- Migrate from function calling to tool calling API
- Add support for Gemini 2.0 models (flash, flash-lite)
- Implement JSON schema to OpenAPI schema conversion
- Add builder pattern for improved configuration
- Deprecate legacy function calling constructors and methods
- Update default model to GEMINI_2_0_FLASH
- Add comprehensive test coverage for tool calling
- Upgrade victools dependency to 4.37.0
- Update the Vertex Tool calling docs
Part of the #2207 epic
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Replace function calling with tool calling in BedrockProxyChatModel
- Deprecate function calling related code and APIs
- Add new tool calling manager and options
- Update builder pattern to remove "with" prefix from methods
- Update tests and documentation for tool calling
Part of the #2207 epic
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Use the new ToolCallingManager API for AzureOpenAI chat model
- Add Builder to construct AzureOpenAI chat model instance
- Deprecate existing constructors
- Update documentation about the change
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Update MistralAiChatModel to use the new ToolCallingManager API, while ensuring full API backward compatibility.
- Introduce Builder to instantiate a new MistralAiChatModel since the number of overloaded constructors is growing too big.
- Update documentation about tool calling and Mistral AI support for that.
- Add extra validation to ensure the uniqueness of tool names when aggregated from different sources.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Additiona fixes: API key validation and tool calling backward compatibility
- Fix API key validation in OpenAiApi builder
- Standardize API key validation using Assert.notNull
- Add backward compatibility support for FunctionCallback in tool calling
- Update integration tests to use LegacyToolCallingManager
Co-authored-by:Christian Tzolov <christian.tzolov@broadcom.com>
Signed-off-by: Ricken Bazolo <ricken.bazolo@gmail.com>
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Update OpenAiChatModel to use the new ToolCallingManager API, while ensuring full API backward compatibility.
- Introduce Builder to instantiate a new OpenAiChatModel since the number of overloaded constructors is growing too big.
- Update documentation about tool calling and OpenAI support for that.
- Add extra validation to ensure the uniqueness of tool names when aggregated from different sources.
- Ensure consistent merging of options, following Spring Boot strategy.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
When fields in OllamaOptions are marked as ignored in Jackson, they require explicit merge of runtime and default options.
Added tests to validate the different merge combinations for all tool-related options.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Spring AI's dependencies management to derive from Spring Boot 3.4.2
- Remove explicit versioning of dependencies
- Update upgrade notes for Spring Boot 3.4.2
- Fix ElasticSearch client changes with the latest dependency derived from Spring Boot 3.4.2
Introduces a new API key interface that allows users to customize how
API keys are provided and managed in their Spring AI applications. This
change improves security and flexibility by:
- Adding core ApiKey interface and SimpleApiKey implementation
- Adding builder pattern for OpenAiApi creation
- Deprecating public constructors in favor of builder API (since 1.0.0.M6)
- Added docs
The new system enables users to implement their own key management
strategies while maintaining backward compatibility with property-based
configuration.
This commit introduces the `reasoningEffort` parameter to the OpenAI API integration, allowing control over the reasoning effort used by models like `o1-mini`.
Changes:
- Adds `reasoningEffort` field to `OpenAiApi.ChatCompletionRequest`.
- Adds `reasoningEffort` field and builder method to `OpenAiChatOptions`.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
This commit comprehensively updates the OpenAiApi `ChatModel` enum to include all the latest OpenAI chat completion models and enhances the documentation.
Signed-off-by: Alexandros Pappas <alexandros.pappas@yiluhub.com>
* Introduced new ToolParam annotation for defining a description for tool parameters and marking them as (non)required.
* Improved the JSON Schema generation for tools, solving inconsistencies between methods and functions, and ensuring a predictable outcome.
* Added support for returning tool results directly to the user instead of passing them back to the model. Introduced new ToolExecutionResult API to propagate this information.
* Consolidated naming of tool-related options in ToolCallingChatOptions.
* Fixed varargs issue in ChatClient when passing ToolCallback[].
* Introduced new documentation for the tool calling capabilities in Spring AI, and deprecated the old one.
* Bumped jsonschema dependency to 4.37.0.
Relates to gh-2049
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Amzon Bedrock chat models were deprecated to support Amazon Bedrock Converse API for the chat models.
- This PR removes all the references of the deprecated Amazon Bedrock chat models
- Remove Amazon Bedrock chat models for anthropic, anthropic3, cohere, jurassic2, titan
- Remove API, chat options and model
- Remove tests and doc references
- Update the doc to reflect the changes
- Update upgrade notes
Resolves#2124
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
* Adopted new tool calling logic in OllamaChatModel, while maintaining full API backward compatibility thanks to the LegacyToolCallingManager.
* Improved efficiency and robustness of merging options in prompts for Ollama.
* Update Ollama Autoconfiguration to use the new ToolCallingManager.
* Improved troubleshooting for new tool calling APIs and finalised changes for full backward compatibility.
* Updated Ollama Testcontainers dependency to 0.5.7.
Relates to gh-2049
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Refactors the test codebase to use tools instead of functions.
- Rename FunctionCallback to FunctionToolCallback
- Rename FunctionCallingOptions to ToolCallingChatOptions
- Update API methods from functions() to tools()
- Deprecate function-related methods in favor of tool alternatives
- Refactor MethodToolCallback implementation with improved builder pattern
- Update all tests to use new tool-based APIs
- Add funcs to tools migration guide
Signed-off-by: Christian Tzolov <christian.tzolov@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
- 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.
Signed-off-by: Alexandros Pappas <alexandros.pappas@yiluhub.com>
- Accumulate the token usage when toolcalling is invoked
- Fix both call() and stream() methods
- Add `usage` field to the Chat completion choice as the usage is returned via Choice
- Add Mootshot chatmodel ITs for functioncalling tests
Move the tests into MoonshotChatModelFunctionCallingIT
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>
* Remove use of Document.getContext method from spring-ai-core, use getText
* Remove deprecated ChatOptionsBuilder class
* Remove deprecated FunctionCallingOptionsBuilder class
- Modify the streaming vs call usage assertion to match the close to 25% value
- This change is done because the OpenAI chat response for call and stream invocation results in slight change in usage.
