## Issue
Closes#5535
## Change
PR #2607 added `JlamaExceptionMapper` but wired it into `JlamaChatModel`
only. The four sibling models (`JlamaStreamingChatModel`,
`JlamaLanguageModel`, `JlamaStreamingLanguageModel`,
`JlamaEmbeddingModel`) used the 2-arg
`RetryUtils.withRetryMappingExceptions(action, maxRetries)`, which falls
back to `ExceptionMapper.DEFAULT`. DEFAULT cannot parse Jlama's
`IOException("HTTP response code: NNN ...")`, so download failures
(401/403/404) threw a generic `LangChain4jException` instead of the
intended `AuthenticationException` / `ModelNotFoundException`.
This passes `JlamaExceptionMapper.INSTANCE` to the 3-arg overload in all
four constructors, keeping the existing retry count of 2.
Compatibility: the error path stays a `RuntimeException`. The new types
(`AuthenticationException`, `ModelNotFoundException`) are subtypes of
the `LangChain4jException` that was thrown before, so existing broad
`catch (LangChain4jException)` handlers are unaffected — the change only
adds the specificity that `JlamaChatModel` already provides. The success
path is unchanged.
Precedent: merged PR #2986 (commit c78a65de6) fixed the same class of
sibling exception-mapping inconsistency in the OpenAI module.
Tests: new `JlamaUnexistingModelIT` with one `@Test` per sibling,
mirroring the accepted `JlamaUnexistingChatModelIT` pattern, asserting
`AuthenticationException`. These ITs are network-dependent and were NOT
run locally (project IT policy); the module unit build is green and the
IT compiles.
Diff size note: the functional change is four one-argument additions (`,
JlamaExceptionMapper.INSTANCE`) plus the new test file. The remaining
diff is Spotless auto-formatting: `langchain4j-jlama` is only built
under the `jdk21` profile and its sources were not Palantir-formatted,
so the Spotless `ratchetFrom origin/main` gate reformats each touched
file in full. The formatting was produced by `spotless:apply`, not by
hand.
Caveat: open PR #5442 reformats these same Jlama files and touches these
`withRetryMappingExceptions` lines, so a rebase will likely be needed
after either merges.
## 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 <!-- N/A:
existing positive-path coverage exists; this fix targets the negative
download-failure path only -->
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green <!-- N/A: ITs are
network-dependent, not run locally per project IT policy; module unit
build is green and the new IT compiles -->
- [ ] I have manually run all the unit and integration tests in the core
and main modules, and they are all green <!-- N/A: change is isolated to
langchain4j-jlama -->
- [ ] I have added/updated the documentation <!-- N/A:
behaviour-consistency bug fix, no doc change -->
- [ ] I have added an example in the examples repo (only for "big"
features) <!-- N/A -->
- [ ] I have added/updated Spring Boot starter(s) (if applicable) <!--
N/A -->
<!-- Checklist for adding new maven module: skipped, no new module. -->
<!-- Checklist for new/existing embedding store integration: skipped,
not an embedding store change. -->
## 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#3985
## Change
<!-- Please describe the changes you made. -->
### Summary
This PR adds a default `modelName()` method to `EmbeddingModel`, along
with overrides in most `EmbeddingModel` implementations.
### Details
- Added a default `modelName()` implementation returning `"unknown"` to
avoid breaking existing implementations.
- Added overrides in:
- `OpenAiEmbeddingModel`
- `LocalAiEmbeddingModel`
- `JlamaEmbeddingModel`
- `CohereEmbeddingModel`
- `GitHubModelsEmbeddingModel`
- `GoogleAiEmbeddingModel`
- `JinaEmbeddingModel`
- `MistralAiEmbeddingModel`
- `NomicEmbeddingModel`
- `OllamaEmbeddingModel`
- `OpenAiOfficialEmbeddingModel`
- `VertexAiEmbeddingModel`
- `VoyageAiEmbeddingModel`
- `WatsonxEmbeddingModel`
- `WorkersAiEmbeddingModel`
- Added fallback and override unit tests.
This provides a public accessor for embedding model names, as requested
in Issue #3985,
and keeps API behavior fully backward compatible.
## 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
## Issue
`OpenAiStreamingChatModel`, `OpenAiStreamingLanguageModel` and
`OpenAiModerationModel` are not mapping low-level `HttpException` to
common exceptions (e.g., `AuthenticationException` and
`RateLimitException`) like all other `OpenAi*Model` do.
## Change
Map exceptions for `OpenAiStreamingChatModel`,
`OpenAiStreamingLanguageModel` and `OpenAiModerationModel`
## General checklist
- [ ] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [x] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] 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)
## Change
- Added `maven-flatten-plugin` to `langchain4j-parent` and
`langchain4j-bom`
- Removed integration-specific dependencies from `langchain4j-parent`'s
`dependencyManagement` section and moved them to the modules where these
dependencies are used
- Explicitly added missing implicit dependencies
- Removed redundant `<maven.compiler.release>` for cassandra, infinispan
and opensearch modules
- Removed redundant license declarations and outdated properties
## General checklist
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [ ] 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)
## Issue
Fixes https://github.com/langchain4j/langchain4j/issues/2918
## Change
- Changed `maxRetry` parameter semantics from "max attempts" to "max
retries".
- Changed default value of the `maxRetry` parameter from 3 to 2, but it
does not change the default behaviour. When `maxRetries` parameter is
not specified explicitly, it will attempt to execute up to 3 times (as
it was before).
## Breaking Change
If you do **_not_** specify `maxRetries` parameter explicitly, there is
no breaking change and you do not need to do any changes to your code.
If you specify `maxRetries` parameter explicitly, you will need to
reduce it by 1, example:
```java
// before
OpenAiChatModel.builder()
.apiKey(System.getenv("OPENAI_API_KEY"))
.modelName(GPT_4_O_MINI)
.maxRetries(1)
.build();
// after
OpenAiChatModel.builder()
.apiKey(System.getenv("OPENAI_API_KEY"))
.modelName(GPT_4_O_MINI)
.maxRetries(0)
.build();
```
## General checklist
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [X] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [X] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Change
Renamed `ChatLanguageModel` into `ChatModel` and
`StreamingChatLanguageModel` into `StreamingChatModel`.
All `chatLanguageModel(...)` methods were renamed into `chatModel(...)`,
all `streamingChatLanguageModel(...)` methods were renamed into
`streamingChatModel(...)`.
`DisabledChatLanguageModel` was renamed into `DisabledChatModel`,
`DisabledStreamingChatLanguageModel` into `DisabledStreamingChatModel`.
### OpenRewrite recipe:
```yml
---
type: specs.openrewrite.org/v1beta/recipe
name: dev.langchain4j.RenameChatModels
recipeList:
- org.openrewrite.java.ChangeType:
oldFullyQualifiedTypeName: dev.langchain4j.model.chat.ChatLanguageModel
newFullyQualifiedTypeName: dev.langchain4j.model.chat.ChatModel
- org.openrewrite.java.ChangeType:
oldFullyQualifiedTypeName: dev.langchain4j.model.chat.StreamingChatLanguageModel
newFullyQualifiedTypeName: dev.langchain4j.model.chat.StreamingChatModel
- org.openrewrite.java.ChangeType:
oldFullyQualifiedTypeName: dev.langchain4j.model.chat.DisabledChatLanguageModel
newFullyQualifiedTypeName: dev.langchain4j.model.chat.DisabledChatModel
- org.openrewrite.java.ChangeType:
oldFullyQualifiedTypeName: dev.langchain4j.model.chat.DisabledStreamingChatLanguageModel
newFullyQualifiedTypeName: dev.langchain4j.model.chat.DisabledStreamingChatModel
- org.openrewrite.java.ChangeMethodName:
methodPattern: dev.langchain4j..* chatLanguageModel(..)
newMethodName: chatModel
- org.openrewrite.java.ChangeMethodName:
methodPattern: dev.langchain4j..* streamingChatLanguageModel(..)
newMethodName: streamingChatModel
```
## General checklist
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [x] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
github-actions[bot]