## Issue
Closes#1153 — distinguish APIs for embedding queries vs. documents/keys
(adds `EmbeddingInputType.QUERY`/`DOCUMENT` as a per-call parameter,
plus opt-in `embeddingInputType(...)` on
`EmbeddingStoreContentRetriever` / `EmbeddingStoreIngestor`).
Partially addresses #4019 — adds the multimodal image-embedding API at
the core level (`EmbeddingInput` of `Content` parts) and wires Cohere,
Voyage, Jina, Google (Gemini Embedding 2), and Bedrock Titan; does
not implement it for `OnnxEmbeddingModel`.
Relates to #5142 — provider-specific / per-call parameters for OpenAI
embeddings (`OpenAiEmbeddingRequestParameters`: `user`,
`encodingFormat`, `customParameters`; e.g. NVIDIA NIM `input_type` via
custom
parameters).
Relates to #4273 — observability for `EmbeddingModel` via listeners
(`EmbeddingModelListener` + request/response/error contexts, wired
across providers).
## Change
Introduces an `EmbeddingModel.embed(EmbeddingRequest) →
EmbeddingResponse` API, structured like `ChatModel`'s request/response
API, so embeddings can carry **per-call parameters** and **multimodal
inputs** and
participate in **observability**. Everything is additive and
`@Experimental`; the existing `embed(String)` / `embed(TextSegment)` /
`embedAll(List)` methods keep working unchanged.
### Core (`langchain4j-core`)
- New request/response types: `EmbeddingRequest`, `EmbeddingResponse`,
`EmbeddingResponseMetadata`, `EmbeddingRequestParameters` (+
`DefaultEmbeddingRequestParameters` and typed `EmbeddingParameter<T>`
tokens), `EmbeddingInput`, `EmbeddingInputType`.
- New default methods on `EmbeddingModel`: `embed(EmbeddingRequest)`,
`doEmbed(...)`, `defaultRequestParameters()`, `supportedParameters()`,
`supportedContentTypes()`, `provider()`, `listeners()`.
- **Strict opt-in / fail-fast:** per-call parameters and content types
are token/type-checked; a request that uses something the model doesn't
declare is rejected with `UnsupportedFeatureException` instead of
being silently ignored. `overrideWith` preserves the provider-specific
parameters subtype (as on the chat side).
- **Multimodal:** an `EmbeddingInput` is an ordered list of `Content`
parts (text/image); models fuse them into one embedding (or
one-per-item, per provider). Modality is auto-detected — no manual flag.
- **Observability:** `EmbeddingModelListener` + request/response/error
contexts (same shape as `ChatModelListener`), fired inline from
`embed(EmbeddingRequest)`. `addListener(...)` still works.
- **RAG opt-in:** `EmbeddingStoreContentRetriever` and
`EmbeddingStoreIngestor` gain an optional `embeddingInputType(...)`
(QUERY / DOCUMENT). Default behavior is unchanged (no input type sent).
- `ModelProvider`: added `COHERE`, `VOYAGE_AI`, `JINA`, with matching
OpenTelemetry `gen_ai.provider.name` mappings (`cohere` is a well-known
OTel value; `voyage_ai` / `jina` are custom, as permitted by the
spec).
### Providers
- **OpenAI** (dimensions, `user`/`encodingFormat`/custom params),
**Cohere** (Embed v4 multimodal + input types), **Voyage** (multimodal +
input types), **Jina** (CLIP multimodal), **Google AI Gemini** (input
types; **Gemini Embedding 2** multimodal), **Amazon Bedrock Titan**
(multimodal).
- **Google Gen AI** (`langchain4j-google-genai`): input type → SDK
`task_type`, per-call dimensions → `outputDimensionality`, `provider()`,
listeners.
- **Ollama**: text-only — `provider()` + listeners (per-call params
correctly fail fast).
- **In-process models** (ONNX / `AbstractInProcessEmbeddingModel`):
already work via the default `doEmbed→embedAll` bridge (text-only,
image/param requests fail fast); observability via `addListener(...)`.
No
code change (no builders to wire listeners into, no dedicated
`ModelProvider`).
- **Gemini Embedding 2** dropped the `task_type` parameter, so input
types are applied as prompt instructions (`task: search result | query:
…` / `title: none | text: …`) automatically; `gemini-embedding-001`
still uses `task_type`.
- `modelName` in the response metadata reflects the API-reported model
where the provider returns one (OpenAI/Voyage/Jina), falling back to the
configured name.
### Tests
- `AbstractEmbeddingModelIT` — a shared IT base (like
`AbstractChatModelIT`) covering the new API, convenience methods,
listeners, and fail-fast; each provider adds a small
`common/…EmbeddingModelIT` that
parameterizes it and declares its capabilities via `supports*()`
overrides.
- Mock-based unit tests per provider for wire format / routing /
fail-fast (run in CI without keys), plus core value-type and listener
tests.
### Docs
- Embedding-model section in the RAG tutorial (request/response,
multimodal, query-vs-document opt-in), the EmbeddingModel listener
section in the Observability tutorial, the embedding contribution
guidance in
`CONTRIBUTING.md`, and the six provider integration pages.
### Notes
- `EmbeddingResponseMetadata` intentionally has no `finishReason`
(embeddings have no finish reason). No real provider is affected: the
only provider that emits `STOP` (Cloudflare WorkersAI) overrides the
convenience methods directly, and every other provider always returned
`null` here.
- `revapi.json` suppressions were added where the new (non-breaking)
types are exposed in provider APIs.
## 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 added/updated the documentation
- [ ] I have manually run all the unit and integration tests in the core
and main modules, and they are all green
- [ ] I have added an example in the examples repo (only for "big"
features)
- [ ] I have added/updated Spring Boot starter(s) (if applicable)
---------
Co-authored-by: agent <agent@langchain4j.dev>
## Issue
<!-- Please specify the ID of the issue this PR is addressing. -->
N/A - routine dependency maintenance prompted by the new Azure Java SDK
release.
## Change
Bumps `com.azure:azure-sdk-bom` from `1.3.5` to `1.3.7` (latest). Most
managed libraries are minor/patch bumps, but the new BOM pulls two
changes that require work:
- **`azure-search-documents` 11.8.1 -> 12.0.0** (major release) used by
`langchain4j-azure-ai-search`.
- **`azure-core` 1.57.1 -> 1.58.0**, which shifts the required
Netty/Reactor stack.
**azure-search-documents 12.0.0 migration**
(`langchain4j-azure-ai-search`). The public langchain4j API of the
module is unchanged; only the internal calls into the Azure SDK were
rewritten:
- `search(text, options, Context)` ->
`search(options.setSearchText(text))`
- `SearchDocument` / `getDocument(...)` removed -> read fields via
`SearchResult.getAdditionalProperties()` (a `Map`)
- `uploadDocuments` / `deleteDocuments` removed ->
`indexDocuments(IndexDocumentsBatch)` built from `IndexAction`s (new
private `toUploadBatch` / `toSearchDocument` helpers)
- `VectorSearchOptions` / `SemanticSearchOptions` removed ->
`setVectorQueries(...)` and `setSemanticConfigurationName(...)`
- `getSemanticSearch().getRerankerScore()` -> `getRerankerScore()`;
`setKNearestNeighborsCount` -> `setKNearestNeighbors`; `new
SearchIndex(name, fields)` constructor
**Dependency re-alignment.** The bump to `azure-core 1.58.0` raises the
minimum Netty/Reactor versions, so the local `dependencyManagement`
workaround pins in `github-models`, `azure-cosmos-nosql`,
`document-loader-azure-storage-blob`, and
`code-execution-engine-azure-acads` were updated (`reactor-core 3.7.17`,
`reactor-netty-http 1.2.16`, `azure-core-http-netty 1.16.4` and
siblings, `netty-bom 4.1.132.Final`) so the `maven-enforcer`
`RequireUpperBoundDeps` rule keeps passing.
Note for reviewers: this is a major version jump of
`azure-search-documents`, so please give the rewritten index/read/write
paths in `AbstractAzureAiSearchEmbeddingStore` a careful look. End-user
behaviour of the module is intended to be unchanged. Integration tests
require live Azure credentials and were not run; all unit tests pass
locally across every affected Azure module.
## 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 - no new module.
## Checklist for adding new embedding store integration
N/A - no new embedding store integration.
## Checklist for changing existing embedding store integration
- [ ] I have manually verified that the `AzureAiSearchEmbeddingStore`
works correctly with the data persisted using the latest released
version of LangChain4j
<!-- Integration tests require live Azure resources; the existing IT
compiles but was not executed in this change. -->
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
## Summary
Removed 18 unused import statements from 17 source files across multiple
modules.
### Modules affected
- `langchain4j-core` (6 files)
- `langchain4j` (3 files)
- `langchain4j-azure-ai-search`
- `langchain4j-cassandra`
- `langchain4j-couchbase`
- `langchain4j-agentic`
- `langchain4j-agentic-mcp`
- `langchain4j-local-ai`
- `langchain4j-workers-ai`
- `document-loaders/langchain4j-document-loader-azure-storage-blob`
### Verification
Each import was verified to be unused — the imported symbol does not
appear in any non-import line of its file (including javadoc `@link` and
`@see` tags).
## 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)
<!--
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#2502
## Change
<!-- Please describe the changes you made. -->
Add document.setMetadata to
AzureAiSearchContentRetriever.add(List<TextSegment>) to avoid metadata
loss
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [X] There are no breaking changes
- [x] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [x] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] 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: Riccardo Vasumini <riccardo.vasumini@agilelab.it>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Issue
Cleanup repeating dependencies in pom.xml. Better test assertions and
apidocs/javadoc generation.
## Change
Refactor project structure and remove unused test dependencies.
- Repeating test dependencies like `tinylog`, `awaitility` and others
were removed from various modules and consolidated in the parent module.
This reduction in clutter helps to streamline the testing process.
- A separate `kotlin` profile was created to manage Kotlin-related
configurations and dependencies.
- Upgraded versions of dependencies like `ai-mocks` and `wiremock` were
implemented. Moved to wiremock-standalone (shaded jar) to avoid
potential version conflicts with runtime classes.
- The test changes in `ChatRequestExtensionsTest.kt` partially migrated
from AssertJ to Kotest assertions.
- Updated Dokka plugin configuration
## 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
- [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
Streamline maven dependencies
Should fix [this
issue](https://github.com/langchain4j/langchain4j/actions/runs/13666001227/job/38207360909?pr=2640#step:5:16630)
```
2025/03/05 00:52:59,050 3922 [INFO ] [main] netty.implementation.NettyUtility - {"az.sdk.message":"The following Netty versions were found on the classpath and have a mismatch with the versions used by azure-core-http-netty. If your application runs without issue this message can be ignored, otherwise please align the Netty versions used in your application. For more information, see https://aka.ms/azsdk/java/dependency/troubleshoot.","azure-netty-version":"4.1.118.Final","azure-netty-native-version":"2.0.70.Final","classpath-netty-version-io.netty:netty-common":"4.1.115.Final","classpath-netty-version-io.netty:netty-handler":"4.1.110.Final","classpath-netty-version-io.netty:netty-handler-proxy":"4.1.110.Final","classpath-netty-version-io.netty:netty-buffer":"4.1.110.Final","classpath-netty-version-io.netty:netty-codec":"4.1.110.Final","classpath-netty-version-io.netty:netty-codec-http":"4.1.110.Final","classpath-netty-version-io.netty:netty-codec-http2":"4.1.110.Final","classpath-netty-version-io.netty:netty-transport-native-unix-common":"4.1.110.Final","classpath-netty-version-io.netty:netty-transport-native-epoll":"4.1.110.Final","classpath-netty-version-io.netty:netty-transport-native-kqueue":"4.1.118.Final","classpath-native-netty-version-io.netty:netty-tcnative-boringssl-static":"2.0.70.Final"}
```
## Change
This pull request includes the following changes to improve project
dependency management:
- Removed unnecessary and redundant Netty dependencies and exclusions.
- Updated and reorganized dependency versions for consistency, including
new BOM imports for Azure SDK, Netty, and Reactor.
- Eliminated AWS SDK v1 dependencies, transitioning to
`software.amazon.awssdk` BOM for better compatibility and reduced
clutter.
- Removed redundant test dependencies like `assertj-core` and `mockito`
across modules, referring to the parent POM.
- Adjusted `kotlinx-coroutines-test` to use JVM-specific artifact and
standardized dependency version variables.
- Refined POM XML formatting for consistency and clarity (`mvn
spotless:apply`)
## General checklist
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] There are no breaking changes
- [ ] I have added unit and/or integration tests for my change
- [ ] The tests cover both positive and negative cases
- [ ] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [ ] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
<!-- Before adding documentation and example(s) (below), please wait
until the PR is reviewed and approved. -->
- [ ] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
- [ ] I have added an example in the [examples
repo](https://github.com/langchain4j/langchain4j-examples) (only for
"big" features)
- [ ] I have added/updated [Spring Boot
starter(s)](https://github.com/langchain4j/langchain4j-spring) (if
applicable)
## Checklist for adding new maven module
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added my new module in the root `pom.xml` and
`langchain4j-bom/pom.xml`
## Checklist for adding new embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreIT` that extends
from either `EmbeddingStoreIT` or `EmbeddingStoreWithFilteringIT`
- [ ] I have added a `{NameOfIntegration}EmbeddingStoreRemovalIT` that
extends from `EmbeddingStoreWithRemovalIT`
## Checklist for changing existing embedding store integration
<!-- Please double-check the following points and mark them like this:
[X] -->
- [ ] I have manually verified that the
`{NameOfIntegration}EmbeddingStore` works correctly with the data
persisted using the latest released version of LangChain4j
---------
Co-authored-by: kpavlov <{ID}+{username}@users.noreply.github.com>
Co-authored-by: Dmytro Liubarskyi <ljubarskij@gmail.com>
## Change
This PR adds a new MetadataFilters that allows filtering metadata values
by checking whether they contain or not contain a given string.
Whilst this is less powerful than #2342, it is easier to implement in
embedding stores, this PR implements the `ContainsString` filter for the
following embedding stores:
- Milvus
- PgVector
- Qdrant
I tried to implement it for Chroma as well, but didn't find a way in the
Chroma docs to do so.
## General checklist
- [X] There are no breaking changes
- [X] I have added unit and/or integration tests for my change
- [X] The tests cover both positive and negative cases
- [X] I have manually run all the unit and integration tests in the
module I have added/changed, and they are all green
- [x] I have manually run all the unit and integration tests in the
[core](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-core)
and
[main](https://github.com/langchain4j/langchain4j/tree/main/langchain4j)
modules, and they are all green
- [x] I have added/updated the
[documentation](https://github.com/langchain4j/langchain4j/tree/main/docs/docs)
github-actions[bot]