- 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
Introduce multimodality support for Mistral AI, which currently supports text and vision modalities.
Added integration tests and documentation for the new capability.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- VectorStore implementations may still be returning the embedding values and mapping onto
Document.class with Jackson
This change ignores that field, but vector store implementations should change to not return
the embedding data that is no longer stored in Document
The FactCheckingEvaluator was initially designed for the Bespoke Minicheck
model which doesn't require explicit instructions. This change adds support
for general-purpose LLMs like Claude and GPT-4 that need clear evaluation
instructions in their prompts.
Key changes:
- Introduce separate prompts for Bespoke and general LLMs
- Add factory method for Bespoke Minicheck configuration
- Make evaluation prompt configurable via constructor
This maintains backward compatibility while enabling the evaluator to work
effectively with any LLM implementation.
The OpenAiImageOptions class previously had inconsistent behavior when
setting width and height properties. This change ensures that the size
property is only computed when both dimensions are available, preventing
invalid states in the API requests.
Key changes:
- Update setWidth/setHeight to only set size when both are non-null
- Add test cases to verify null size when dimensions are incomplete
- Improve code organization with proper import conventions
This change aligns with OpenAI's API requirements for image generation
where both dimensions must be specified for valid requests.
- This PR removes the reference of `embedding` from the `Document` object.
- The Document is designed to contain the content and its metadata but not the embedding representation of its content. This provides clear separation of concern.
- Prior to this change, all the vector stores are updated by not depending on the embedding from Document. Instead, use the embedding values returned by the Embedding Models directly: https://github.com/spring-projects/spring-ai/issues/1826Resolves#1781
Removes duplicate state by reusing parent's options field for both function
calling and chat options. This simplifies the inheritance structure and
prevents potential state inconsistencies.
- Remove functionCallingOptions field from DefaultFunctionCallingOptionsBuilder
- Set parent class options with FunctionCallingOptions in child constructor
- Add protected constructor in DefaultChatOptionsBuilder for inheritance
- Initialize options through constructors instead of direct assignment
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.
- Create SimpleVectorStoreBuilder which can be used to create the SimpleVectorStore instance
- Remove the field embeddingModel from SimpleVectorStore as it can be retrieved from AbstractObservationVectorStore
- Deprecate the existing SimpleVectorStore constructors and use the builder to instantiate it
- Fix the tests
Ollama has recently introduced native support for JSON structured output, as described in https://ollama.com/blog/structured-outputs.
This PR introduces support for it, both for directly passing a JSON schema and when using the Spring AI output conversion APIs.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Refactor the builder methods to remove `with` as the prefix.
- Introduce new methods with updated naming conventions.
- Deprecate the existing `with*` methods to maintain backward compatibility.
- Update WatsonxAi documentation
- Refactor the builder methods to remove `with` as the prefix.
- Introduce new methods with updated naming conventions.
- Deprecate the existing `with*` methods to maintain backward compatibility.
- Update AnthropicChatOptions builder documentation
- Refactor the builder methods to remove `with` as the prefix.
- Introduce new methods with updated naming conventions.
- Deprecate the existing `with*` methods to maintain backward compatibility.
- Update MistralAiChatOptions builder documentation
Introduces a builder pattern for configuring QdrantVectorStore instances to
provide a more flexible and type-safe way to create and configure vector stores.
This change:
- Makes configuration more intuitive through fluent builder methods
- Improves validation by enforcing required parameters at compile time
- Deprecates old constructors in favor of the builder pattern
- Adds comprehensive builder tests to ensure reliability
- Updates reference documentation with builder usage examples
- Maintains backward compatibility while providing a clear migration path
The builder pattern simplifies QdrantVectorStore configuration by providing
clear method names, proper validation, and better IDE support through method
chaining. This makes the API more user-friendly and helps prevent configuration
errors at compile time rather than runtime.
- Refactor builder methods in `ChatResponseMetadata` to remove `with` prefixes and introduce new methods with updated naming conventions.
- Deprecate existing `with*` methods while maintaining backward compatibility.
- Ensure dependent files and tests are compatible with the updated `ChatResponseMetadata` class.
- Refactor the builder methods to remove `with` as the prefix.
- Introduce new methods with updated naming conventions.
- Deprecate the existing `with*` methods to maintain backward compatibility.
- Update the `copy()` method to use the new builder methods.
- Update MoonshotChatOptions builder documentation
Introduces a builder pattern for configuring MariaDBVectorStore instances and
improves the overall implementation. This change:
- Makes configuration more flexible and type-safe through builder methods
- Deprecates old constructors and builder in favor of the new builder pattern
- Adds comprehensive validation of configuration options
- Improves documentation with clear examples and better structure
- Updates all test classes to use the new builder pattern
- Adds comprehensive builder tests
- Updated reference documentation
The builder pattern provides a more maintainable and user-friendly way to
configure vector stores while ensuring configuration validity at compile time.
This aligns with the project's move towards using builder patterns across all
vector store implementations.
Introduces a builder pattern for configuring TypesenseVectorStore instances and
moves the implementation to the org.springframework.ai.vectorstore.typesense
package. This change:
- Makes configuration more flexible and type-safe through builder methods
- Improves code organization by moving to a dedicated vector store package
- Deprecates old constructors in favor of the builder pattern
- Adds comprehensive validation of configuration options
- Enhances documentation with clear usage examples
- Adds dedicated builder test class for better test coverage
- Add builder tests
- update reference docs
The builder pattern simplifies TypesenseVectorStore configuration while ensuring
proper validation of all settings. The package move aligns with Spring AI's
architectural patterns and improves maintainability by grouping related classes
together.
review
- Deprecate existing FunctionCallingOptionsBuilder
- Create FunctionCallingOptions.Builder which extends ChatOptions.Builder
- Create DefaultFunctionCallingOptions which extends DefaultChatOptions and implements FunctionCallingOptions to serve the default FunctionCalling options
- Create DefaultFunctionCallingOptionsBuilder to build the default functioncalling options
- Update the usage of functioncalling options builder to use the newly added builder including the tests
Improve extensibility of DefaultChatOptionsBuilder
- Enable DefaultChatOptionsBuilder to accommodate any other sub types
- Introduce generics to support sub types that extend DefaultChatOptionsBuilder
- Update builder methods to return the sub type
- Make FunctionCallingOptions' builder()'s return type to accommodate sub types which can extend FunctionCallingOptions.Builder
- Deprecate the builder methods with the prefix `with`
- Fix OCI cohere chat model options and OCI Embedding model options
- Update references and docs
