- Integrate ObservationRegistry and EmbeddingModelObservationConvention
- Update TransformersEmbeddingModel to use observations
- Add TransformersEmbeddingModelObservationTests
- Update TransformersEmbeddingModelAutoConfiguration for observation support
- Add ONNX to AiProvider enum
- Adding observability for Vertex Gemini chat model streaming call
- Updating auto-configuration for gemini chat model with the observability components
- Integration test for streaming observability
- Implement observation instrumentation for AzureOpenAiEmbeddingModel
- Create AzureOpenAiEmbeddingModelObservationIT for integration testing
- Update AzureOpenAiAutoConfiguration to support observation
- Introduce ObservationRegistry and observation conventions
- Integrate ObservationRegistry for instrumentation in VertexAiGeminiChatModel's non-streaming call
- Add ChatModelObservationContext and related classes for observation
- Refactor createGeminiRequest method to support runtime options for imperative calls
- Implement observation for non-streaming chat operations in VertexAiChatModelObservationIT
- Add VertexAiGeminiConstants class for provider name
This commit enhances the VertexAiGeminiChatModel with observability features
for the non-streaming, imperative call() method. It allows for better
monitoring and instrumentation of synchronous chat operations. The changes
include refactoring to improve runtime option handling for these calls and
adds integration tests for the new observability features.
- Replaced `Map<String, Object>` with `ToolContext` in the `FunctionCallback`, `AbstractFunctionCallback`, and related classes.
- Updated all BiFunction definitions to use `ToolContext` as the second parameter,
enhancing the clarity and structure of the tool context management.
- Modified `FunctionCallbackWrapper` and `FunctionCallbackContext` to adapt to the new `ToolContext` parameter.
- Adjusted the handling of tool context in the documentation and test classes.
- Updated relevant test cases to reflect the API changes and modified the function handling logic to ensure consistency.
- Introduce toolContext to ChatClient, DefaultChatClient, and AdvisedRequest
- Add methods to set and manage toolContext via the FunctionCallingOptions
- Update tests to include toolContext in relevant scenarios
- Implement toolContext handling in function calling options
Unlike other metrics implementations supported by Micrometer, when using the Prometheus integration, all metric attributes are supposed to have a value, or else the related metrics are dropped.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Chat model observations support several key-value pairs, coming from the Spring AI abstractions.
Currently, whenever a value is not available (either because not configured by the user or not supported by the model provider), a span/metrics is generated anyway with value none.
That causes several issues, including an unneeded increase in time series, challenges in alerting/monitoring (especially for integer/double attributes that suddenly are populated with a string), and incompliance with the OpenTelemetry Semantic Conventions (according to which, attributes should be excluded altogether if there's no value).
This pull request changes the conventions for chat model observation to exclude the generation of span/metrics attributes for optional values which don't have any value.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
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
Implement observability for imperative calls in AzureOpenAiChatModel:
* Integrate ObservationRegistry to track metrics and events
* Create observation context and define conventions for consistency
* Add integration test to verify chat model observations
* Update AiProvider enum with new AZURE_OPENAI entry
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
This commit adds support for new Meta Llama 3.1 and 3.2 instruct models
to the LlamaChatBedrockApi enum. It includes model IDs for:
Llama 3.1: 8B, 70B, 405B
Llama 3.2: 1B, 3B, 11B, 90B
These additions allow users to specify the latest Llama models when
using the Bedrock API. The commit also updates the class Javadoc with
a link to AWS documentation for model IDs and bumps the @since version
to 1.0.0.
- Switch to OpenAIAsyncClient for streaming operations
- Modify AzureOpenAiChatModel constructor to accept OpenAIClientBuilder
- Update getChatCompletionsStream to use non-blocking async client
- Refactor related classes and tests to support OpenAIClientBuilder
- Revise AzureOpenAiAutoConfiguration to provide OpenAIClientBuilder
- Add AzureOpenAiChatClientTest to verify streaming functionality
- Adjust existing tests for compatibility with OpenAIClientBuilder
Resolves https://github.com/spring-projects/spring-ai/issues/981
This change improves support for asynchronous streaming operations
in the AzureOpenAiChatModel, addressing potential issues in reactive environments.
Resolves https://github.com/spring-projects/spring-ai/issues/832
Introduces retry functionality to VertexAI embedding and
chat models, enhancing their resilience against transient failures.
It also corrects a typo in the VertexAiEmbeddingConnectionDetails
class name.
Key changes:
* Add RetryTemplate to VertexAiTextEmbeddingModel and VertexAiGeminiChatModel
* Introduce spring-ai-retry dependency
* Refactor code to support retry logic
* Update auto-configuration classes to incorporate retry functionality
* Fix typo in VertexAiEmbeddingConnectionDetails class name
remove extraneous commented out code
Add missing copyright headers, author etc.
This commit introduces a major overhaul of the advisor system in Spring AI,
improving modularity, type safety, and consistency
Core Changes:
- Replace RequestAdvisor and ResponseAdvisor with CallAroundAdvisor and StreamAroundAdvisor
- Introduce AdvisedRequest and AdvisedResponse classes for better encapsulation
- Deprecate RequestResponseAdvisor in favor of new advisor types
- Remove AdvisorObservableHelper class
Advisor Implementation Updates:
- Update AbstractChatMemoryAdvisor, MessageChatMemoryAdvisor, PromptChatMemoryAdvisor,
QuestionAnswerAdvisor, SafeGuardAroundAdvisor, SimpleLoggerAdvisor, and
VectorStoreChatMemoryAdvisor to implement new advisor interfaces
- Remove CacheAroundAdvisor (functionality likely moved elsewhere)
- Make CallAroundAdvisor and StreamAroundAdvisor extend Ordered interface
Client and Chain Management:
- Modify DefaultChatClient to use new advisor chain approach
- Refactor DefaultAroundAdvisorChain for better ordering and observation
- Implement builder pattern for advisor chain construction in DefaultChatClient
- Separate call and stream advisors in DefaultAroundAdvisorChain
Observation and Context Handling:
- Update observation conventions and context handling in advisors
- Add order field to AdvisorObservationContext
- Modify DefaultAdvisorObservationConvention to include order in high cardinality key values
Testing and Integration:
- Refactor ChatClientAdvisorTests and add new AdvisorsTests
- Update integration tests to reflect new advisor structure
- Enhance AdvisorsTests to verify correct advisor execution order
New Features:
- Generalize the Protect From Blocking functionality across all advisors
- Add (experimental) Re2 advisor to enhance reasoning capabilities of LLMs
- Add disabled Re2 test in OpenAiChatClientIT
Documentation:
- Add Advisors documentation
- Enhance advisors documentation with order explanation and Re2 example
Advisor Ordering:
- Introduce Advisor constants for precedence ordering
- Update AbstractChatMemoryAdvisor to use new precedence constant
- Improve advisor ordering and management in DefaultAroundAdvisorChain.Builder
- Remove redundant reordering logic from DefaultAroundAdvisorChain
These changes aim to provide a more flexible and powerful advisor system,
allowing for easier implementation of complex AI-driven interactions
Co-authored-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
An upper bound for the number of tokens that can be generated for a completion,
including visible output tokens and reasoning tokens.
Replaces max_tokens field which is now deprecated.
This is related to https://github.com/spring-projects/spring-ai/issues/889
This commit addresses a bug where certain fields were being made
indirectly mandatory due to Assert.notNull checks in the Builder's
with* methods. Specifically:
- Removed Assert.notNull checks from withResponseFormat, withSeed,
withLogprobs, withTopLogprobs, and withEnhancements methods.
These checks were causing exceptions in AzureOpenAiChatModel.getDefaultOptions
when not all fields were set, leading to failures in methods like
ChatClient.create, even when using the AzureOpenAiChatModel constructor
with OpenAIClient.
The removal of these checks aligns with the @JsonInclude(Include.NON_NULL)
annotation on AzureOpenAiChatOptions, which already ignores null options.
This change maintains the intended flexibility while preventing unintended
mandatory requirements.
This commit introduces support for Oracle Cloud Infrastructure (OCI)
GenAI embedding models in Spring AI. It includes:
* New OCIEmbeddingModel class for interacting with OCI GenAI API
* Auto-configuration for easy setup and integration
* Properties for configuring OCI connection and embedding options
* Documentation updates explaining usage and configuration
* Integration tests to verify functionality
Signed-off-by: Anders Swanson <anders.swanson@oracle.com>
- 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 change introduces a new field for tracking reasoning tokens in the
OpenAI API response. It extends the Usage record to include
CompletionTokenDetails, allowing for more granular token usage
reporting. The OpenAiUsage class is updated to expose this new data,
and corresponding unit tests are added to verify the behavior.
This enhancement provides more detailed insights into token usage,
particularly for advanced AI models that separate reasoning from other
generation processes.
Add missing options from Azure ChatCompletionsOptions to Spring AI
AzureOpenAiChatOptions. The following fields have been added:
- seed
- logprobs
- topLogprobs
- enhancements
This change ensures better alignment between the two option sets,
improving compatibility and feature parity.
Resolves https://github.com/spring-projects/spring-ai/issues/889
- Add handling for cases where ChatCompletion has a stop reason but empty generations.
Creates a Generation with empty content and metadata when this occurs.
- Update AnthropicChatModelObservationIT to expect "end_turn" finish reason.
- Update javadoc.
- When ChatClientRequestSpec#prompt(Prompt) is used, unseal the prompt instance.
Convert the last message instance (if user message) into spec#user and spec#media
and add the remaining messages (excluding the last) to the spec#messages.
Add the prompt#options to the spec#options.
- Improve DefaultChatClient to handle UserMessage media and content separately.
- Update AbstractToolCallSupport to use new hasToolCalls() method.
- Add hasToolCalls() method to AssistantMessage.
- Enhance ChatClientTest with additional test cases for media handling.
- Disable Groq and Nvidia integration tests due to rate limiting and credit requirements.
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
This commit introduces support for the Watsonx.ai embedding model.
It includes:
- Watsonx embedding options class with tests
- Watsonx embedding model implementation
- Auto-configuration and properties for the embedding model
- Tests for the Watsonx embedding model
- Documentation for using the Watsonx embedding model
Also removed use of deprecated APIs in WatsonAIChatModel
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>
