
* `cancelBatchJob` - Returns nothing but will try to cancel a pending or
running job, throws otherwise.
### TODO:
* `deleteBatchJob` - Deletes a batch job no matter the state.
* `listBatchJobs` - Retrieves all the batch jobs - may use filters and
pagination to limit these.
* `createBatchFromFile` - Will need to implement the Files API as the
API takes a file reference.
This means batching works with this implementation but is missing some
useful APIs. It also limits users to batch sizes no larger than 20MB as
as the file API should be used for anything beyond that.
### Changes/Considerations:
* `GoogleAiGeminiBatchChatModel` is the new main API and re-uses the
`BaseGeminiChatModel` marked as `@Experimental`
* `Some helper methods moved from `GoogleAiGeminiChatModel` to
`BaseGeminiChatModel`
* All Request/Response records are grouped in `BatchRequestResponse` to
restrict the number of files added to the root package.
* Minor changes to `GeminiService` to allow different the use of
`HttpMethod.GET` and an empty Http body (Both are needed for
`retrieveBatchResults`)
* Added plenty of unit tests
* Added minimal Integration tests; The problem is that the time it takes
to create/process a batch is non-deterministic which means retrieving
erroneous and successful batches is impossible
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
---------
Co-authored-by: Mario Fusco <mario.fusco@gmail.com>
Co-authored-by: Julio <52171109+wadajo@users.noreply.github.com>
Co-authored-by: Xin Wang <xinwang@apache.org>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Co-authored-by: Óscar del Pozo <44649617+odelpozo-denodo@users.noreply.github.com>
Co-authored-by: Andrea Di Maio <85737936+andreadimaio@users.noreply.github.com>
Co-authored-by: Mathias Geat <mathias.geat@camunda.com>
Co-authored-by: Guillaume Laforge <glaforge@gmail.com>
Co-authored-by: Antonio Goncalves <antonio.goncalves@gmail.com>
Co-authored-by: Linn Aung <linnyehtutaung@gmail.com>
Co-authored-by: Hemanth Savasere <hemanth.savasere@gmail.com>
Co-authored-by: Oleksandr Klymenko <alexanderklmn@gmail.com>
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
Simplifies the agentic declarative API by getting rid of the no longer
necessary `@Subagent` annotation.
Note that this is a breaking change.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes #
## Change
This PR adds support for video content in OpenAI chat messages, enabling
the use of video URLs and base64-encoded videos in conversations.
This is particularly useful as some integrations like VLLMs work via
OpenAI classes, so we need Video support on it.
### Changes made:
- Added `VIDEO_URL` enum value to `ContentType`
- Created new `VideoUrl` class following the same pattern as `ImageUrl`
- Updated `Content` class to support video content with proper
serialization
- Extended `OpenAiUtils` with video content conversion logic (URL and
base64)
- Added helper methods `addVideoUrl()` and `addVideoUrls()` to
`UserMessage.Builder`
- Implemented comprehensive unit tests in `VideoContentConversionTest`
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
N/A
## Checklist for adding new embedding store integration
N/A
## Checklist for changing existing embedding store integration
N/A
## Issue
Closes #
## Change
Added a new builder method to the AIservices allowing us to pass a Set
of tool names. This will allow programmatically built tool to return
immediately the result of a tool execution request.
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4051
## Change
Add support for the ReasoningEffortValue parameter in the
AzureOpenAiChatModel and AzureOpenAiStreamingChatModel.java class. This
enhancement would:
Extend the AzureOpenAiChatModel.Builder to accept a reasoningEffort
parameter
Store the reasoningEffort value in the model configuration
Pass the reasoningEffort value to the ChatCompletionsOptions when making
API calls
Allow users to specify reasoning effort levels (LOW, MEDIUM, HIGH) for
GPT-5 models
This would enable full compatibility with GPT-5 (o1 series) models and
provide users with control over the reasoning compute effort.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
Creates a new module that will gather all the out-of-the-box guardrails
as discussed in https://github.com/langchain4j/langchain4j/issues/3248
## Change
* Added a new Maven module `langchain4j-guardrail` (I did not use the
plural `langchain4j-guardrails` because there is no other plural repo)
* Move the `JsonExtractorOutputGuardrail` (and test) from the core to
this new module (this introduces a breaking change as people have now to
depend on this module, and not just core, to get this guardrail)
* Updated the documentation to point at the new location of the
`JsonExtractorOutputGuardrailTests`
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!-- Please note that the maintainer of this repository (@dliubarskyi)
will be offline from 25 October till 10 November.
Please expect delays with processing. Thank you for your understanding.
-->
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Changes:
- Added new `WatsonxModerationModel` implementing LangChain4j's
`ModerationModel` interface
- Renamed `url()` to `baseUrl()` across all WatsonxLangChain4j model
builders for consistency
- Renamed `timeLimit()` to `timeout()` across all WatsonxLangChain4j
model builders for consistency
- Enhanced `WatsonxBuilder` with additional configuration options
(projectId, spaceId, timeout)
- Improved thinking configuration with better null handling and enabled
flag support
- Updated documentation
- Added test coverage
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!-- Please note that the maintainer of this repository (@dliubarskyi)
will be offline from 25 October till 10 November.
Please expect delays with processing. Thank you for your understanding.
-->
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
this is related to langchain4j-community: Add SQLServer 2025 embedding
store integration
([#432](https://github.com/langchain4j/langchain4j-community/pull/432))
## Change
<!-- Please describe the changes you made. -->
Added documentation for the new embedding store integration for SQL
Server 2025.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
Link was broken
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Custom agentic patterns
The `langchain4j-agentic` module provides out-of-the-box a few useful
agentic pattern, but what if none of them fit the specific needs of your
application? In this case it is possible to create your own custom
pattern, that orchestrates the interactions among a set of subagents in
a way that is tailored to your requirements.
In more details an agentic pattern is simply the specification of an
execution plan for the subagents that it coordinates. This plan can be
defined by implementing the following `Planner` interface:
```java
public interface Planner {
default void init(AgenticScope agenticScope, AgentInstance plannerAgent, List<AgentInstance> subagents) { }
default Action firstAction(AgenticScope agenticScope) {
return nextAction(agenticScope, null);
}
Action nextAction(AgenticScope agenticScope, AgentExecution previousAgentExecution);
}
```
This interface has three methods: `init`, `firstAction`, and
`nextAction`. The `init` method is called once at the beginning of the
execution, and can be used to initialize any state or data structures
needed by the planner. The `firstAction` method is called to determine
the first action to be taken by the agentic pattern, while the
`nextAction` method is called after each agent execution to determine
the next action to be taken based on the current state of the
`AgenticScope` and the result of the previous agent execution.
The `Action` class returned by the `firstAction` and `nextAction`
methods represents the next step to be taken by the agentic pattern, and
can be one either a list of one or more subagents to be called next, or
a signal that the execution has been completed. If the action specifies
only one subagent invocation, then it will be executed sequentially, and
in the same thread that is executing the planner itself, while if there
are more than one, they will be executed in parallel using the provided
`Executor` or the LangChain4j default one.
All the built-in agentic patterns are also written in terms of this
`Planner` abstraction and giving a look at their implementation can
clarify how this works and be a good starting point to create your own
custom patterns. For instance the parallel workflow is probably the
simplest of those implementation, and it is defined as follows:
```java
public class ParallelPlanner implements Planner {
private List<AgentInstance> agents;
@Override
public void init(AgenticScope agenticScope, AgentInstance plannerAgent, List<AgentInstance> subagents) {
this.agents = subagents;
}
@Override
public Action firstAction(AgenticScope agenticScope) {
return call(agents);
}
@Override
public Action nextAction(final AgenticScope agenticScope, final AgentExecution previousAgentExecution) {
return done();
}
}
```
Here the `init` method simply stores the list of subagents with which
the parallel workflow has been configured, while the `firstAction`
method returns an action that calls all those agents in parallel. Once
this parallel execution is completed, there isn't any other action to be
taken, so the `nextAction` method simply returns `done()` used to signal
the termination of the execution.
The `Planner` implementing the sequential workflow is only slightly more
complex, as it needs to keep track of the next subagent to be invoked
using an internal cursor, and then return the appropriate action in the
`nextAction` method or signal the termination of the execution when all
subagents have been invoked.
```java
public class SequentialPlanner implements Planner {
private List<AgentInstance> agents;
private int agentCursor = 0;
@Override
public void init(AgenticScope agenticScope, AgentInstance plannerAgent, List<AgentInstance> subagents) {
this.agents = subagents;
}
@Override
public Action nextAction(AgenticScope agenticScope, AgentExecution previousAgentExecution) {
return agentCursor >= agents.size() ? done() : call(agents.get(agentCursor++));
}
}
```
To understand how to define an agentic system from a planner
implementation, it is possible, for example, to create an instance of
the formerly discussed sequential workflow generating a novel for a
topic and then editing it for a specific style and audience, as it
follows:
```java
UntypedAgent novelCreator = AgenticServices.plannerBuilder()
.subAgents(creativeWriter, audienceEditor, styleEditor)
.outputKey("story")
.planner(SequentialPlanner::new)
.build();
```
which is totally equivalent to use the dedicated API for sequential
workflows:
```java
UntypedAgent novelCreator = AgenticServices.sequenceBuilder()
.subAgents(creativeWriter, audienceEditor, styleEditor)
.outputKey("story")
.build();
```
The `plannerBuilder()` method is similar to all other agent builders,
with the only difference that it requires to provide a
`Supplier<Planner>` returning a new instance of the specific planner to
be used by this agentic system. Of course an agentic system implementing
a custom planner can be seamlessly combined with any other of the
agentic pattern offered out-of-the-box by the `langchain4j-agentic`
module.
Having clarified how this `Planner` abstraction works, it is now
possible to create your own custom agentic patterns by implementing it.
The following sections provide two examples of custom patterns that can
be useful in different scenarios.
### Goal oriented agentic pattern
The workflow patterns and the supervisor agent represents the two
extremes of the spectrum of possible agentic systems: the former is
completely deterministic and rigid, forcing to decide in advance the
sequence of agents to be invoked, while the latter is completely
flexible and adaptive, but delegates the decision of the sequence of
agents to be invoked to a non-deterministic LLM. However, there are
cases where a middle ground between these two extremes can be more
appropriate, allowing agents to work towards a specific goal in a
relatively flexible way, but also determining how these agents should be
invoked in an algorithmic way.
In order to put this approach in practice, not only the whole agentic
system needs to define a goal, but also each subagent needs to declare
its own pre and postconditions. This is necessary to calculate the
sequence of agent invocations that lead to the achievement of the goal
in the fastest possible way. However, all this information are
implicitly already present in the agentic system, as those pre and
postconditions are nothing else than the required inputs and produced
outputs of each agent, and the final goal is simply the desired outputs
of the whole agentic system.
Following this idea, it is possible to calculate a dependency graph of
all the subagents participating in the agentic system, and then to
implement a `Planner` that is capable of analyzing the initial state of
the `AgenticScope`, comparing it with the desired goal, and then using
that graph to determine the sequence of agent invocations that can lead
to the achievement of that goal.
```java
public class GoalOrientedPlanner implements Planner {
private String goal;
private GoalOrientedSearchGraph graph;
private List<AgentInstance> path;
private int agentCursor = 0;
@Override
public void init(AgenticScope agenticScope, AgentInstance plannerAgent, List<AgentInstance> subagents) {
this.goal = plannerAgent.outputKey();
this.graph = new GoalOrientedSearchGraph(subagents);
}
@Override
public Action firstAction(AgenticScope agenticScope) {
path = graph.search(agenticScope.state().keySet(), goal);
if (path.isEmpty()) {
throw new IllegalStateException("No path found for goal: " + goal);
}
return call(path.get(agentCursor++));
}
@Override
public Action nextAction(AgenticScope agenticScope, AgentExecution previousAgentExecution) {
return agentCursor >= path.size() ? done() : call(path.get(agentCursor++));
}
}
```
As anticipated, here the goal coincides with the final output of the
planner-based agentic pattern itself, while the path from the initial
state to the goal is calculated using a `GoalOrientedSearchGraph`, that
is built analyzing the input and output keys of all subagents. The
sequence of agents to be invoked is then calculated as the shortest path
on that graph from the current state to the desired goal.
To give a practical example of how this works, let's try to build a
goal-oriented agentic system that can extract the name and zodiac sign
of a person from a prompt, generate the horoscope for that sign, look
for a related story on the internet and finally create a nice writeup
combining all this information. We can achieve this set of tasks by
using the following 5 agents:
```java
public interface HoroscopeGenerator {
@SystemMessage(
"""
You are an astrologist that generates horoscopes based on the user's name and zodiac sign.
""")
@UserMessage("""
Generate the horoscope for {{person}} who is a {{sign}}.
""")
@Agent("An astrologist that generates horoscopes based on the user's name and zodiac sign.")
String horoscope(@V("person") Person person, @V("sign") Sign sign);
}
public interface PersonExtractor {
@UserMessage("""
Extract a person from the following prompt: {{prompt}}
""")
@Agent("Extract a person from user's prompt")
Person extractPerson(@V("prompt") String prompt);
}
public interface SignExtractor {
@UserMessage("""
Extract the zodiac sign of a person from the following prompt: {{prompt}}
""")
@Agent("Extract a person from user's prompt")
Sign extractSign(@V("prompt") String prompt);
}
public interface Writer {
@UserMessage("""
Create an amusing writeup for {{person}} based on the following:
- their horoscope: {{horoscope}}
- a current news story: {{story}}
""")
@Agent("Create an amusing writeup for the target person based on their horoscope and current news stories")
String write(@V("person") Person person, @V("horoscope") String horoscope, @V("story") String story);
}
public interface StoryFinder {
@SystemMessage("""
You're a story finder, use the provided web search tools, calling it once and only once,
to find a fictional and funny story on the internet about the user provided topic.
""")
@UserMessage("""
Find a story on the internet for {{person}} who has the following horoscope: {{horoscope}}.
""")
@Agent("Find a story on the internet for a given person with a given horoscope")
String findStory(@V("person") Person person, @V("horoscope") String horoscope);
}
```
Leveraging the `GoalOrientedPlanner` developed before, these agents can
be combined in a goal-oriented agentic system as follows:
```java
HoroscopeGenerator horoscopeGenerator = AgenticServices.agentBuilder(HoroscopeGenerator.class)
.chatModel(baseModel())
.outputKey("horoscope")
.build();
PersonExtractor personExtractor = AgenticServices.agentBuilder(PersonExtractor.class)
.chatModel(baseModel())
.outputKey("person")
.build();
SignExtractor signExtractor = AgenticServices.agentBuilder(SignExtractor.class)
.chatModel(baseModel())
.outputKey("sign")
.build();
Writer writer = AgenticServices.agentBuilder(Writer.class)
.chatModel(baseModel())
.outputKey("writeup")
.build();
StoryFinder storyFinder = AgenticServices.agentBuilder(StoryFinder.class)
.chatModel(baseModel())
.tools(new WebSearchTool())
.outputKey("story")
.build();
UntypedAgent horoscopeAgent = AgenticServices.plannerBuilder()
.subAgents(horoscopeGenerator, personExtractor, signExtractor, writer, storyFinder)
.outputKey("writeup")
.planner(GoalOrientedPlanner::new)
.build();
```
As anticipated, the overall goal of this agentic system is to produce a
`writeup` which is also the output key of the GOAP-based planner itself.
Taking into account the inputs and outputs of all subagents, the
dependency graph built by the `GoalOrientedSearchGraph` will look like
this:
<img width="970" height="871" alt="goap"
src="https://github.com/user-attachments/assets/0249b79f-9839-427c-9548-58774c371c30"
/>
When invoking this agentic system with a prompt like "My name is Mario
and my zodiac sign is pisces"
```java
Map<String, Object> input = Map.of("prompt", "My name is Mario and my zodiac sign is pisces");
String writeup = horoscopeAgent.invoke(input);
```
the `GoalOrientedPlanner` will analyze the initial state of the
`AgenticScope`, that contains only the `prompt` variable, and then it
will calculate the shortest path on the dependency graph from that
initial state to the desired goal, which is the `writeup`, so that the
resulting sequence of agent invocations will be:
```
Agents path sequence: [extractPerson, extractSign, horoscope, findStory, write]
```
Note that, as anticipated, this goal-oriented agentic pattern can be
mixed and combined with any other of the existing agentic patterns. For
instance this possibility can be used to overcome an evident limitation
of this approach that, being optimized to reach a specific goal
following the shortest possible path, structurally doesn't allow loops,
so in some cases it could be useful to have a loop agentic pattern as a
subagent of this goal-oriented one.
### Peer-to-peer agentic pattern
All the agentic system discussed up to this point are based on a
centralized and hierarchical architecture. In fact all the workflow
patterns had a well-defined top-level agent coordinating the activities
of multiple sub-agents in a programmatically predetermined way. Even the
supervisor pattern, which is more flexible and dynamic thanks to the
presence of its LLM-based planner agent, still relies on a coordinator
agent that controls the interactions among the various sub-agents. This
typology of architectures are suitable for many applications and
scenarios, but they can also have some limitations, especially in terms
of scalability and fault tolerance. This is why we may want to offer an
alternative peer-to-peer approach for multi-agent systems, that can
overcome these limitations by adopting a more decentralized and
distributed strategy.
In a peer-to-peer agentic systems there isn't any top level agent, and
all agents are equal peers that are coordinated through the state of the
`AgenticScope`. In particular, an agent is triggered by the presence of
its own required inputs as state variables in the `AgenticScope`.
Subsequently, a change in one or more of those variables, produced by
the output of a different agent, can retrigger the invocation of that
agent again. The process terminates either when the `AgenticScope`
reaches a stable state and no agent can be invoked anymore, or when the
predefined exit condition is satisfied, or when a maximum number of
agent invocations has been reached. A `Planner` implementation that
realizes this peer-to-peer agentic pattern could be written as it
follows:
```java
public class P2PPlanner implements Planner {
private final int maxAgentsInvocations;
private final BiPredicate<AgenticScope, Integer> exitCondition;
private int invocationCounter = 0;
private Map<String, AgentActivator> agentActivators;
public P2PPlanner(int maxAgentsInvocations, BiPredicate<AgenticScope, Integer> exitCondition) {
this(null, maxAgentsInvocations, exitCondition);
}
@Override
public void init(AgenticScope agenticScope, AgentInstance plannerAgent, List<AgentInstance> subagents) {
this.agentActivators = subagents.stream().collect(toMap(AgentInstance::name, AgentActivator::new));
}
@Override
public Action nextAction(AgenticScope agenticScope, AgentExecution previousAgentExecution) {
if (terminated(agenticScope)) {
return done();
}
AgentActivator lastExecutedAgent = agentActivators.get(previousAgentExecution.agentSpec().uniqueName());
lastExecutedAgent.finishExecution();
agentActivators.values().forEach(a -> a.onStateChanged(lastExecutedAgent.agent.outputKey()));
AgentInstance[] agentsToCall = agentActivators.values().stream()
.filter(agentActivator -> agentActivator.canActivate(agenticScope))
.peek(AgentActivator::startExecution)
.map(AgentActivator::agent)
.toArray(AgentInstance[]::new);
invocationCounter += agentsToCall.length;
return call(agentsToCall);
}
private boolean terminated(AgenticScope agenticScope) {
return invocationCounter > maxAgentsInvocations || exitCondition.test(agenticScope, invocationCounter);
}
}
```
Here the `P2PPlanner` keeps track of the number of agent invocations
performed so far, and uses an `AgentActivator` for each subagent to
determine if it can be invoked based on the current state of the
`AgenticScope`. The `nextAction` method checks if the exit condition has
been met or if the maximum number of invocations has been reached, and
if not, it identifies all agents that can be activated based on the
current state, marks them as started, and returns an action to call
them.
To give a practical example of how this works let's try to build a
peer-to-peer agentic system that can perform a scientific research and
formulate new hypothesis on a given topic, so that the API of this
service could be something like:
```java
public interface ResearchAgent {
@Agent("Conduct research on a given topic")
String research(@V("topic") String topic);
}
```
To this purpose the following 5 agents can be defined:
```java
public interface LiteratureAgent {
@SystemMessage("Search for scientific literature on the given topic and return a summary of the findings.")
@UserMessage("""
You are a scientific literature search agent.
Your task is to find relevant scientific papers on the topic provided by the user and summarize them.
Use the provided tool to search for scientific papers and return a summary of your findings.
The topic is: {{topic}}
""")
@Agent("Search for scientific literature on a given topic")
String searchLiterature(@V("topic") String topic);
}
public interface HypothesisAgent {
@SystemMessage("Based on the research findings, formulate a clear and concise hypothesis related to the given topic.")
@UserMessage("""
You are a hypothesis formulation agent.
Your task is to formulate a clear and concise hypothesis based on the research findings provided by the user.
The topic is: {{topic}}
The research findings are: {{researchFindings}}
""")
@Agent("Formulate hypothesis around a give topic based on research findings")
String makeHypothesis(@V("topic") String topic, @V("researchFindings") String researchFindings);
}
public interface CriticAgent {
@SystemMessage("Critically evaluate the given hypothesis related to the specified topic. Provide constructive feedback and suggest improvements if necessary.")
@UserMessage("""
You are a critical evaluation agent.
Your task is to critically evaluate the hypothesis provided by the user in relation to the specified topic.
Provide constructive feedback and suggest improvements if necessary.
If you need to, you can also perform additional research to validate or confute the hypothesis using the provided tool.
The topic is: {{topic}}
The hypothesis is: {{hypothesis}}
""")
@Agent("Critically evaluate a hypothesis related to a given topic")
String criticHypothesis(@V("topic") String topic, @V("hypothesis") String hypothesis);
}
public interface ValidationAgent {
@SystemMessage("Validate the provided hypothesis on the given topic based on the critique provided.")
@UserMessage("""
You are a validation agent.
Your task is to validate the hypothesis provided by the user in relation to the specified topic based on the critique provided.
Validate the provided hypothesis, either confirming it or reformulating a different hypothesis based on the critique.
The topic is: {{topic}}
The hypothesis is: {{hypothesis}}
The critique is: {{critique}}
""")
@Agent("Validate a hypothesis based on a given topic and critique")
String validateHypothesis(@V("topic") String topic, @V("hypothesis") String hypothesis, @V("critique") String critique);
}
public interface ScorerAgent {
@SystemMessage("Score the provided hypothesis on the given topic based on the critique provided.")
@UserMessage("""
You are a scoring agent.
Your task is to score the hypothesis provided by the user in relation to the specified topic based on the critique provided.
Score the provided hypothesis on a scale from 0.0 to 1.0, where 0.0 means the hypothesis is completely invalid and 1.0 means the hypothesis is fully valid.
The topic is: {{topic}}
The hypothesis is: {{hypothesis}}
The critique is: {{critique}}
""")
@Agent("Score a hypothesis based on a given topic and critique")
double scoreHypothesis(@V("topic") String topic, @V("hypothesis") String hypothesis, @V("critique") String critique);
}
```
These agents will be all provided with a tool capable of performing
research on scientific literature, for instance downloading academic
papers from arXiv, and then added to the P2P agentic system:
```java
ArxivCrawler arxivCrawler = new ArxivCrawler();
LiteratureAgent literatureAgent = AgenticServices.agentBuilder(LiteratureAgent.class)
.chatModel(baseModel())
.tools(arxivCrawler)
.outputKey("researchFindings")
.build();
HypothesisAgent hypothesisAgent = AgenticServices.agentBuilder(HypothesisAgent.class)
.chatModel(baseModel())
.tools(arxivCrawler)
.outputKey("hypothesis")
.build();
CriticAgent criticAgent = AgenticServices.agentBuilder(CriticAgent.class)
.chatModel(baseModel())
.tools(arxivCrawler)
.outputKey("critique")
.build();
ValidationAgent validationAgent = AgenticServices.agentBuilder(ValidationAgent.class)
.chatModel(baseModel())
.tools(arxivCrawler)
.outputKey("hypothesis")
.build();
ScorerAgent scorerAgent = AgenticServices.agentBuilder(ScorerAgent.class)
.chatModel(baseModel())
.tools(arxivCrawler)
.outputKey("score")
.build();
ResearchAgent researcher = AgenticServices.plannerBuilder(ResearchAgent.class)
.subAgents(literatureAgent, hypothesisAgent, criticAgent, validationAgent, scorerAgent)
.outputKey("hypothesis")
.planner(() -> new P2PPlanner(10, agenticScope -> {
if (!agenticScope.hasState("score")) {
return false;
}
double score = agenticScope.readState("score", 0.0);
System.out.println("Current hypothesis score: " + score);
return score >= 0.85;
}))
.build();
String hypothesis = researcher.research("black holes");
```
With this configuration the `researcher` p2p coordinator is passed with
the topic of the research. At this point the only agent that can be
invoked is the `literatureAgent`, because it is the only one that has
all its required inputs, in this case the `topic`, present in the
`AgenticScope`. The invocation of this agent produces the
`researchFindings` variable, which is added to the `AgenticScope` state,
and this new variable triggers the invocation of the `HypothesisAgent`.
Then this produces a `hypothesis` that in turn triggers the
`criticAgent`. Finally, the `ValidationAgent` takes in input both the
`hypothesis` and the `critique` and generates a new `hypothesis` that
eventually retriggers the other agents again. In the meanwhile the
`ScorerAgent` gives a `score` to the `hypothesis` and the process
terminates when this `score` is greater than or equal to 0.85, or when a
maximum of 10 agents invocations have been performed. The following
image summarizes all the agents and variables involved in this
execution.
<img width="1693" height="1101" alt="p2p"
src="https://github.com/user-attachments/assets/38d96c6d-c4b8-49ac-ae5f-6741067a2ab7"
/>
For instance a typical run of this example could terminate because the
`ScorerAgent` produced a score above the predetermined threshold
```
Current hypothesis score: 0.95
```
and the final output could be something like:
```
Based on the provided references, here are some key points about stochastic gravitational wave backgrounds (SGWBs) from primordial black holes (PBHs):
1. **Detection Rates and Sources:**
- The detection rate of gravity waves emitted during parabolic encounters of stellar black holes in globular clusters was estimated by Kocsis et al. [85].
- Gravitational wave bursts from PBH hyperbolic encounters were discussed by García-Bellido and Nesseris [93].
2. **Energy Emission:**
- The energy spectrum of gravitational waves from hyperbolic encounters was studied by De Vittori, Jetzer, and Klein [88].
- Gravitational wave energy emission and detection rates for PBH hyperbolic encounters were analyzed by García-Bellido and Nesseris [90].
3. **Template Banks:**
- Template banks for gravitational waveforms from coalescing binary black holes (including non-spinning binaries) were developed by Ajith et al. [92].
4. **Constraints on PBHs:**
- Constraints on primordial black holes were reviewed by Carr, Kohri, Sendouda, and Yokoyama [98].
- Universal gravitational wave signatures of cosmological solitons were discussed by Lozanov, Sasaki, and Takhistov [100].
5. **Induced SGWBs:**
- Doubly peaked induced stochastic gravitational wave backgrounds were tested for baryogenesis from primordial black holes by Bhaumik et al. [101].
- Distinct signatures of spinning PBH domination and evaporation, including doubly peaked gravitational waves, dark relics, and CMB complementarity, were explored by Bhaumik et al. [101].
6. **Future Detectors:**
- Future detectors like Taiji, LISA, DECIGO, Big Bang Observer, Cosmic Explorer, Einstein Telescope, and KAGRA are expected to contribute significantly to the detection of SGWBs from PBHs.
7. **Pulsar Timing Arrays:**
- Pulsar timing arrays have been used to search for an isotropic stochastic gravitational wave background [73-75].
8. **Template Banks and Simulations:**
- Template banks like those developed by Ajith et al. are crucial for matching observed signals with theoretical predictions.
```
<!-- Please note that the maintainer of this repository (@dliubarskyi)
will be offline from 25 October till 10 November.
Please expect delays with processing. Thank you for your understanding.
-->
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3996
## Change
<!-- Please describe the changes you made. -->
occured → occurred
in
langchain4j-workers-ai\src\main\java\dev\langchain4j\model\workersai\WorkersAiImageModel.java
226
Syncronous → Synchronous
in docs\docs\integrations\language-models\mistral-ai.md 282 and 366
incoherrent → incoherent
in
langchain4j-bedrock\src\test\java\dev\langchain4j\model\bedrock\common\BedrockChatModelWithoutVisionIT.java
100
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: JustinChoi <justinchoi929@foxmail.com>
<!-- Please note that the maintainer of this repository (@dliubarskyi)
will be offline from 25 October till 10 November.
Please expect delays with processing. Thank you for your understanding.
-->
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
add Agentic AI to intro
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/1146
## Change
Implemented streaming cancellation for the following APIs:
- `StreamingChatModel` + `StreamingChatResponseHandler`
- `TokenStream`
Implemented streaming cancellation for the following modules:
- Anthropic
- Azure OpenAI
- Bedrock
- Google AI Gemini
- Mistral
- Ollama
- OpenAI
- OpenAI Official
- Vertex AI Gemini
## Examples
### `StreamingChatModel` + `StreamingChatResponseHandler` APIs
If you wish to cancel the streaming, you can do so from one of the
following `StreamingChatResponseHandler` methods:
- `onPartialResponse(PartialResponse, PartialResponseContext)`
- `onPartialThinking(PartialThinking, PartialThinkingContext)`
- `onPartialToolCall(PartialToolCall, PartialToolCallContext)`
The context object contains the `StreamingHandle`, which can be used to
cancel the streaming:
```java
model.chat(userMessage, new StreamingChatResponseHandler() {
@Override
public void onPartialResponse(PartialResponse partialResponse, PartialResponseContext context) {
process(partialResponse);
if (shouldCancel()) {
context.streamingHandle().cancel();
}
}
@Override
public void onCompleteResponse(ChatResponse completeResponse) {
System.out.println("onCompleteResponse: " + completeResponse);
}
@Override
public void onError(Throwable error) {
error.printStackTrace();
}
});
```
### `TokenStream` API
If you wish to cancel the streaming, you can do so from one of the
following callbacks:
- `onPartialResponseWithContext(BiConsumer<PartialResponse,
PartialResponseContext>)`
- `onPartialThinkingWithContext(BiConsumer<PartialThinking,
PartialThinkingContext>)`
For example:
```java
tokenStream
.onPartialResponseWithContext((PartialResponse partialResponse, PartialResponseContext context) -> {
process(partialResponse);
if (shouldCancel()) {
context.streamingHandle().cancel();
}
})
.onCompleteResponse((ChatResponse response) -> futureResponse.complete(response))
.onError((Throwable error) -> futureResponse.completeExceptionally(error))
.start();
```
When `StreamingHandle.cancel()` is called, LangChain4j will close the
connection and stop the streaming.
Once `StreamingHandle.cancel()` has been called, `TokenStream` will not
receive any further callbacks.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Update rag docs
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Update numbers in intro
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
open-ai-official was missing in supported language models list.
Add open-ai-official model to list
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Update chat memory docs
Currently, no document shows all supported Chat Memory Stores.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
- Remove example links from yugabyte docs that are not yet available
- Add note that examples will be added soon
Removes example links from YugabyteDB embedding store documentation.
Since the version is currently `1.8.0-beta15-SNAPSHOT` (not yet
released), the examples repository doesn't have these examples available
yet.
Current link:
90c2f0fae2
Examples PR currently under review, it will be merged once the version
is officially released.
Link: https://github.com/langchain4j/langchain4j-examples/pull/175
## Issue
Closes#3848
## Change
Rename `outputName` with `outputKey` in agentic module.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Change
- Upgraded **IBM watsonx-ai dependency** from `0.9.0` to ~`0.10.1`~
`0.11.0` and excluded Jackson transitive dependencies to prevent
conflicts.
- Updated `WatsonxChatModel` and `WatsonxStreamingChatModel` to allow
enabling **thinking mode** via parameters.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
mariadb was missing in supported embedding store list.
Add mariadb to embedding store list
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
Closes #
## Change
- Adds a new documentation page
`docs/docs/tutorials/otel-genai-instrumentation.md`.
- Explains how to enable OpenTelemetry GenAI tracing in Spring Boot apps
via the `langchain4j-otel` starter, links to the community repo, and
embeds a Grafana screenshot showing the telemetry in action.
## General checklist
- [x] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
- closes#3460
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
The pure agentic example code used `exchangeAgent` a non-existent agent
in the agentic tutorials.
https://docs.langchain4j.dev/tutorials/agents/#pure-agentic-ai
ExchangeAgent **exchange** = AgenticServices
.agentBuilder(ExchangeAgent.class)
.chatModel(BASE_MODEL)
.tools(new ExchangeTool())
.build();
SupervisorAgent bankSupervisor = AgenticServices
.supervisorBuilder()
.chatModel(PLANNER_MODEL)
.subAgents(withdrawAgent, creditAgent, **exchangeAgent**)
.responseStrategy(SupervisorResponseStrategy.SUMMARY)
.build();
This PR changed the `exchange` to `exchangeAgent` in tutorials docs and
tests(`SupervisorAgentIT`).
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
- Add comprehensive YugabyteDB embedding store documentation
- Include detailed API descriptions for YugabyteDBEmbeddingStore,
YugabyteDBEngine, and YugabyteDBSchema
- Add parameter summary tables for all configuration options
- Document vector index types (HNSW, NoIndex)
- Document metadata storage modes (JSONB, JSON, Column-per-key)
- Include usage examples for basic operations, indexes, metadata, and
driver configuration
- Document known limitations and performance considerations
- Add YugabyteDB to embedding stores comparison table
- Version: 1.8.0-beta15
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes#3810
## Change
Updated the docs home page to display features using a card view for
better readability.
<img width="1680" height="1050" alt="image"
src="https://github.com/user-attachments/assets/66149771-824d-4208-b1d4-c76e96d9786a"
/>
## General checklist
- [x] There are no breaking changes
- [ ] I have manually verified the change
- [ ] I have updated the documentation
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Introduce yaml document parser
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes (API, behaviour)
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
This pull request integrates GPU-accelerated large language model (LLM)
inference into LangChain4j by incorporating
GPULlama3.java](https://github.com/beehive-lab/GPULlama3.java), a
Java-native implementation of Llama3, Mistral, Phi-3, Qwen2.5, Qwen3 and
Disteled-DeepSeek models powered by TornadoVM.
Key Features:
* Multi-Model Support: Llama3, Mistral, Phi-3, Qwen2.5, Qwen3,
Distilled-DeepSeek.
* GPU Backends: Supports PTX (NVIDIA) and OpenCL devices (Intel/Apple
GPUs).
* CPU Fallback: Switch between GPU and pure-Java CPU execution
seamlessly, as GPULlama3.java extends the existing Llama3.java
implementation.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: ibriq <iain.apreotesei@gmail.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Co-authored-by: Orion Papadakis <orion.papadakis@manchester.ac.uk>
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/3213
## Change
Deprecated `HuggingFaceChatModel` and `HuggingFaceLanguageModel` which
do not longer work in favour of
`OpenAiChatModel` from the `langchain4j-open-ai` module.
If you wish to use [Hugging Face's Inference
Providers](https://huggingface.co/docs/inference-providers/en/index),
please use `OpenAiChatModel` or `OpenAiStreamingChatModel`:
Example:
```xml
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-open-ai</artifactId>
<version>1.6.0</version>
</dependency>
```
```java
ChatModel model = OpenAiChatModel.builder()
.apiKey(System.getenv("HF_API_KEY"))
.baseUrl("https://router.huggingface.co/v1")
.modelName("HuggingFaceTB/SmolLM3-3B:hf-inference")
.build();
StreamingChatModel streamingModel = OpenAiStreamingChatModel.builder()
.apiKey(System.getenv("HF_API_KEY"))
.baseUrl("https://router.huggingface.co/v1")
.modelName("HuggingFaceTB/SmolLM3-3B:hf-inference")
.build();
```
## General checklist
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
PR raised to open discussion for the implementation, it's only a
prototype for now.
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3493
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
This was initially implemented by @vijaypatidar
---
Implementing ChromaDB V2 API using LangChain4J HttpClient an jackson
Removing the use of retrofit
Upgrading testcontainers to be able to test against current ChromaDB
version( 1.1.0)
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Signed-off-by: Emmanuel Hugonnet <ehugonne@redhat.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
https://github.com/langchain4j/langchain4j/issues/3784
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Fixes#3780
## Change
Support anyOf and null JSON schema elements in googleai.SchemaMapper.
## General checklist
- [X] There are no breaking changes (API, behaviour)
- [X] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [X] I have manually run all the unit and ~integration~ tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Change
- Added LOGO_LICENSE.md in the root
- Added the std logo and the transparent version under docs/
## General checklist
- [V ] There are no breaking changes (API, behaviour)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3627
## Change
<!-- Please describe the changes you made. -->
Backport [auditing
capabilities](https://docs.quarkiverse.io/quarkus-langchain4j/dev/observability.html#_auditing)
from Quarkus LangChain4j.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#3629
## Change
<!-- Please describe the changes you made. -->
Add support for user-defined custom-parameters in OpenAI chat and
streaming chat models
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes (API, behaviour)
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Co-authored-by: JungAh <70677614+Jungahgo@users.noreply.github.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Introduce markdown document parser.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
Fix typo in 'Anthropic' reference
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
https://github.com/langchain4j/langchain4j/issues/3620
## Change
<!-- Please describe the changes you made. -->
This pull request introduces 2 agents listener:
1. `onAgentInvocation` invoked immediately before an agent is invoked
2. `onAgentCompletion` invoked immediatly after an agent invocation
returns
This is still a draft and in particular the documentation is still
missing because I would prefer to gather some feedback before writing
it.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
This pull request improves the exit condition of the agentic workflow
loop in 2 ways, optionally allowing to:
1. Also have the loop counter in the exit predicate
2. Testing the exit condition only at the end of the loop, instead of
after each agent invocation as it does by default
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Just the raw implementation + basic docs + basic tests that run against
the official registry (when/if we have our own MCP registry SDK, we
might want to switch to using that)
The next step will probably be some tooling to attempt to automatically
transform MCP server metadata into usable instances of `McpTransport`
(for building an actual MCP client that talks to the server) in cases
when it's possible...
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/3658
## Summary
- Added native support for AWS Bedrock's prompt caching functionality
- Reduces latency by up to 85% and costs by up to 90% for cached prompts
## Changes
- Added `promptCaching(BedrockCachePointPlacement)` method to
enable/disable prompt caching and specify cache point placement
- Added `BedrockCachePointPlacement` enum with options: AFTER_SYSTEM,
AFTER_USER_MESSAGE, AFTER_TOOLS
- Added comprehensive unit tests for all new functionality
## Usage Example
```java
BedrockChatRequestParameters params = BedrockChatRequestParameters.builder()
.promptCaching(BedrockCachePointPlacement.AFTER_SYSTEM)
.build();
```
## Testing
- All unit tests pass
- Maintains backward compatibility with existing code
- No breaking changes
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes #3635
## Change
Added support for receiving generated images from Gemini's image
generation models (e.g., gemini-2.5-flash-image-preview).
**Changes made:**
- Modified `PartsAndContentsMapper.fromGPartsToAiMessage()` to process
`inlineData` containing generated image data
- Added `GeneratedImageHelper` utility class for easy access to
generated images from `AiMessage.attributes()`
- Generated images are stored in `AiMessage.attributes()` under key
"generated_images"
- Solution works for both streaming and non-streaming responses
- Maintains full backward compatibility with existing code
**Technical details:**
- Processes Gemini response parts with `inlineData` and image mime types
- Converts base64 image data to `Image` objects
- Uses existing `attributes` mechanism to avoid breaking changes
- Includes comprehensive test coverage
This enables full Gemini image generation support while preserving the
existing architecture.
## General checklist
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
Clarify that only A2A Tasks are currently supported by the A2A
integration (not A2A Messages)
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
I started working on this change with the idea of making the
`HumanInTheLoop` non-blocking, meaning that the invocation is made on
another thread and the agentic system execution blocks only when the
result provided by the `HumanInTheLoop` is really necessary because it
is read as an input for another agent. Then I figured out that this
non-blocking feature was quite useful, so I decided to extend it to all
agents. In this way, for instance, it is possible to achieve a parallel
execution without using the parallel workflow, but simply putting the
non-blocking agents in sequence.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
### Summary
The Agents tutorial references a `StyleEditor` agent but does not
include its implementation.
This PR adds the missing `StyleEditor` interface, making the tutorial
complete and runnable.
### Details
The implementation was adapted from the example in
[`Agents.java`](https://github.com/langchain4j/langchain4j/blob/main/langchain4j-agentic-a2a/src/test/java/dev/langchain4j/agentic/a2a/Agents.java).
### Why
- Completes the tutorial so it is self-contained.
- Reduces confusion for new users.
- Maintains consistency with other agent interfaces such as
`AudienceEditor`.
Co-authored-by: Harikrishna <harikrishna.gurram@walmart.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Update the watsonx.ai SDK and implement the tokenization methods
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
Hi! I have started with the audio transcription and would like to get
feedback to ensure I'm heading in the right direction, as this is my
first PR for this project.
## Issue
Closes#255
## Change
Add Azure OpenAI
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and integration tests for my change
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [x] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Mohamed <mohamed.aitabderrahman@gmail.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes https://github.com/langchain4j/langchain4j-community/issues/269
## Change
<!-- Please describe the changes you made. -->
Added documentation about how to execute a Neo4j follow-up query after
an embedding search.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/124
## Change
This is a rework from scratch of what has been done in
https://github.com/langchain4j/langchain4j/pull/2291 and
https://github.com/langchain4j/langchain4j/pull/2772 also based on the
comments made during the review of those pull requests.
As I described in the Javadocs, here I added a `ReturnBehavior` enum
(names are very questionable and I'm open to change them if you have
better proposals) implementing 3 different behaviors for tools:
```
/**
* Return behavior of the tool.
* - If {@link ReturnBehavior#TO_LLM} is used (default), the value returned by the tool is sent back to the LLM for further processing.
* The LLM invocation will directly return the value returned by the last invoked tool, instead of the one further manipulated by the LLM,
* if and only if all the tools invoked by the LLM to fulfill the request are marked with {@link ReturnBehavior#DIRECT}.
* - If {@link ReturnBehavior#IMMEDIATE} is used, returns immediately to the caller the value returned by the tool without
* allowing the LLM to further processing it.
*
* @return return behavior of the tool.
*/
ReturnBehavior returnBehavior() default ReturnBehavior.TO_LLM;
```
The tests that I added should also help to clarify how this works.
Regarding the actual need for this feature, what has been discussed in
[this
article](https://quarkus.io/blog/agentic-ai-with-quarkus-p3/#comparing-the-workflow-and-agentic-approaches)
provides another example of a situation where this could be useful.
## General checklist
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Fixes#3596
## Change
Fix typo in pom type configuration tag
Corrects a typo in the documentation where the XML tag for pom type was
incorrectly written as `<typ>pom</typ>` instead of the proper
`<type>pom</type>`.
This change:
- Fixes invalid XML syntax in the configuration example
- Ensures consistency with standard Maven configuration conventions
- Prevents potential implementation issues when developers copy-paste
the snippet
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
https://github.com/langchain4j/langchain4j/issues/3532
## Change
<!-- Please describe the changes you made. -->
Allows to programmatically define the name and description of an agent
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
https://github.com/langchain4j/langchain4j/discussions/3509
## Change
<!-- Please describe the changes you made. -->
This pull request adds missing features the declarative API of the
agentic module.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes#3363
## Change
Introduced `ToolArgumentsErrorHandler` and `ToolExecutionErrorHandler`
that can be configured on the AI Service to handle errors related to
tools:
- when tool arguments cannot be parsed/prepared in order to execute a
tool
- when something wrong happens during tool execution
Currently, there are two ways to handle errors:
1. Throw an exception: this will stop the AI service flow.
2. Return a text message (e.g., an error description) that will be sent
back to the LLM,
allowing it to respond appropriately (for example, by correcting the
error and retrying).
## Example
```java
Assistant assistant = AiServices.builder(Assistant.class)
.chatModel(chatModel)
.tools(tools)
.toolArgumentsErrorHandler((error, context) -> ToolErrorHandlerResult.text("Can't parse tool arguments: " + error.getMessage()))
.toolExecutionErrorHandler((error, context) -> ToolErrorHandlerResult.text("Can't execute tool: " + error.getMessage()))
.build();
```
## Breaking Changes
This PR requires breaking changes in
`DefaultMcpClient.executeTool(ToolExecutionRequest)`: instead of
returning strings with error messages, `ToolArgumentsException`,
`ToolExecutionException` or `RuntimeException` will be thrown in case of
errors.
## General checklist
- [ ] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
The vast majority of long running operations, eventually running in
parallel, are I/O tasks and for this reason it is very beneficial to
execute them on virtual threads.
This pull request introduces a default executor, that should be used by
all parallel operations performed by langchain4j. When possible, i.e.
when running on Java 21+, this executor is a pool of virtual threads,
otherwise normal cached platform threads are used.
This pull request also contains a minor change in the agentic parallel
workflow, making it to use a more generic `Executor` instead of a more
restrictive `ExecutorService`.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Open #3526
## Change
- Add `businessContext` variable to help planning process more powerful
when handling real business
- Updated document
- Updated test
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Mario Fusco <mario.fusco@gmail.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
This is a PR to fix some minor wording problems. There is no
corresponding issue.
## Change
<!-- Please describe the changes you made. -->
Fixes minor wording problems in new agents.md file in the tutorial.
## General checklist
Not applicable. No code changes included in this PR (changes are all in
a .md file).
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes #
## Change
Added `JsonRawSchema` so that any existing raw schema (specified as a
`String`) can be used without reproducing it manually using the
`JsonSchemaElement`s builder.
Background is that we already have huge and well defined schemas in
resource-files, such as this
[process](https://json-schema.axonivy.com/process/12.0.0/process.json)
example.
Manually reproducing them is a show stopper.
Currently supported providers:
- [X] Azure OpenAI
- [X] Mistral
- [X] Ollama
- [X] OpenAI
- [X] OpenAI Official
## General checklist
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Change
The `McpToolProvider` has an implementation of a `ToolExecutor` used
internally.
This PR extracts it to a `McpToolExecutor` so it can be used outside the
`McpToolProvider`.
**Why doing this?**
To register tools for an AI service, there are a lot of different ways:
- using `AiService.tools(Object...)`
- using `AiService.toolProvider(ToolProvider)`
- using `AiSerice.tools(Map<ToolSpecification, ToolExecutor>)`
We use the latter in our code as we handle dynamically multiple types of
tools (WebSearch, MCP Client, custom tools, etc.). To be able to use it,
we have our own copy of the currently private MCP ToolExecutor.
With the change of this PR, we would be able to use the newly extracted
`McpToolExecutor` to register tools using
`AiSerice.tools(Map<ToolSpecification, ToolExecutor>)` instead of
copying its code to a custom class.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [x] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
## Issue
Closes#3290
## Change
Added an option to execute tools concurrently:
```java
/**
* By default, when the LLM calls multiple tools, the AI Service executes them sequentially.
* If you enable this option, tools will be executed concurrently (with one exception - see below),
* using the default {@link Executor}.
* You can also specify your own {@link Executor}, see {@link #executeToolsConcurrently(Executor)}.
* <ul>
* <li>When using {@link ChatModel}:</li>
* <ul>
* <li>When the LLM calls multiple tools, they are executed concurrently in separate threads
* using the {@link Executor}.</li>
* <li>When the LLM calls a single tool, it is executed in the same (caller) thread,
* the {@link Executor} is not used to avoid wasting resources.</li>
* </ul>
* <li>When using {@link StreamingChatModel}:</li>
* <ul>
* <li>When the LLM calls multiple tools, they are executed concurrently in separate threads
* using the {@link Executor}.
* Each tool is executed as soon as {@link StreamingChatResponseHandler#onCompleteToolCall(CompleteToolCall)}
* is called, without waiting for other tools or for the response streaming to complete.</li>
* <li>When the LLM calls a single tool, it is executed in a separate thread using the {@link Executor}.
* We cannot execute it in the same thread because, at that point,
* we do not yet know how many tools the LLM will call.</li>
* </ul>
* </ul>
*
* @return builder
* @see #executeToolsConcurrently(Executor)
* @since 1.4.0
*/
public AiServices<T> executeToolsConcurrently() {
context.toolService.executeToolsConcurrently();
return this;
}
/**
* See {@link #executeToolsConcurrently()}'s Javadoc for more info.
* <p>
* If {@code null} is specified, the default {@link Executor} will be used.
*
* @param executor The {@link Executor} to be used to execute tools.
* @return builder
* @see #executeToolsConcurrently()
* @since 1.4.0
*/
public AiServices<T> executeToolsConcurrently(Executor executor) {
context.toolService.executeToolsConcurrently(executor);
return this;
}
```
## General checklist
- [x] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
<!-- Please describe the changes you made. -->
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
<!--
Thank you so much for your contribution!
Please fill in all the sections below.
Please open the PR as a draft initially. Once it is reviewed and
approved, we will ask you to add documentation and examples.
Please note that PRs with breaking changes or without tests will be
rejected.
Please note that PRs will be reviewed based on the priority of the
issues they address.
We ask for your patience. We are doing our best to review your PR as
quickly as possible.
Please refrain from pinging and asking when it will be reviewed. Thank
you for understanding!
-->
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
This pull request introduces the new experimental `langchain4j-agentic`
module. The new module is built on top of the existing code and doesn't
affect it in any way.
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Bruno Baptista
Rui Yang