Pre-Retrieval:
* Consolidated naming and documentation
Retrieval:
* Consolidated naming and documentation
* Introduced DocumentJoiner sub-module and CompositionDocumentJoiner operator
Post-Retrieval:
* Introduced main interfaces for sub-modules. Implementation waiting for missing features in Document APIs
Orchestration:
* Introduced QueryRouter sub-module and AllDocumentRetrieversQueryRouter operator
Generation:
* Consolidated naming and documentation
Advisor:
* Introduced BaseAdvisor to reduce boilerplate when implementing Advisors
* Extended RetrievalAugmentationAdvisor to include the new sub-modules
Relates to #gh-1603
- Replace hardcoded "tool_use" with StopReason enum value
- Add tests for token usage aggregation with tool calls
- Add handling for null response metadata
Add AI_OPERATION_TYPE and AI_PROVIDER as low cardinality key names to advisor observations.
The advisor AI_OPERATION_TYPE is set to 'framework' and the AI_PROVIDER to 'spring_ai'.
Resolves#1660
- Add TOOL_CALL_HISTORY constant to store tool call history
- Extend ToolContext with getToolConversationHistory method
- Include tool call history in tool context during function execution
- Add test coverage for tool call history verification
Resolves#1202
Add support for no-argument Supplier and single-argument Consumer function
callbacks in the Spring AI core module. This enhancement allows:
- Registration of Supplier<O> callbacks with no input (Void) type
- Registration of Consumer<I> callbacks with no output (Void) type
- Support for Kotlin Function0 (equivalent to Java Supplier)
- Handle empty properties for Void input types in schema generation
- Enhance FunctionCallback builder to support Supplier/Consumer patterns
Additional changes:
- Add test coverage for both Supplier and Consumer callbacks in various scenarios
- Enhance TypeResolverHelper to support Consumer input type resolution
- Support lambda-style function declarations for improved ergonomics
- Add test cases for void input/output handling in OpenAI chat model
- Include examples of function calls without return values
- Add support for parameterless functions through Supplier interface
Add comprehensive documentation for the FunctionCallback API:
- Overview of the interface and its key methods
- Builder pattern usage with function and method invocation approaches
- Examples for different function types (Function, BiFunction, Supplier, Consumer)
- Best practices and common pitfalls
- Schema generation and customization options
Resolves#1718 , #1277 , #1118, #860
Improves function calling documentation with clearer organization and examples:
- Reorganizes content into server-side and client-side registration sections
- Adds detailed examples for both function-invoking and method-invoking approaches
- Enhances tool context documentation with diagrams and usage examples
- Updates function-calling diagrams to reflect current implementation
- Update deprecated annotation messages to correctly reference functions() instead of function()
- Add detailed documentation for FunctionCallback.Builder hierarchy
- Deprecate FunctionCallbackWrapper class in favor of Builder pattern
- Fix typos and improve code documentation
Introduces a simplified, type-safe builder pattern for function callbacks to
improve developer experience and code reliability. The new hierarchical API
separates concerns between direct function invocation and method reflection,
while providing better compile-time safety.
This change deprecates the older FunctionCallbackWrapper in favor of a more
intuitive FunctionCallback.Builder that better handles generic types via
ParameterizedTypeReference. It also adds automatic function description
generation as a fallback when none is provided, though explicit descriptions
are still recommended.
The update standardizes function callback handling across all AI model
implementations (OpenAI, Ollama, Minimax, etc.) and improves response
handling with configurable converters.
Core API Enhancements:
- New Builder Interface: Replaced FunctionCallbackWrapper.builder() with
FunctionCallback.builder(), introducing a hierarchical approach that improves
customization and type safety.
- Specialized Builders: Introduced FunctionInvokerBuilder for direct Function/BiFunction
implementations and MethodInvokerBuilder for reflection-based invocations.
- Generic Type Support: Added ParameterizedTypeReference for better handling of generic parameters.
- Unified Method Definition: Merged method() and argumentTypes() into a single method() call
for simplicity and type safety.
- Automatic Descriptions: Implemented auto-generation of function descriptions, with warnings
to encourage explicit descriptions.
- Configurable Response Converters: Enhanced response handling with support for custom
converters, reducing unnecessary JSON conversions.
Architecture Improvements:
- Established common Builder interface for shared properties
- Separated function object handling from constructor
- Added method-specific configuration (name, arg types, target)
- Added JSON schema generation support for ResolvableType
- Moved to standardized schema types across AI providers
- Set OPEN_API_SCHEMA as default for Vertex AI Gemini
Builder Pattern Standardization:
- Standardized builder method ordering across implementations
- Moved function() call after description() for consistency
- Improved function callback configuration with unified patterns
- Enhanced error handling and validation in DefaultFunctionCallbackBuilder
Deprecations:
- FunctionCallbackWrapper.Builder replaced by DefaultFunctionCallbackBuilder
- Removed CustomizedTypeReference in favor of ParameterizedTypeReference
- Deprecated older ChatClient API methods for function handling
Testing & Documentation:
- Updated all AI model implementations (OpenAI, Ollama, Minimax, Moonshot, ZhiPuAI)
- Added comprehensive integration tests for static/instance methods
- Added integration tests for auto-generated descriptions
- Updated documentation to reflect new builder pattern usage
- Added Kotlin extension for inputType() support
Co-authored-by: Sébastien Deleuze <sebastien.deleuze@broadcom.com>
- Remove deprecated types,methods and references
- Remove usage of "Generation(String text)" and replace with
"Generation(AssistantMessage)"
- Remove MiniMaxApi,MootShotApi,OpenAiApi,ZhiPuAiApi
ChatCompletionFinishReason's FUNCTION_CALL
- Remove OllamaApi's deprecated types
- Remove deprecated constructors from PostgresMlEmbeddingModel
- Remove deprecated constructor from Media
- Remove tokenNames usage from antlr4 FiltersLexer and FiltersParser
- Remove deprecated methods from CassandraVectorStoreProperties
- Remove deprecated constructor and static config class from QdrantVectorStore
- Minor cleanups on removing deprecated models and versions
- Remove old name for mixtral models
Resolves#1599
- Adviser name is moved from hight to low cardinality key values.
- Updated tests in to reflect these changes, ensuring the new low cardinality key is correctly captured.
Resolves#1716
Query Analysis
* Introduce Query Analysis Module
* Define QueryTransformer API and TranslationQueryTransformer implementation
* Define QueryExpander API and MultiQueryExpander implementation
* Support QueryTransformer in RetrievalAugmentationAdvisor (support for QueryExpander will be in the next PR together with the needed DocumentFuser API).
Improvements
* Refine Retrieval and Augmentation Modules for increased robustness
* Expand test coverage for both modules
* Define clone() method for ChatClient.Builder
Tests
* Introduce “spring-ai-integration-tests” for full-fledged integration tests
* Add integration tests for RAG modules
* Add integration tests for RAG advisor
Query Analysis
* Introduce Query Analysis Module
* Define QueryTransformer API and TranslationQueryTransformer implementation
* Define QueryExpander API and MultiQueryExpander implementation
* Support QueryTransformer in RetrievalAugmentationAdvisor (support for QueryExpander will be in the next PR together with the needed DocumentFuser API).
Improvements
* Refine Retrieval and Augmentation Modules for increased robustness
* Expand test coverage for both modules
* Define clone() method for ChatClient.Builder
Tests
* Introduce “spring-ai-integration-tests” for full-fledged integration tests
* Add integration tests for RAG modules
* Add integration tests for RAG advisor
Relates to #gh-1603
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
This change enables more flexible integration between Spring AI and LLM function
calling capabilities while maintaining type safety and ease of use.
- Add new MethodFunctionCallback class to support method invocation via reflection
- Supports both static and non-static method calls
- Handles multiple parameter types including primitives, objects, collections
- Supports empty parameters and empty response
- Auto-generates JSON schema from method parameters
- Special handling for ToolContext parameters
- Builder pattern for easy configuration
- Add comprehensive unit tests for MethodFunctionCallback
- Add integration tests for MethodFunctionCallback with both Anthropic and OpenAI clients
- Add jackson-module-jsonSchema dependency
- Modify FunctionCallback to check for empty tool context
Testing coverage includes:
- Static method invocation scenarios
- Non-static method calls with various parameter types
- Void return type methods
- Complex parameter types (enums, records, lists)
- Tool context handling
- Error cases and validation
Add MethodFunctionCallback reference docs
- Add support for proper Kotlin functions handling by adapting
`kotlin.jvm.functions.Function1` to `java.util.function.Function` and
`kotlin.jvm.functions.Function2` to `java.util.function.BiFunction`.
- Removes the dependency on Spring Cloud Function and
`net.jodah:typetools` which are replaced by leveraging
Spring Framework `ResolvableType` capabilities.
- Add a Kotlin extension function for
`FunctionCallbackWrapper.Builder.withInputType` allowing to
specify `withInputType<T>()` instead of `withInputType(T::class.java)`.
- Add Kotlin documentation.
- Verify that the BeanOutputConverter converts with the right order as specified in the JSON schema
Update the BeanOutputConverterTest's test case to tweak the order for validation
Fixes: #1335https://github.com/spring-projects/spring-ai/issues/1335
Add support for maintaining JSON property order in generated schemas using
@JsonPropertyOrder. Users can now control the order of properties in their
JSON schemas by annotating their classes/records with @JsonPropertyOrder.
- Add JacksonOption.RESPECT_JSONPROPERTY_ORDER to BeanOutputConverter
- Add test to verify schema property ordering
- Update documentation with property ordering example
This commit rename the thresholdFactor parameter to reservePercentage to better
reflect its purpose in the TokenCountBatchingStrategy class. It also adds
validation for input parameters including maxInputTokenCount > 0 and
reservePercentage between 0 and 1 for safer initialization.
The change ensures proper parameter validation on TokenCountBatchingStrategy
creation to prevent potential runtime errors from invalid inputs.
- Add a new test case for testing function call with advisor in BedrockConverseChatClientIT
- Add a new test case for testing tool proxy function call in OpenAiChatClientProxyFunctionCallsIT
- Remove unused model property from BedrockConverseProxyChatProperties
Add support for proper Kotlin functions handling
by adapting kotlin.jvm.functions.Function1 to
java.util.function.Function and kotlin.jvm.functions.Function2 to
java.util.function.BiFunction.
It also removes the dependency on Spring Cloud Function and
net.jodah:typetools which are replaced by leveraging
Spring Framework ResolvableType capabilities.
Added withInputType Kotlin extension
- Add a Kotlin extension function for
FunctionCallbackWrapper.Builder.withInputType allowing
to specify withInputType<T>() instead of
withInputType(T::class.java).
- Add Kotlin documentation
- Disable project-wide Checkstyle checks to unblock development
- Add documentation for enabling Checkstyle locally
- Fix remaining checkstyle violations in current codebase
Fixes#1669
Introduces support for Amazon Bedrock Converse API through a new BedrockProxyChatModel
implementation. This enables integration with Bedrock's conversation models with features
including:
- Support for sync/async chat completions
- Stream response handling
- Tool/function calling capabilities
- System message support
- Image input support
- Observation and metrics integration
- Configurable model parameters and AWS credentials
Adds core support classes:
- BedrockUsage: Implements Usage interface for token tracking
- ConverseApiUtils: Utility class for handling Bedrock API responses including:
- Tool use event aggregation and processing
- Chat response transformation from stream outputs
- Model options conversion
- Support for metadata aggregation
- URLValidator: Utility for URL validation and normalization with support for:
- Basic and strict URL validation
- URL normalization
- Multimodal input handling
- Enhanced FunctionCallingOptionsBuilder with merge capabilities for both ChatOptions
and FunctionCallingOptions
- Added BEDROCK_CONVERSE to AiProvider enum for metrics tracking
- Extended AWS credentials support with session token capability
- Added configurable session token property to BedrockAwsConnectionProperties
Adds new auto-configuration support:
- BedrockConverseProxyChatAutoConfiguration for automatic setup of the Bedrock Converse chat model
- BedrockConverseProxyChatProperties for configuration including:
- Model selection (defaults to Claude 3 Sonnet)
- Timeout settings (defaults to 5 minutes)
- Temperature and token control
- Top-K and Top-P sampling parameters
- Integration with existing BedrockAwsConnectionConfiguration for AWS credentials
Updates to testing infrastructure:
- Adds comprehensive test suite for Bedrock Converse properties and auto-configuration
- Integration tests for chat completion and streaming scenarios
- Property validation tests for configuration options
- Temporarily disabled other Bedrock tests due to AWS quota limitations
- Added ObjectMapper configuration for proper JSON handling
Added new spring-ai-bedrock-converse-spring-boot-starter module
Updates module configuration in parent POM and BOM to include new bedrock-converse
modules and starters. Adds necessary auto-configuration imports for seamless integration
with Spring Boot applications.
Unrelated changes:
- Disabled several Bedrock model tests (Jurassic2, Llama, Titan) due to AWS quota limitations
- Disabled PaLM2 tests due to API decommissioning by Google
Resolves#809, #802
Add docs and fix configs
- Move timeout configuration from chat properties to connection properties
- Add comprehensive documentation for Bedrock Converse API usage and configuration
- Update tests to reflect configuration changes
Co-authored-by: maxjiang153 <maxjiang153@users.noreply.github.com>
Standardize AWS credential handling in integration tests
- Improve how we manage AWS credentials across our integration test
suite and ensures consistent test configuration. We're replacing individual
environment variable checks with @RequiresAwsCredentials
annotation and standardizing the use of BedrockTestUtils for context creation
in tests
We also align all AWS regions to US_EAST_1 for consistency and add missing
dependency versioning for Oracle Free.
These changes make our AWS tests more easier to maintain.
Key changes:
- Replace @EnabledIfEnvironmentVariable with @RequiresAwsCredentials
- Standardize context creation via BedrockTestUtils
- Set AWS region to US_EAST_1
- Add Oracle Free dependency version in pom.xml
* Add new QueryAugmentor API, a component for augmenting a user query with contextual data.
* Implement ContextualQueryAugmentor that combines the content of each document and add it to the original user prompt, with support for the scenario where the context is empty.
* Extend RetrievalAugmentationAdvisor to use the new augmentation building block.
* Introduce utility to assist in validating arguments for prompt-related operations.
Relates to gh-#1603
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
The system text advise prompt is only joined with the value of the system text if it's non-null and non-empty.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Introduced null-safety for all ChatClient APIs and verified via extensive auto-tests.
* Made the final message list computed by ChatClient consistent and predictable across the different options for providing messages (prompt(), messages(), user(), prompt()) and verified via extensive auto-tests.
* Added even more auto-tests to cover as many scenarios and edge cases as possible.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Establish new package for Modular RAG components.
* Add new Query API, representing a query in the context of a RAG flow.
* Define Retrieval package for the RAG building blocks handling the data retrieval operations.
* Relocate DocumentRetriever to Retrieval package and implement VectorStoreDocumentRetriever.
* Introduce RetrievalAugmentationAdvisor as the successor of QuestionAnswerAdvisor. It uses the Retrieval building blocks described in the previous point.
* Make Advisor APIs null-safe and update tests accordingly.
Relates to gh-#1603
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Remove @NestedConfigurationProperty and @ConstructorBinding annotations from model options classes
- Remove spring-boot dependency from spring-ai-openai module
- Add exclusion for spring-boot-autoconfigure in spring-cloud-function-context dependency
- Move configuration metadata to spring-ai-spring-boot-autoconfigure module
This change decouples the core AI model implementations from Spring Boot,
making the core modules more lightweight and allowing them to be used in
non-Spring Boot applications. Configuration properties are now handled by
the spring-ai-spring-boot-autoconfigure module instead.
Fixes#1540
This commit configures Maven to support compiling Kotlin
main and test classes, and adds a JacksonUtilsKotlinTests
class that ensures that serialization and deserialization
of Kotlin data classes works as expected.
The Maven configuration follows recommendations from
https://kotlinlang.org/docs/maven.html.
All output parser functionality has already been migrated to the converter package
since milestone M1.
Changes:
- Replace all instances of 'parser' with 'converter' in variable names and test cases
- Delete (pre M1) deprecated parser package and all associated classes
- Remove Output Parsers section from README.md
- Update Javadoc comments to reference converters instead of parsers
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
