Major Changes:
- Created new module spring-ai-vector-store from spring-ai-core functionality
- Split advisor functionality into three new modules:
* advisor-memory: Memory-based chat advisors
* advisor-rag: Retrieval Augmentation Generation advisors
* advisor-vector-store: Vector store based advisors
The commit restructures the ChromaVectorStore builder pattern to use a no-args constructor
with fluent API for setting the ChromaApi.
This change:
- Makes builder creation consistent with other vector stores
- Moves ChromaApi validation to the doValidate method
- Improves builder API ergonomics
The change requires updating all builder usages to use the new .chromaApi() method instead
of passing it in the constructor.
The Document class previously allowed multiple media entries while also having a
text field, leading to ambiguity in content handling. This change enforces a
clear separation between text and media documents to prevent content type
confusion and simplify document processing.
A Document now must contain either text content or a single media entry, but
never both. This aligns with the class's primary use in ETL pipelines where
clear content type boundaries are essential for proper embedding generation and
vector database storage.
Additional architectural changes:
- Document now implements a cleaner API by removing deprecated methods
- Removed MediaContent interface implementation from Document class
- Document.getMedia() now returns a single Media object instead of Collection
- Removed EMPTY_TEXT constant in favor of proper null handling
- Constructor signatures simplified and streamlined
- Builder pattern improved to enforce single content type constraint
The breaking changes include:
- Media is now a single entry instead of a collection
- Content field renamed to text for clarity
- Removed support for mixed content types
- Simplified builder API to prevent ambiguous construction
Prefer using text-related methods over deprecated content methods to
better reflect the actual content type being handled and improve API clarity.
This refactoring introduces a consistent builder pattern across vector store
implementations to standardize configuration and initialization, while also
moving ChromaVectorStore to a dedicated chroma package.
Key changes:
- Add VectorStore.Builder interface and AbstractVectorStoreBuilder to establish
a common builder hierarchy
- Move ChromaVectorStore and related classes from vectorstore to
org.springframework.ai.chroma.vectorstore package
- Migrate ChromaVectorStore to builder pattern as the first implementation
- Add null-safety annotations and parameter validation
- Deprecate direct constructors in favor of builder API
- Update all tests and documentation to reflect new structure
The builder pattern provides several benefits:
- Consistent configuration across all vector store implementations
- Better validation of required parameters
- More flexible initialization order
- Clearer separation of concerns between configuration and usage
- Improved discoverability of options through method chaining
- Since the Document object's reference to the `embedding` is deprecated and will be removed, the VectorStore implementations require a way to store the embedding of the corresponding Document objects
- One way to fix this is, to have the EmbeddingModel#embed to return the embeddings in the same order as that of the Documents passed to it.
- Since both the Document and embedding collections use the List object, their iteration operation will make sure to keep them in line with the same order.
- A fix is required to preserve the order when batching strategy is applied.
- Updated the Javadoc for BatchingStrategy
- Fixed the Document List order in TokenCountBatchingStrategy
- Refactored the vector store implementations to update this change
Resolves #GH-1826
Document
* Introduced “score” attribute in Document API. It stores the similarity score.
* Consolidate “distance” metadata for Documents. It stores the distance measurement.
* Adopted prefix-less naming convention in Document.Builder and deprecated old methods.
* Deprecated the many overloaded Document constructors in favour of Document.Builder.
Vector Stores
* Every vector store implementation now configures a “score” attribute with the similarity score of the Document embedding. It also includes the “distance” metadata with the distance measurement.
* Fixed error in Elasticsearch where distance and similarity were mixed up.
* Added missing integration tests for SimpleVectorStore.
* The Azure Vector Store and HanaDB Vector Store do not include those measurements because the product documentation do not include information about how the similarity score is returned, and without access to the cloud products I could not verify that via debugging.
* Improved tests to actually assert the result of the similarity search based on the returned score.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Add new Maven profile 'ci-fast-integration-tests' for running selective ITs
- Remove redundant vector store skip flags from properties section
- Update maven-failsafe-plugin to version 3.5.2
- Configure test exclusions for various components:
- Most model integration tests (Anthropic and OpenAI)
- Most vector store tests (except PgVector and Chroma)
- Most auto-configuration tests
- All test containers and docker compose tests
- AI evaluation tests
- Convert the docker-compose tests into ITs
- Convert the testcontainers tests into ITs
- Updated README.md
- Explain the new profile and also the new integration tests repo
- Describe ways to run integration tests for specific modules
- Add badge for https://github.com/spring-projects/spring-ai-integration-tests
- Added Jackson annotations for JSON property handling in Chroma API request/response records.
Use @JsonInclude(JsonInclude.Include.NON_NULL) to ignore empty fields such as null where.
Use @JsonProperty(XYZ) to provide a strong contract with the Cohere API.
- Updated the Docker image for running Chroma locally and in tests to version 0.5.20.
- Enhanced methods with non-null assertions for improved code safety.
- Added a simple search test to verify document similarity search functionality.
Fixes#1749
Due to changes in Chroma v0.5.13 (chroma-core/chroma#2880), the delete
operation no longer returns values. This impacts our ChromaVectorStore's delete
functionality.
Now we need to check the HTTP status code instead to properly verify if the
delete operation succeeded.
Test suite has been updated.
Resolves#1529
The change addresses initialization issues when ChromaVectorStore is used outside
Spring context, particularly in scenarios where collections are created manually
before store instantiation. Previously, collection ID wasn't properly populated
when afterPropertiesSet() wasn't called by Spring container.
- Add builder pattern to ChromaVectorStore for better initialization control
- Add initialization flag to prevent multiple collection creation calls
- Add integration tests for builder pattern usage scenarios
- Add spring-ai-transformers dependency for testing
- Remove unused constants (SIMILARITY_THRESHOLD_ALL, DEFAULT_TOP_K)
Collection ID is now properly set regardless of whether the store is managed by
Spring or created manually, solving the 404 Not Found errors during document
insertion.
Fixes: #1240
- Add maven properties for all vector stores such as
skip.vectorstore.azure-cosmos-db to control IT test execution
- Chroma and PGVector IT tests are enabled by default
- Docker Compose and Testcontainers module ITs are skipped by default
- Add parallel job to run docker-compose and testcontainers ITs
Adds @EnabledIfEnvironmentVariable annotation to integration tests that
use OpenAI embeddings. Tests will be skipped if OPENAI_API_KEY is not set,
making the build process more reliable for contributors who don't have
access to OpenAI services.
ObjectMapper instantiation is costly, so unless its usage
is one-shot, it is better to create a reusable instance
for upcoming usage.
Also, before this commit, serialization of most Kotlin
classes was not supported due to the lack of proper
Jackson KotlinModule detection.
This commit:
- Avoids per invocation ObjectMapper instantiation when
relevant
- Automatically detects and enables well-known Jackson
modules including the Kotlin one
- Removes org.springframework.ai.vectorstore.JsonUtils
which looks not needed anymore
More optimizations are possible like reusing more
ObjectMapper instances, but this could introduce more breaking
changes so this commit intends to be a good first step.
Kotlin tests will be provided in a follow-up commit.
Additional changes:
- Update ModelOptionsUtils to use JacksonUtils.instantiateAvailableModules()
- Add missing license headers
- Add missing author Javadoc comments
- Remove unnecessary spring-web dependencies
- Update third-party library versions
- Refactor API classes to use consistent header handling
- Remove ApiUtils class and inline its functionality
- Adjust RestClient and WebClient builder usage in autoconfiguration
- Replace direct RestClient.Builder injections with ObjectProvider<RestClient.Builder>
and WebClient.Builder injections with ObjectProvider<WebClient.Builder>
- Update ChromaVectorStoreAutoConfiguration to use ObjectProvider
- Rename MongoDbAtlasLocalContainerConnectionDetailsFactoryTest to IT
- Switch spring-ai-chroma-store dependency from spring-web to spring-webflux
- Simplify ChromaApi constructor by using method reference for default headers
- Adjust import order
Resolves#1066Resolves#524
- Improve ChromaVectorStore to throw exception on missing collection with disabled schema
- Add test case to verify exception is thrown when collection doesn't exist and schema init is false
- Correctly set Chroma collection id when initializeSchema set to false
Co-authored-by: Christian Tzolov <ctzolov@vmware.com>
* Unify image definition for vector stores in vector-store modules
* Unify image definition for vector stores in spring-ai-testcontainers module
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Vector store observations support several key-value pairs, coming from the Spring AI abstractions. Currently, whenever a value is not available (either because not configured by the user or not supported by the vector store provider), span/metrics attributes are generated anyway with value none.
That causes several issues, including an unneeded increase in time series, challenges in alerting/monitoring (especially for integer/double attributes that suddenly are populated with a string), and non-compliance with the OpenTelemetry Semantic Conventions (according to which, attributes should be excluded altogether if there's no value).
This pull request changes the conventions for vector store observations to exclude the generation of span/metrics attributes for optional values which don't have any value.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Apply batching when adding Documents to the following vector stores:
- Chroma
- ElasticSearch
- Neo4j
- Qdrant
- Redis
- Typesense
- Weaviate
This improves efficiency by processing multiple Documents at once instead of individually, reducing the overhead for each operation.
Related to #1261
* Consolidate usage of “db.collection.name” attribute to track table name, collection name, index name, document name, or whatever concept a vector database uses to store data. Removed “db.index” that was use sometimes instead of “db.collection.name”. This usage is in line with the OpenTelemetry Semantic Conventions.
* Configure query response content to be included as a “span event” instead of a “span attribute” if the backend system supports that, similar to how we do for the model observations.
* Structure vector store observation attributes in dedicated enums, including one for the Spring AI Kinds to avoid hard-coding the same value in a lot of places. This follows the OpenTelemetry Semantic Conventions as much as possible. Also, adopt Spring usual non-null-by-default strategy as much as possible.
* Align vector store conventions to the chat model ones, and follow alphabetical order for values. This is particularly useful for the convention classes, for which the Micrometer performance of exporting telemetry data improves when key values are added already sorted to the context.
* Fix flaky test in Mistral AI.
* Improve Qdrant integration tests.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- replace RestTemplate by RestClient but default to SimpleClientHttpRequestFactory as Chroma seems to have issues with HTTP2.
- update the documentation.
- update the ghcr.io/chroma-core/chroma version to 0.5.0. Fix the withBasicAuthCredentials.
Co-authored-by: Christian Tzolov <ctzolov@vmware.com>
* Rename the ModelClient class hierarchy into Model:
- Rename ModelClient into Model. Update all code and doc references.
- Rename ChatClient to ChatModel. Update all ChatClient suffixes and chatClient fields and variables in code and doc.
- Rename EmbeddingClient into EmbeddingModel. Update the XxxEmbeddingClient class and variable suffixes and embeddingClient variables and fields in code and docs.
- Rename ImageClient into ImageModel.
- Rename SpeechClient into SpeechModel.
- Rename TranscriptionClient into TranscriptionModel.
- Update all javadocs and antora pages. Update the related diagrams.
* Create fluent API in ChatClient interface that now includes streaming support
* Add OpenAI FunctionCallbackWrapper2IT auto-config tests.
* Add ChatClientTest mockito testing.
* Add ChatModel#getDefaultOptions(), and remove @FunctionalInterface
* ChatModel enums extend the new ModelDescription interface.
* Implement fromOptions copy method in every ChatOptions implementation.
* Extend ChatClient to use the model default options if not provided explicitly.
* Update readme to provide guidance on how to adapt to breaking changes.
Co-authored-by: Christian Tzolov <ctzolov@vmware.com>
Co-authored-by: Mark Pollack <mpollack@vmware.com>
