When streaming happens on an event loop, due to the fact that currently
tools can only be synchronous and blocking, every tool call needs to be
offloaded to a blocking-safe Scheduler.
Resolves#2341
Signed-off-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
- Remove model specific Usage implementations
- Add `Object getNativeUsage()` to Usage interface
- This will allow the model specific Usage data to be returned
- At the client side, client needs to cast the return type of `getNativeUsage` into the corresponding Usage returned by the model API
- Rename `generationTokens` to `completionTokens`
- Since `completion` token name is more common among the models, renaming generation tokens into completion tokens
- Maintain JSON deserialization compatibility for legacy `generationTokens` field
- Remove deprecated Long-based constructors to avoid API ambiguity
- Change the prompt, completion and total token return types from Long to Integer
- This is a breaking change that requires updating all constructor calls
- Integer is sufficient for token counts and aligns better with most model APIs
- Use DefaultUsage for most of the model specific usage handling
- When initializing set the native usage to the model specific usage type
- Ensure immutability by making all fields final and removing setters
- Add comprehensive test coverage for all functionality including edge cases
Resolves#1407
This commit adds support for the MiniMax-Text-01 model,
which is recommended for general scenarios due to its
longer context window.
The new model is added to the ChatModel enum as MiniMax_Text_01.
Signed-off-by: Alexandros Pappas <alexandros.pappas@yiluhub.com>
- 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.
- Deprecate existing ChatOptionsBuilder and its inner class DefaultChatOptions
- Create a new builder interface ChatOptions.Builder for building the Chat options
- Create an explicit DefaultChatOptions
- Create DefaultChatOptionBuilder which can create DefaultChatOptions
- Add javadoc for the deprecated Builder
Resolves#1875
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.
Extracts shared function callback builder functionality into DefaultCommonCallbackInvokingSpec
base class, reducing code duplication across builder implementations.
Makes FunctionInvokingSpec and MethodInvokingSpec extend CommonCallbackInvokingSpec for better
code organization. Also fixes function/description builder order in Anthropic tests.
- Introduced a common base class for function callback builders to centralize shared logic
- Standardized the order of method chaining for function and description in multiple AI model test classes
- Refactored test cases across various AI model integrations
- Corrected builder method order from .description().function() to .function().description()
and .description().method() to .method().description()
- Updated multiple test files to consistently use .function() before .description()
- Updated documentation examples to reflect new builder method order
- Modified DefaultFunctionCallbackResolver to maintain new builder method order
- Updated DefaultChatClient and ChatClient test classes to reflect new builder pattern
- Simplified callback specification by removing parent spec reference
- Removed cascading getter logic for description, schema type, and other properties
- Minor adjustments to function callback builder and invoking specs
- Introduces a new FunctionCallbackResolver interface to define the strategy for
resolving FunctionCallback instances.
- Renames FunctionCallbackContext to DefaultFunctionCallbackResolver to better reflect its
implementation role. Updates all related components to use the new interface.
- Update the affected AI model implementations
- Replaces FunctionCallbackContext parameter with FunctionCallbackResolver in all
model constructors
- Updates builder patterns to use functionCallbackResolver() method instead of
withFunctionCallbackContext()
- Deprecates old withFunctionCallbackContext() methods in builders to guide
migration
- Updates integration tests to use DefaultFunctionCallbackResolver
- Improves documentation to clarify the resolver's role in function callbacks
- Moves SchemaType enum from FunctionCallbackContext to FunctionCallback
Resolves#758
- ChatGenerationMetadata provides Map for additional metadata
- Add Builder interface and DefaultChatGenerationMetadataBuilder
- Add DefaultChatGenerationMetadata implementation
- Update all AI model implementations to use the new builder pattern
- Deprecate ChatGenerationMetadata.from() factory method
- Remove commented out legacy code from ChatGenerationMetadata interface
- Make metadata and content filter collections immutable via Collections.unmodifiableSet()
- Add null validation in DefaultChatGenerationMetadata constructor
- Improve toString() method with more informative output
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
The DEFAULT_RETRY_TEMPLATE uses exponential backoff starting at 2s with max 3min
delay between retries, making tests run unnecessarily long. This change
introduces SHORT_RETRY_TEMPLATE with fixed 100ms backoff to speed up test
execution while preserving the same retry behavior and error handling.
- Disable project-wide Checkstyle checks to unblock development
- Add documentation for enabling Checkstyle locally
- Fix remaining checkstyle violations in current codebase
Fixes#1669
Add @JsonIgnore annotation to the jsonSchema field in Function classes across
multiple AI provider APIs (MiniMax, MistralAI, OpenAI, ZhiPuAI) to exclude
it from JSON serialization.
Following removal of Spring Boot's ConstructorBinding, convert record types
to regular POJOs to maintain JSON serialization. Update API classes:
- Convert FunctionTool and Function records to standard Java classes with
getters/setters
- Update test assertions to use getter methods instead of record accessors
- Fix failing tests in MiniMax, OpenAi and ZhiPu API implementations
This keeps core API models independent of Spring Boot while ensuring proper
serialization through standard Java beans.
- MistralAIApi FunctionTool ConstructorBinding removal changes
- 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
- 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
This commit adds support for tool context in various chat options classes across
different AI model implementations and enhances function calling capabilities.
The tool context allows passing additional contextual information to function callbacks.
- Add toolContext field to chat options classes
- Update builder classes to support setting toolContext
- Enhance FunctionCallback interface to support context-aware function calls
- Update AbstractFunctionCallback to implement BiFunction instead of Function
- Modify FunctionCallbackWrapper to support both Function and BiFunction and
to use the new SchemaType location
- Add support for BiFunction in TypeResolverHelper
- Update ChatClient interface and DefaultChatClient implementation to support
new function calling methods with Function, BiFunction and FunctionCallback arguments
- Refactor AbstractToolCallSupport to pass tool context to function execution
- Update all affected <Model>ChatOptions with tool context support
- Simplify OpenAiChatClientMultipleFunctionCallsIT test
- Add tests for function calling with tool context
- Add new test cases for function callbacks with context in various integration tests
- Modify existing tests to incorporate new context-aware function calling capabilities
- Add docs in in openai function calling
Resolves#864, #1303, #991
Add support for PortableFunctionCallingOptions across AI models
- Modify FunctionCallingOptions interface to extend ChatOptions for better integration
- Refactor option handling in chat models to accommodate both ChatOptions and FunctionCallingOptions
- Implement handling of FunctionCallingOptions in Anthropic, Azure OpenAI,
MistralAI, Ollama, OpenAI, VertexAI Gemini, and other models
- Update existing function calling tests to use new FunctionCallingOptions.
Resolves#624
- Removed the assertion checking for a non-null 'name' in ToolResponseMessage
- This change affects multiple AI model implementations:
AzureOpenAiChatModel, MiniMaxChatModel, MistralAiChatModel,
MoonshotChatModel, OpenAiChatModel, and ZhiPuAiChatModel
Resolves#1410
This commit introduces a new proxyToolCalls option for various chat
models in the Spring AI project. When enabled, it allows the client to
handle function calls externally instead of being processed internally
by Spring AI.
The change affects multiple chat model implementations, including:
AnthropicChatModel
AzureOpenAiChatModel
MiniMaxChatModel
MistralAiChatModel
MoonshotChatModel
OllamaChatModel
OpenAiChatModel
VertexAiGeminiChatModel
ZhiPuAiChatModel
The proxyToolCalls option is added to the respective chat options
classes and integrated into the AbstractToolCallSupport class for
consistent handling across different implementations.
The proxyToolCalls option can be set either programmatically via
the <ModelName>ChatOptions.builder().withProxyToolCalls() method
or the spring.ai.<model-name>.chat.options.proxy-tool-calls
application property.
Documentation for the new option is also updated in the relevant
Antora pages.
Added ITs for proxy tool calls
Remove ChatClientPromptRequestSpec and all ChatClient.prompt() overloads can how take advantage of the full fluent API. Docs updated
Resolves#1367
Sometimes, the MiniMax stream mode function calls might get split,
resulting in an empty tool call ID. This indicates that the previous
call is not finished, which is an unusual API design.
The issue occurs when tool calls return in a format like:
[{"id":"1","function":{"name":"a"}},{"id":"","function":{"arguments":"[1]"}}]
These need to be merged into:
[{"id":"1","name":"a","arguments":"[1]"}]
This commit addresses the merging process to handle split function calls.
authored-by: mxsl-gr <mxsl-gr@users.noreply.github.com>
This change updates the type of portable chat options from Float to
Double. Affected options include:
- frequencyPenalty
- presencePenalty
- temperature
- topP
The motivation for this change is to simplify coding. In Java, Float
values require an "f" suffix (e.g., 0.5f), while Double values don't
need any suffix. This makes Double easier to type and reduces
potential errors from forgetting the "f" suffix.
APIs, tests, and documentation have been updated to reflect this
change.
Fixes gh-712
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Add web search mode response in choice.message for enhanced
compatibility
- Implement web search mode for stream mode
- Add comprehensive unit tests for new features
Related to #1292
feat: enhance the compatibility of the minimax model and tests, related issue #1292
Implement web search functionality for the MiniMax model.
Includes unit tests
This enhancement expands the model's ability to access and utilize current information from the internet.
Resolves#1245
