Bumps [dompurify](https://github.com/cure53/DOMPurify) from 3.3.3 to
3.4.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/cure53/DOMPurify/releases">dompurify's
releases</a>.</em></p>
<blockquote>
<h2>DOMPurify 3.4.0</h2>
<p><strong>Most relevant changes:</strong></p>
<ul>
<li>Fixed a problem with <code>FORBID_TAGS</code> not winning over
<code>ADD_TAGS</code>, thanks <a
href="https://github.com/kodareef5"><code>@kodareef5</code></a></li>
<li>Fixed several minor problems and typos regarding MathML attributes,
thanks <a
href="https://github.com/DavidOliver"><code>@DavidOliver</code></a></li>
<li>Fixed <code>ADD_ATTR</code>/<code>ADD_TAGS</code> function leaking
into subsequent array-based calls, thanks <a
href="https://github.com/1Jesper1"><code>@1Jesper1</code></a></li>
<li>Fixed a missing <code>SAFE_FOR_TEMPLATES</code> scrub in
<code>RETURN_DOM</code> path, thanks <a
href="https://github.com/bencalif"><code>@bencalif</code></a></li>
<li>Fixed a prototype pollution via
<code>CUSTOM_ELEMENT_HANDLING</code>, thanks <a
href="https://github.com/trace37labs"><code>@trace37labs</code></a></li>
<li>Fixed an issue with <code>ADD_TAGS</code> function form bypassing
<code>FORBID_TAGS</code>, thanks <a
href="https://github.com/eddieran"><code>@eddieran</code></a></li>
<li>Fixed an issue with <code>ADD_ATTR</code> predicates skipping URI
validation, thanks <a
href="https://github.com/christos-eth"><code>@christos-eth</code></a></li>
<li>Fixed an issue with <code>USE_PROFILES</code> prototype pollution,
thanks <a
href="https://github.com/christos-eth"><code>@christos-eth</code></a></li>
<li>Fixed an issue leading to possible mXSS via Re-Contextualization,
thanks <a
href="https://github.com/researchatfluidattacks"><code>@researchatfluidattacks</code></a>
and others</li>
<li>Fixed an issue with closing tags leading to possible mXSS, thanks <a
href="https://github.com/frevadiscor"><code>@frevadiscor</code></a></li>
<li>Fixed a problem with the type dentition patcher after Node version
bump</li>
<li>Fixed freezing BS runs by reducing the tested browsers array</li>
<li>Bumped several dependencies where possible</li>
<li>Added needed files for OpenSSF scorecard checks</li>
</ul>
<p><strong>Published Advisories are here:</strong>
<a
href="https://github.com/cure53/DOMPurify/security/advisories?state=published">https://github.com/cure53/DOMPurify/security/advisories?state=published</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="5b16e0b892"><code>5b16e0b</code></a>
Getting 3.x branch ready for 3.4.0 release (<a
href="https://redirect.github.com/cure53/DOMPurify/issues/1250">#1250</a>)</li>
<li>See full diff in <a
href="https://github.com/cure53/DOMPurify/compare/3.3.3...3.4.0">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 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>
## Change
- Added `OpenAiResponsesChatModel` as a non-streaming `ChatModel`
implementation backed by OpenAI `/v1/responses`.
- Extended `OpenAiResponsesClient` with synchronous `chat(...)` support
and response parsing for:
- assistant text output
- tool execution requests
- response metadata and token usage
- Added a new integration test `OpenAiResponsesChatModelIT` that
exercises a basic tool-calling flow:
- first request asks model to call `create_person`
- second request sends tool result
- final assertion verifies person details in assistant response
- Updated OpenAI docs to include non-streaming Responses API usage and
note GPT-5.4 requirement to use Responses API for tools + reasoning
effort.
## 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
## Validation performed
- `./mvnw -pl langchain4j-open-ai spotless:check`
- `./mvnw -pl langchain4j-open-ai -Dtest=OpenAiResponsesChatModelIT
-DfailIfNoTests=false test`
---------
Co-authored-by: Joshua Sperry <jrsperry@halosight.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
Bumps
[follow-redirects](https://github.com/follow-redirects/follow-redirects)
from 1.15.11 to 1.16.0.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="0c23a22306"><code>0c23a22</code></a>
Release version 1.16.0 of the npm package.</li>
<li><a
href="844c4d302a"><code>844c4d3</code></a>
Add sensitiveHeaders option.</li>
<li><a
href="5e8b8d024e"><code>5e8b8d0</code></a>
ci: add Node.js 24.x to the CI matrix</li>
<li><a
href="7953e2255a"><code>7953e22</code></a>
ci: upgrade GitHub Actions to use setup-node@v6 and checkout@v6</li>
<li><a
href="86dc1f86e4"><code>86dc1f8</code></a>
Sanitizing input.</li>
<li>See full diff in <a
href="https://github.com/follow-redirects/follow-redirects/compare/v1.15.11...v1.16.0">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 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>
Follow-up on #3816.
This PR tightens OpenAI Responses support in both official and
unofficial integrations:
- keep `strict` disabled by default and align Responses-mode JSON-schema
handling with actual supported behavior
- add explicit `previousResponseId` request parameters instead of shared
mutable model state
- restore unofficial client logging and remove extra local
`maxToolCalls` truncation
- improve streaming behavior and test coverage for
reasoning/tool-call/error/completion paths
- simplify Response-related AI-service test overrides via shared hooks
- add license metadata required for
`internal/langchain4j-internal-test-retry`
- fix brittle Vertex AI Anthropic integration-test initialization by
moving the quota-gating condition out of a class with provider-dependent
static initialization
## 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
- [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: Dmytro Liubarskyi <ljubarskij@gmail.com>
Adds a short ChatRequestOptions example to the Chat Model Observability
tutorial.
This documents how to pass per-invocation listener metadata via
listenerAttributes, and clarifies that these options stay within the
LangChain4j invocation chain and are not sent to the LLM provider.
## Issue
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4268
## Change
Documentation of the changes applied to the `langchain4j-spring`
project: the https://github.com/langchain4j/langchain4j-spring/pull/175
## 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
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/4652
## Change
- Add support for `@Tool`-annotated methods to return multimodal content
(images) to the LLM, not just text. Tools can now return `Image`,
`ImageContent`, `Content`, `List<Content>`, `Content[]`, etc.
- Refactor `ToolExecutionResultMessage` to store `List<Content>`
internally instead of a plain `String`, with backward-compatible
`text()` accessor and new `contents()` / `hasSingleText()`
methods.
- Refactor `ToolExecutionResult` to support
`resultContents(List<Content>)` as an alternative to
`resultText(String)` and `resultTextSupplier(Supplier)`.
- Implement multimodal tool result mapping for providers that support
it: Anthropic, Amazon Bedrock, and Google AI Gemini.
- Add `UnsupportedFeatureException` guards in providers that do not
support non-text tool results: Azure OpenAI, GitHub Models, Jlama,
Mistral AI, Ollama, OpenAI (Chat Completions
& Responses), Vertex AI (Anthropic & Gemini), Watsonx, and Workers AI.
- Update `ToolExecutedEvent` / `DefaultToolExecutedEvent` to carry
`resultContents` alongside the existing `resultText` accessor.
- Add comprehensive unit and integration tests
(`should_execute_tool_returning_Image`,
`should_execute_tool_returning_ImageContent`,
`should_execute_tool_returning_ContentList`,
`should_fail_when_tool_returns_image_and_provider_does_not_support_it`).
- Update tools documentation with new "Returning Images and Multimodal
Content" and "Multimodal Tool Results" sections.
## 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
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes #
## Change
The new section in the `agents.md` file explains how this new feature
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
add 'dependencies' tag in 'dependencyManagement'
<!--
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] -->
- [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
No issue opened.
## Changes
* Migrated from RestClient to ElasticsearchClient in embedding store and
related classes.
* Upgraded Elasticsearch to 9.3.1.
Now that the `ElasticsearchClient` can be super easily built with a
simple line like:
```java
ElasticsearchClient esClient = ElasticsearchClient.of(b -> b
.host(serverUrl)
.apiKey(apiKey)
);
```
We don't need to import the old Low Level rest client anymore.
I marked some of the old APIs as `@Deprecated`. I just don't know when
we are allowed to remove them.
Also this will make the documentation looking much better in
https://github.com/langchain4j/langchain4j-examples/tree/main/elasticsearch-example.
I'm in the process of updating also this examples repo...
## 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
- [ ] 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)
## Checklist for changing existing embedding store integration
- [X] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
Allows passing `_meta` fields for MCP client invocations. See the
`docs/docs/tutorials/mcp.md` file for explanation.
The first commit slightly reorganizes the internal protocol messages to
more closely mirror the MCP schema
(https://github.com/modelcontextprotocol/modelcontextprotocol/blob/2025-06-18/schema/2025-06-18/schema.json).
It doesn't introduce any breaking change. The gist is the introduction
of `McpClientRequest`,`McpClientResponse`,`McpClientNotification` in the
middle of the hierarchy to provide the proper distinction between these
types of messages. `McpClientRequest` and ,`McpClientNotification` now
contain a common `params` field instead of each implementation providing
its own field - instead, where appropriate, they have their own subclass
of `McpClientParams` to hold their specific params, so it's more
typesafe and the meta fields can be applied to each request type in a
unified way. I've also added javadoc comments to make it clear which
schema type each class corresponds to.
This is a prerequisite for proper implementation of distributed tracing
of MCP client
(https://github.com/quarkiverse/quarkus-langchain4j/issues/2221)
## Change
#### Skill-Scoped Tools
You can attach tools directly to a skill. These tools are **only exposed
to the LLM
after the skill has been activated** via the `activate_skill` tool.
This keeps the LLM's tool list small and focused, and ensures
skill-specific tools only
appear when they are relevant.
##### Using `@Tool`-Annotated Methods
The simplest way to attach tools is to pass objects with
`@Tool`-annotated methods:
```java
class OrderTools {
@Tool("Validates a customer order by ID")
String validateOrder(String orderId) {
// validation logic
return "valid";
}
@Tool("Charges payment for a customer order")
String chargePayment(String orderId) {
// payment logic
return "charged";
}
}
Skill skill = Skill.builder()
.name("process-order")
.description("Processes a customer order end-to-end")
.content("""
To process an order:
1. Call `validateOrder(orderId)` to check the order is valid.
2. Call `chargePayment(orderId)`.
""")
.tools(new OrderTools())
.build();
```
Tools can also be attached to an already-built skill using `toBuilder()`
— for example,
to add tools to a skill loaded from the file system:
```java
FileSystemSkill skill = FileSystemSkillLoader.loadSkill(Path.of("skills/process-order"));
Skill skillWithTools = skill.toBuilder()
.tools(new OrderTools())
.build();
```
##### Using Tool Providers
You can also attach `ToolProvider`s to a skill — for example, to expose
tools from an
MCP server only after the skill is activated:
```java
ToolProvider mcpToolProvider = McpToolProvider.builder()
.mcpClients(mcpClient)
.toolFilter((tool, mcpClient) -> tool.name().startsWith("inventory_"))
.build();
Skill skill = Skill.builder()
.name("inventory-management")
.description("Manages warehouse inventory")
.content("""
Use inventory tools to check stock levels and update quantities.
""")
.toolProviders(mcpToolProvider)
.build();
```
##### Using a `Map<ToolSpecification, ToolExecutor>`
For full control over tool specifications and execution logic, you can
pass a map directly:
```java
ToolSpecification validateOrder = ToolSpecification.builder()
.name("validateOrder")
.description("Validates a customer order by ID")
.addParameter("orderId", JsonSchemaProperty.STRING, JsonSchemaProperty.description("The order ID"))
.build();
ToolExecutor validateOrderExecutor = (request, memoryId) -> {
String orderId = parseOrderId(request.arguments());
return validate(orderId);
};
Skill skill = Skill.builder()
.name("process-order")
.description("Processes a customer order end-to-end")
.content("""
To process an order:
1. Call `validateOrder(orderId)` to check the order is valid.
""")
.tools(Map.of(validateOrder, validateOrderExecutor))
.build();
```
All three approaches can be combined — `@Tool` methods, `ToolProvider`s,
and `Map` entries
are merged into a single set of skill-scoped tools:
```java
Skill skill = Skill.builder()
.name("process-order")
.description("Processes a customer order end-to-end")
.content("...")
.tools(new OrderTools())
.tools(Map.of(validateOrder, validateOrderExecutor))
.toolProviders(mcpToolProvider)
.build();
```
##### Wiring It Up
```java
Skills skills = Skills.from(skill);
MyAiService service = AiServices.builder(MyAiService.class)
.chatModel(chatModel)
.chatMemory(MessageWindowChatMemory.withMaxMessages(100))
.toolProvider(skills.toolProvider())
.systemMessage("You have access to the following skills:\n" + skills.formatAvailableSkills()
+ "\nWhen the user's request relates to one of these skills, activate it first.")
.build();
```
##### How Skill-Scoped Tools Work
1. Before skill activation, the LLM only sees the `activate_skill` (and
`read_skill_resource`) tools.
Skill-scoped tools are not included in the tool list.
2. When the LLM calls `activate_skill("process-order")`, the activation
is recorded in the `ToolExecutionResultMessage`.
3. Before the next LLM call (within the same AI Service invocation), the
AI Service re-evaluates dynamic tool providers
against the current messages. The skill-scoped tools (e.g.
`validateOrder`) become
visible and the LLM can call them immediately, in the same AI Service
invocation.
The skill-scoped tools stay visible to the LLM in the next AI Service
invocations, they become invisible only when
the skill is deactivated.
##### Using Skills with Tool Search
Skills work alongside [Tool Search](/tutorials/tools#tool-search). When
both are configured,
they operate independently:
- **Skill-scoped tools are never searchable.** They don't appear in the
searchable tool pool
and cannot be found via `tool_search_tool`. They only become visible
after the LLM activates
the corresponding skill.
- **Regular tools remain searchable.** Tools registered via
`.tools(...)` on the AI Service
(not on a skill) continue to be searchable, regardless of whether any
skill is activated.
- **`activate_skill` is always visible.** It is marked as
`ALWAYS_VISIBLE`, so the LLM can
always call it even when Tool Search is enabled.
```java
Skills skills = Skills.from(mySkills);
MyAiService service = AiServices.builder(MyAiService.class)
.chatModel(chatModel)
.chatMemory(MessageWindowChatMemory.withMaxMessages(100))
.tools(new MySearchableTools()) // these are searchable
.toolProvider(skills.toolProvider()) // skill-scoped tools are NOT searchable
.toolSearchStrategy(new SimpleToolSearchStrategy())
.systemMessage("You have access to the following skills:\n" + skills.formatAvailableSkills()
+ "\nWhen the user's request relates to one of these skills, activate it first.")
.build();
```
## 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
<!-- Please specify the ID of the issue this PR is addressing. For
example: "Closes #1234" or "Fixes #1234" -->
Closes#4442
## 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
---------
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Summary
- add a dedicated docs page for the
`langchain4j-community-prompt-repetition` module
- add discovery links from the guardrails and RAG tutorials
- document the module as an experimental, ready-made prompt repetition
integration
## Details
This adds documentation in the main `langchain4j` docs site for the
community prompt repetition module introduced in
`langchain4j-community`.
It includes:
- a new integration page under `Integrations > Prompt Repetition`
- a short pointer from the guardrails tutorial to
`PromptRepeatingInputGuardrail`
- a short pointer from the RAG tutorial to `RepeatingQueryTransformer`
The docs position the module as:
- an optional community module
- an experimental but real integration, not just an evaluation harness
- inspired by the paper [Prompt Repetition Improves Non-Reasoning
LLMs](https://arxiv.org/html/2512.14982v1)
- a way to apply the core repeated-input transformation in LangChain4j
for eligible inputs
- something users should still validate on their own prompts, models,
and tasks
The wording intentionally avoids claiming that this module reproduces
the paper's full methodology or results.
## Issue
Closes#4725.
## Change
This PR switches `ElasticsearchConfiguration` from an abstract class to
an interface with default methods throwing an
`UnsupportedOperationException`.
This allows creating a self-made implementation. See the
`ElasticsearchConfigurationCustomIT` test and its
`ElasticsearchConfigurationCustom` class.
```java
public class ElasticsearchConfigurationCustom implements ElasticsearchConfiguration {
@Override
public SearchResponse<Document> vectorSearch(
ElasticsearchClient client, String indexName, EmbeddingSearchRequest embeddingSearchRequest)
throws ElasticsearchException {
// Implement here
}
}
```
## 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
- [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. -->
## 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#4543
## Change
Implemented support for **Structured Output** in AWS Bedrock, allowing
models to generate responses adhering to a specific JSON schema.
**Key changes:**
- **SDK Upgrade**: Upgraded `aws-java-sdk-bedrockruntime` from `2.33.5`
to `2.41.22` to access `OutputConfig` and `JsonSchemaDefinition` APIs.
- **New Feature**: Added `outputConfig` support to `ConverseRequest` in
`BedrockChatModel` and `BedrockStreamingChatModel`.
- **Schema Mapping**: Created `BedrockSchemaMapper` to convert
LangChain4j `JsonSchema` objects into AWS SDK `Document` format.
- **Validation**: Removed the `UnsupportedFeatureException` that was
previously thrown when `ResponseFormat.JSON` was requested.
## 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)
## Checklist for adding new maven module
- [ ] I have added my new module in the root
[pom.xml](cci:7://file:///Users/mohankumarsagadevan/Documents/projects/github/langchain4j/langchain4j-parent/pom.xml:0:0-0:0)
and
[langchain4j-bom/pom.xml](cci:7://file:///Users/mohankumarsagadevan/Documents/projects/github/langchain4j/langchain4j-bom/pom.xml:0:0-0:0)
## 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: Mohan Kumar Sagadevan <mohankumarsagadevan@Mohans-MacBook-Air.local>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Closes https://github.com/langchain4j/langchain4j/issues/4396
## Change
Introduces support for [Agent Skills](https://agentskills.io/home)
# Skills
:::note
The Skills API is experimental. APIs and behavior may still change in
future releases.
:::
Skills is a mechanism for equipping an LLM with reusable, self-contained
behavioral instructions.
A skill bundles a name, a short description, and a body of instructions
(its _content_),
together with optional resources (e.g., references, assets, templates,
etc.).
The LLM loads a skill on demand, keeping the initial context small and
only pulling in
the detailed instructions when they are actually needed.
:::note
Skills are designed according to the [Agent Skills
specification](https://agentskills.io).
:::
## Creating Skills
### From the File System
Typically, each skill lives in its own directory containing a `SKILL.md`
file.
The file must start with a YAML front matter block that declares the
skill's `name` and `description`.
Everything below the front matter becomes the skill's content — the
instructions given to the LLM
when it activates the skill.
```
skills/
├── docx/
│ ├── SKILL.md
│ └── references/
│ └── tracked-changes.md ← loaded as a resource
└── data-analysis/
└── SKILL.md
```
Example `SKILL.md`:
```markdown
---
name: docx
description: Edit and review Word documents using tracked changes
---
When the user asks you to edit a Word document:
1. Always use tracked changes so edits can be reviewed.
...
```
Any file in the skill directory (other than `SKILL.md` itself and files
under a `scripts/`
subdirectory) is automatically loaded as a `SkillResource` that the LLM
can read on demand.
Use `FileSystemSkillLoader` from the `langchain4j-skills` module to load
skills from the file system:
```xml
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-skills</artifactId>
<version>1.12.0-beta20</version>
</dependency>
```
```java
// Load all skills found in immediate subdirectories:
List<FileSystemSkill> skills = FileSystemSkillLoader.loadSkills(Path.of("skills/"));
// Or load a single skill by its directory:
FileSystemSkill skill = FileSystemSkillLoader.loadSkill(Path.of("skills/docx"));
```
### Programmatically
Skills do not have to be file-system based.
You can create them from any source — a database, a remote API,
generated at runtime — using the builder API:
```java
Skill skill = Skill.builder()
.name("incident-response")
.description("Step-by-step runbook for diagnosing and resolving production incidents")
.content("""
When a production alert fires:
1. Call `fetchRecentLogs(serviceName)` to retrieve the last 5 minutes of logs.
2. Call `checkServiceHealth(serviceName)` to get current health metrics.
3. Based on the findings, call `createIncidentTicket(summary, severity)`.
4. If severity is CRITICAL, also call `pageOnCall(incidentId)`.
""")
.build();
```
You can also attach resources programmatically:
```java
SkillResource reference = SkillResource.builder()
.relativePath("references/tone-guide.md")
.content("Use warm, concise language. Avoid jargon.")
.build();
Skill skill = Skill.builder()
.name("customer-support")
.description("Handles customer support inquiries")
.content("Follow the tone guide in references/tone-guide.md ...")
.resources(List.of(reference))
.build();
```
## Modes
Skills can be integrated with an AI Service in two distinct modes,
depending on how much
control and trust you need.
### Tool Mode (Recommended)
**Class:** `Skills` (from the `langchain4j-skills` module)
This corresponds to the **Tool-based agents** integration approach
described in the
[Agent Skills specification](https://agentskills.io/integrate-skills).
In this mode, the LLM activates a skill to receive step-by-step
instructions, then carries
them out by calling the [tools](/tutorials/tools) you have explicitly
registered.
**The LLM has no access to the file system at inference time** — all
skill content and
resources are loaded into memory upfront (e.g. via
`FileSystemSkillLoader`), and the `activate_skill`
and `read_skill_resource` tools returns that preloaded content rather
than reading from disk.
Because only your pre-defined tools can be invoked, **there is no risk
of arbitrary code execution**.
#### Registered Tools
| Tool | When registered |
|-----------------------|-----------------------------------------------------------------------------------------------|
| `activate_skill` | Always. The LLM calls this to load a skill's full
instructions into the context. |
| `read_skill_resource` | When at least one skill has resources. The LLM
calls this to read individual reference files. |
#### How It Works
1. The system message lists the available skills (names and
descriptions) so the LLM can choose.
2. The user asks a question that requires a specific skill.
3. The LLM calls `activate_skill("my-skill")` to receive its
instructions.
4. The LLM follows those instructions to complete the task, optionally
reading resource files along the way.
#### Example Skill
Skills describe the _policy_ — the exact order of calls, required
arguments, error-handling steps,
and worked examples — while the actual execution stays in type-safe,
tested Java code:
```markdown
---
name: process-order
description: Processes a customer order end-to-end
---
To process an order:
1. Call `validateOrder(orderId)` to check the order is valid.
2. Call `reserveInventory(orderId)` to reserve the required stock.
3. Only if reservation succeeds, call `chargePayment(orderId)`.
4. Finally, call `sendConfirmationEmail(orderId)`.
If any step fails, call `rollbackOrder(orderId)` before reporting the error.
```
#### Wiring It Up
Pass the `ToolProvider` from `Skills` to your AI Service builder
alongside your regular tools.
Use `formatAvailableSkills()` to inject the skill catalogue into the
system message so
the LLM knows which skills it can activate:
```java
Skills skills = Skills.from(FileSystemSkillLoader.loadSkills(Path.of("skills/")));
MyAiService service = AiServices.builder(MyAiService.class)
.chatModel(chatModel)
.tools(new OrderTools()) // your tools
.toolProvider(skills.toolProvider()) // or .toolProviders(mcpToolProvider, skills.toolProvider())
.systemMessage("You have access to the following skills:\n" + skills.formatAvailableSkills()
+ "\nWhen the user's request relates to one of these skills, activate it first using the `activate_skill` tool before proceeding.")
.build();
```
`formatAvailableSkills()` returns an XML-formatted block listing each
skill's name and description:
```xml
<available_skills>
<skill>
<name>process-order</name>
<description>Processes a customer order end-to-end</description>
</skill>
<skill>
<name>data-analysis</name>
<description>Analyse tabular data and produce charts</description>
</skill>
</available_skills>
```
#### Customisation
The name, description, and parameter metadata of each tool can be
overridden through the
corresponding config class on the builder:
```java
Skills skills = Skills.builder()
.skills(mySkills)
.activateSkillToolConfig(ActivateSkillToolConfig.builder()
.name(...) // tool name (default: "activate_skill")
.description(...) // tool description
.parameterName(...) // parameter name (default: "skill_name")
.parameterDescription(...) // parameter description
.throwToolArgumentsExceptions(...) // throw ToolArgumentsException instead of ToolExecutionException (default: false)
.build())
.readResourceToolConfig(ReadResourceToolConfig.builder()
.name(...) // tool name (default: "read_skill_resource")
.description(...) // tool description
.skillNameParameterName(...) // skill_name parameter name (default: "skill_name")
.skillNameParameterDescription(...) // skill_name parameter description
.relativePathParameterName(...) // relative_path parameter name (default: "relative_path")
.relativePathParameterDescription(...) // static description (takes precedence over provider)
.relativePathParameterDescriptionProvider(...) // dynamic description based on available resources
.throwToolArgumentsExceptions(...) // throw ToolArgumentsException instead of ToolExecutionException (default: false)
.build())
.build();
```
### Shell Mode (Experimental)
**Class:** `ShellSkills` (from the
`langchain4j-experimental-skills-shell` module)
This corresponds to the **Filesystem-based agents** integration approach
described in the
[Agent Skills specification](https://agentskills.io/integrate-skills).
:::warning
**Shell execution is inherently unsafe.**
Commands run directly in the host process environment **without any
sandboxing, containerization,
or privilege restriction**. A misbehaving or prompt-injected LLM can
execute arbitrary commands
on the machine running your application.
Only use this in controlled environments where you fully trust the input
and accept
the associated risks.
:::
In this mode, the LLM is given a single `run_shell_command` tool and
reads skill instructions
directly from the file system using shell commands. There is no
`activate_skill` or
`read_skill_resource` tool — the LLM navigates skill files like a human
developer would.
#### Registered Tools
| Tool | When registered |
|---------------------|---------------------------------------------------------------------------------------------------|
| `run_shell_command` | Always. The LLM runs shell commands to read
`SKILL.md` files, resource files and execute scripts. |
#### How It Works
1. The system message lists available skills with their absolute
filesystem paths.
2. The user asks a question that requires a specific skill.
3. The LLM runs `cat /path/to/skills/docx/SKILL.md` to read the
instructions.
4. The LLM follows those instructions by running further shell commands.
#### Dependency
Shell execution lives in a separate experimental artifact — add it to
your build:
```xml
<dependency>
<groupId>dev.langchain4j</groupId>
<artifactId>langchain4j-experimental-skills-shell</artifactId>
<version>1.12.0-beta20</version>
</dependency>
```
#### Wiring It Up
All skills must be filesystem-based (loaded via
`FileSystemSkillLoader`).
Use `ShellSkills` instead of `Skills`:
```java
ShellSkills skills = ShellSkills.from(FileSystemSkillLoader.loadSkills(Path.of("skills/")));
MyAiService service = AiServices.builder(MyAiService.class)
.chatModel(chatModel)
.toolProvider(skills.toolProvider()) // or .toolProviders(mcpToolProvider, skills.toolProvider())
.systemMessage("You have access to the following skills:\n" + skills.formatAvailableSkills()
+ "\nWhen the user's request relates to one of these skills, read its SKILL.md before proceeding.")
.build();
```
`formatAvailableSkills()` includes a `<location>` field so the LLM knows
exactly where to find each `SKILL.md`:
```xml
<available_skills>
<skill>
<name>docx</name>
<description>Edit and review Word documents using tracked changes</description>
<location>/path/to/skills/docx/SKILL.md</location>
</skill>
<skill>
<name>data-analysis</name>
<description>Analyse tabular data and produce charts</description>
<location>/path/to/skills/data-analysis/SKILL.md</location>
</skill>
</available_skills>
```
#### When to Use Shell Mode
This mode is best suited for **experimentation and prototyping**, or
when you want to use
third-party skills published by the community (e.g. from the
[agentskills.io](https://agentskills.io) ecosystem) without first
porting them to Java.
It lets you wire up a working workflow quickly, then migrate individual
actions
to tools as the solution matures.
#### Customisation
Use `RunShellCommandToolConfig` to tune the working directory, output
limits,
and parameter names:
```java
ShellSkills skills = ShellSkills.builder()
.skills(mySkills)
.runShellCommandToolConfig(RunShellCommandToolConfig.builder()
.name(...) // tool name (default: "run_shell_command")
.description(...) // tool description (default: includes OS name)
.commandParameterName(...) // command parameter name (default: "command")
.commandParameterDescription(...) // command parameter description
.timeoutSecondsParameterName(...) // timeout parameter name (default: "timeout_seconds")
.timeoutSecondsParameterDescription(...) // timeout parameter description
.workingDirectory(...) // working directory for commands (default: JVM's user.dir)
.maxStdOutChars(...) // max stdout chars in result (default: 10_000)
.maxStdErrChars(...) // max stderr chars in result (default: 10_000)
.executorService(...) // ExecutorService for reading stdout/stderr streams
.throwToolArgumentsExceptions(...) // throw ToolArgumentsException instead of ToolExecutionException (default: false)
.build())
.build();
```
## 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
- [X] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Issue
This PR adds observability support for `ModerationModel`
implementations, following the same patterns established for `ChatModel`
listeners. It introduces a new request/response API for moderation
operations and provides listener callbacks for monitoring moderation
requests, responses, and errors.
## Change
Commits:
1)
[f025c0f61](https://github.com/jeanbisutti/langchain4j/commit/f025c0f61)
- **Add ModerationRequest/ModerationResponse API to ModerationModel**
- Introduce `ModerationRequest` with builder pattern supporting both
text and messages
- Introduce `ModerationResponse` with metadata (model name, token usage,
finish reason)
- Add `moderate(ModerationRequest)` method to `ModerationModel`
interface
- Update all implementations (OpenAI, MistralAI, Watsonx) to support the
new API
- Add unit tests for request/response classes
2)
[aed77bf60](https://github.com/jeanbisutti/langchain4j/commit/aed77bf60)
- **Add moderation model listener support**
- Add `ModerationModelListener` interface with `onRequest`,
`onResponse`, `onError` callbacks
- Add context classes: `ModerationModelRequestContext`,
`ModerationModelResponseContext`, `ModerationModelErrorContext`
- Add `ModerationModelListenerUtils` for consistent listener invocation
across implementations
- Implement listener support in OpenAI, MistralAI, and Watsonx
moderation models
- Add `AbstractModerationModelListenerIT` base test class for consistent
testing
- Add documentation in observability tutorial
3)
[2c600cd90](https://github.com/jeanbisutti/langchain4j/commit/2c600cd90)
- **Refactoring - Add toInputs and toText utility methods to
ModerationModel**
- Extract common `toInputs()` and `toText()` utility methods to
`ModerationModel` interface
- Remove duplicate code from OpenAI, MistralAI, and Watsonx
implementations
**Backward Compatibility:** The existing `moderate(String text)` and
`moderate(ChatMessage... messages)` methods remain unchanged. The new
`moderate(ModerationRequest)` API is additive. Listener support is
opt-in via builder 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 #
## Change
Allows agents to be monitored by simply extending the new
`MonitoredAgent` interface. This will be convenient especially using the
declarative API, so that the `AgentMonitor` could be directly retrieved
from the top level agent instance.
## 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#4490
## 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
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>
Dmytro Liubarskyi
Rui Yang