- Remove deprecations from models, vector stores and usage
- Deprecations from FunctionCallback and ObservationContext/Convention will be in a separate PR
Models updates
- Remove AbstractToolCallSupport from the models which use ToolCallingManager
- Remove deprecated constructors and their usage
- Remove FunctionCallbackResolver and FunctionCallbacks usage in the models
- Add back deprecations for VectorStoreChatMemoryAdvisor until builder is fixed
- Update OpenAiPaymentTransactionIT to use ToolCallbackResolver in config
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Extract common vector store delete tests to base class
This commit extracts shared delete operation tests into a reusable BaseVectorStoreTests class.
This reduces code duplication and provides a consistent test suite for delete operations across
different vector store implementations. The base class includes tests for:
Deleting by ID
Deleting by filter expressions
Deleting by string filter expressions
Most of the vector store implementation now extends this base class and inherits these
common tests while maintaining the ability to add vector store specific tests.
Adding javadoc
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Change VectorStore.delete() and related implementations to return void instead of Optional<Boolean>
- Remove unnecessary boolean return values and success status checks across all vector store implementations
- Clean up tests by removing redundant assertions
- Implementations continue using runtime exceptions for error signaling
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Adds getNativeClient API to VectorStore interface allowing access to the underlying native client implementation.
This change:
- Adds getNativeClient() default method to VectorStore interface returning Optional<T>
- Implements getNativeClient() in all vector store implementations exposing their respective native clients
- Adds integration tests verifying native client access for all implementations
Fixes: #2137
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Add string-based filter deletion alongside the Filter.Expression-based deletion
for Neo4j and OpenSearch vector stores, providing consistent deletion capabilities
with other vector store implementations.
Key changes:
- Add delete(Filter.Expression) implementation for Neo4j store using Cypher queries
- Add delete(Filter.Expression) implementation for OpenSearch store using query_string
- Leverage existing filter expression converters for both stores
- Use Neo4j's transaction batching for efficient large-scale deletions
- Use OpenSearch's delete_by_query API for metadata-based deletion
- Add comprehensive integration tests for both stores covering:
* Simple equality filters
* String-based filter expressions
* Complex filter expressions with multiple conditions
This maintains consistency with other vector store implementations while utilizing
store-specific features for efficient metadata-based deletion.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Moving BatchingStrategy configuration from individual vector store implementations
to the base AbstractVectorStoreBuilder to reduce code duplication and provide consistent
batching behavior across all vector stores.
The default TokenCountBatchingStrategy is now set in the base builder class.
* Remove use of Document.getContext method from spring-ai-core, use getText
* Remove deprecated ChatOptionsBuilder class
* Remove deprecated FunctionCallingOptionsBuilder class
- Rename all specific builder inner classes (PineconeBuilder, MongoDBBuilder, etc.)
to simply Builder for consistency across vector store implementations
- Update code references to use the new standardized Builder class names
The change establishes a consistent naming convention for builder classes
across the vector store implementations, improving code uniformity.
- Replace Document.getContent() with getText() across all vector store implementations
- Fix incorrect package declarations in package-info.java files
- Make builder constructors private and implement proper builder patterns
- Add @Nullable annotations for better null safety
- Simplify PineconeVectorStore builder API by requiring essential parameters in factory method
- Make static Map fields final
- Clean up code and improve JavaDoc documentation
The changes focus on making the vector store APIs more consistent,
type-safe, and maintainable while following best practices for
builder patterns and null safety.
This commit refactors the builder pattern implementation across all VectorStore
implementations to make the EmbeddingModel a required constructor parameter
rather than an optional builder method. Key changes include:
- Move embeddingModel from being a builder method to a required constructor parameter
- Make embeddingModel final in AbstractVectorStoreBuilder
- Remove redundant validate() methods since EmbeddingModel validation now happens
in constructor
- Update all VectorStore builder instantiations to pass EmbeddingModel in builder
creation
- Add @Nullable annotations to appropriate methods in VectorStore interface
This change improves the API design by:
1. Enforcing that EmbeddingModel is provided at builder creation time
2. Removing the possibility of forgotten EmbeddingModel configuration
3. Simplifying the builder implementation by moving validation to construction
4. Making the dependency on EmbeddingModel more explicit in the API
Breaking Changes:
- VectorStore builders must now be created with an EmbeddingModel parameter
- The embeddingModel() builder method has been removed from all implementations
The Ollama options builder API has been refactored to follow standard Java
builder pattern conventions. This change deprecates all builder methods
prefixed with 'with' in favor of more concise method names, improving API
consistency and usability.
The deprecated methods are marked for removal in version 1.0.0-M5, giving
users time to migrate to the new builder pattern. This change aligns with
our goal of providing a more intuitive and maintainable API surface.
Breaking Changes:
* builder() method now returns Builder instead of OllamaOptions
* Clients using the old fluent API will need to migrate to the new builder pattern
Refactor Ollama options builder methods
This commit deprecates builder methods with the "with" prefix in the VectorStoreObservationContext class
and introduces new methods without the prefix for a cleaner API. For example:
withCollectionName() → collectionName()
withDimensions() → dimensions()
withNamespace() → namespace()
The old methods are marked as deprecated for maintaining backward compatibility.
All vector store implementations have been updated to use the new method names.
Add builder pattern to OpenSearchVectorStore
Introduces a builder pattern for OpenSearchVectorStore configuration and
refactors the package structure to org.springframework.ai.vectorstore.opensearch
for better organization and consistency with other vector stores.
The builder pattern improves usability by:
* Providing a fluent API for configuring store instances
* Making configuration options more discoverable through method names
* Enabling better validation of configuration parameters
* Supporting optional parameters with sensible defaults
* The package refactoring aligns with the project's standard package naming
conventions and improves code organization. All constructors are deprecated
in favor of the new builder pattern to guide users toward the preferred
configuration approach.
- Since Document's reference to its embedding is deprecated, store the embedding into OpenSearch vector store by creating an explicit OpenSearch Document type which has embedding associated with it
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
- PaymentStatusFunctionCallingIT in org.springframework.ai.mistralai.api.tool
is failing. Needs investigation.
See https://github.com/spring-projects/spring-ai/issues/1853
- OpenSearchVectorStoreWithOllamaIT updated to pull model if not available.
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>
- Fix the embedding dimension configuration for opensearch client indices mapping
The dimension config is obtained by the underlying embedding model's dimension
- Updated OpenSearch mapping JSON to include dynamic embedding dimension.
- Changed default mapping for OpenSearch vector store to use generic dimension placeholder.
- Fixed OpenSearchVectorStoreAutoConfiguration to fallback to new default mapping if no custom mapping is provided.
- Added test for verifying mapping configuration with OpenSearch vector store.
- Added test dependencies for Ollama integration.
- Refactored OpenSearch integration tests to use new mapping and dimension logic.
Add tests
- Verify the mappingJson field is correctly set - verify the override works fine
- Add integration tests with Ollama embedding model
Resolves#1589
- Resolved issue where index name was not being sent during
similaritySearch
- Updated similaritySearch method to include index in the SearchRequest
- Implemented test to verify documents can be added and retrieved from
two different indices using separate OpenSearchVectorStore instances
- Ensured similarity search results are correctly returned for the
respective indices
Fixes#885
* 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:
- Azure vector store
- Cassandra
- MongoDB Atlas
- OpenSearch
- Oracle
- Pinecone
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>
* Change default schema initialization of vector stores from `true` to `false.`
Users need to explicitly opt-in for schema initialization by setting the
`initialize-schema` property on the corresponding vector store.
* Update integration tests
* Update docs
Fixes#907
- implement OpensSearchVectorStore
- add opensearch auto-configuration and boot starter
- add documentation for OpenSearch VectorStore
- add bom dependecies
- align with to new Spirng AI API
