* Surface more configuration APIs to ChatOptions
* Use abstraction in Observations directly instead of dedicated implementation
* Simplify metadata config in observations for defined models
* Improve merging of runtime and default options in OpenAI
* Fix missing option in Mistral AI
Relates to gh-1148
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Add `TEXT` to the supported ResponseFormat types
- Add JsonSchema record for structured output configuration
- Update OpenAI chat documentation with details on Structured Outputs
- Clarify usage of JSON_SCHEMA response format in properties and code examples
- Update Structured Output Converter docs to mention OpenAI Structured Outputs
- Added support for OpenAI's structured outputs feature, which allows specifying a JSON schema for the model to match
- Introduced new record to configure the desired response format
- Added support for configuring the response format via application properties or the chat options builder
- Extend teh BeanOutputConverter to help generate JSON schema from a target domain object and convert the response.
- Added comprehensive tests to cover the new response format functionality
Resolves#1196
- Updated OpenAiChatModel, OpenAiApi, and OpenAiStreamFunctionCallingHelper to include the `refusal` field in metadata.
- Adjusted constructors and methods to handle the new `refusal` attribute.
- Modified related tests to account for the new `refusal` field.
- Add the refusal field value to the Spring AI AssistantMessage metadata
Resolves#1178
Integrated Micrometer's Observation into the OpenAiChatModel#stream reactive chain.
Included changes:
- Added ability to aggregate streaming responses for use in Observation metadata.
- Improved error handling and logging for chat response processing.
- Updated unit tests to include new observation logic and subscribe to Flux responses.
- Refined validation of observations in both normal and streaming chat operations.
- Disabled retry for streaming which used RetryTemplate - should use .retryWhen operator as the next step.
- Added an integration test.
Resolves#1190
Co-authored-by Christian Tzolov <ctzolov@vmware.com>
* Add model and dimensions to option abstraction
* Use abstraction in Observations directly instead of dedicated implementation
* Clean-up the merge of runtime and default embedding options in OpenAI
Relates to #gh-1148
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Add style to option abstraction
* Use abstraction in Observations directly instead of dedicated implementation
* Clean-up the merge of runtime and default image options in OpenAI and Stability AI
Related to #1148
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Update OllamaEmbeddingModel to support batch embedding requests
- Rename EmbeddingRequest/Response to EmbeddingsRequest/Response
- Add truncate option to control input truncation
- Update documentation and tests for new embedding API
- Remove deprecated withModel and withDefaultOptions methods
- Adjust default values for various Ollama model options
- Include response medata with response model name
Resolves#1158
- Add org-id and project-id properties with unified merging logic
- Update autoconfig and docs for all OpenAI models
- Introduce OpenAiChatOptions#httpHeaders option
- Add integration test for httpHeaders and update docs
Resolves#1141
* Observation APIs for chat, embedding and image models
* Conventions based on OpenTelemetry Semantic Conventions for GenAI
* Instrumentation for OpenAI chat, embedding, and image models
* Autoconfiguration for observability for OpenAI
Fixes gh-953
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
The autoconfiguration adds the FunctionCallbacks directly to the model's ChatOptions,
which results in the FunctionCallback being included in the request each time it is called.
The modification registers the container's FunctionCallback directly to the model's functionCallbackRegister
using the parent AbstractToolCallSupport constsructor.
Replace the handleFunctionCallbackConfigurations by simplified runtimeFunctionCallbackConfigurations.
Co-authored-by Christian Tzolov <ctzolov@vmware.com>
- factor out the common funciton calling logic form AnthropicChatModel to the AbstractToolCallSupport.
- improve the AbstractToolCallSupport isToolCall to handle OpenAi and Anthropic.
- fix an issue with the function calling streaming aggreagation leading to lost usage statistics.
- small code improvements for OpenAiChatModel.
- extend the OllamaApi with Tool, ToolCalls and Function and add Tool Role.
- make OllamaChatModel extend the AbstractToolCallSupport.
- extend the OllamaChatModel to convert the Spring AI messages to OllamaApi messages, including Tools.
- OllamaOptions implements FunctionCallingOptions.
- add OllamaApiToolFunctionCallIT for testing function calling.
- patch the AbstractToolCallSupport#isToolCall to take set of stop resons.
- add FunctionCallbackInPromptIT and FunctionCallbackWrapperIT function calling auto-configuration tests.
- extend OllamAutoConfiguration to support function calling registration.
- add function call tests to OllamChatAutoConfigurationIT.
- add OllamaWithOpenAiChatModelIT to OpenAi that uses the OpenAI API to call Ollama.
- move buildToolCallConversation and handleToolCalls to parent AbstractToolCallSupport.
- update Docs. add Ollama function call docs.
- update Ollama diagrams.
Resolves#720
The Lambda functions do not retain the type information, so we need to provide the input type explicitly.
Resolves#1052
Co-authored-by: liuzhifei <2679431923@qq.com>
- Breaking changes: Classes from the org.springframework.ai.openai.metadata.audio.transcription package have been moved to the org.springframework.ai.audio.transcription package.
- The AzureOpenAiAudioTranscriptionModel has been added to the auto-configuration.
- The spring.ai.azure.openai.audio.transcription prefix was introduced for properties.
- Introduces options properties which cover all of them (see: AzureOpenAiAudioTranscriptionOptions).
- fix missing MutableResponseMetadata
- add docs
- adjust code to updated ResponseMetadata design
- add test to AzureOpenAiAutoConfiguration
- add missing AzureOpenAiAudioTranscriptionModel tests
- introduce copy() method to the ChatOptions.
- make sure that the DefaultChatClientRequestSpec takes a copy of the input chat options to prevent multation.
- add a OpenAiChatClientMultipleFunctionCallsIT to reproduce the problem and verify the solution.
Resolves#1064
