Fixes: #2518
Issue: https://github.com/spring-projects/spring-ai/issues/2518
This commit removes the deprecated requestOptions field from ChatModelObservationContext
and EmbeddingModelObservationContext classes. Instead of passing options separately,
the code now retrieves them directly from the request objects (prompt.getOptions() or
embeddingRequest.getOptions()).
Key changes:
- Removed requestOptions parameter from observation context builders
- Updated all model implementations to stop passing options separately
- Fixed EmbeddingRequest handling in several model implementations
- Added buildEmbeddingRequest method in models to properly merge options
This change simplifies the API and removes duplication, as options are already
available in the request objects themselves.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- FunctionCallbackResolver is deprecated and replaced by ToolCallingManager's ToolCallbackResolver
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
* ChatMemory will become a generic interface to implement different memory management strategies. It’s been moved from the “”spring-ai-client-chat” package to “spring-ai-model” package while retaining the same package, so it’s transparent to users.
* A MessageWindowChatMemory has been introduced to provide support for a chat memory that keeps at most N messages in the memory.
* A ChatMemoryRepository interface has been introduced to support different storage strategies for the chat memory. It’s meant to be used as part of a ChatMemory implementation. This is different than before, where the storage-specific implementation was directly tied to the ChatMemory. This design is familiar to Spring users since it’s used already in the ecosystem. The goal was to use a programming model similar to Spring Session and Spring Data.
* The JdbcChatMemory has been supersed by JdbcChatMemoryRepository.
* A ChatMemory bean is auto-configured for you whenever using one of the Spring AI Model starters. By default, it uses the MessageWindowChatMemory implementation and stores the conversation history in memory. If a different repository is already configured (e.g., Cassandra, JDBC, or Neo4j), Spring AI will use that instead.
* First-class documentation has been introduced to describe the ChatMemory API and related features.
* All the changes introduced in this PR are backward-compatible.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Update ZhipuAI Chat Model to use ToolCalling Manager and ToolExecutionEligibilityPredicate
- Update ZhipuAI ChatOptions to implement ToolCallingChatOptions
- Update Autoconfiguration for ZhipuAI model to use ToolCallingAutoconfiguration
- Update tests
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Update Minimax Chat Model to use ToolCalling Manager and ToolExecutionEligibilityPredicate
- Update Minimax ChatOptions to implement ToolCallingChatOptions
- Update Autoconfiguration for MinimaxChat model to use ToolCallingAutoconfiguration
- Update tests
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Adjust MergeUtils to accommodate API changes:
- Update ChatCompletions constructor parameter list to remove the usage argument
- Move usage assignment to post-construction via reflection
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Introduce “ChatClientRequest” and “ChatClientResponse” for propagating requests/responses in a ChatClient advisor chain.
- Structure a Prompt at the beginning of the chain, to ensure a consistent view across execution chain and observations. Any template is rendered at the beginning so that every advisor doesn’t have to do it again.
- Improve observations to include the complete view of the prompt messages, instead of only considering userText and systemText.
- Remove legacy “around” advisor type concept.
- Keep backward compatibility for AdvisedRequest, AdvisedResponse, and legacy Advisor APIs.
Relates to gh-2655
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Sync the ChatModel enum with the latest OpenAI documentation:
- Reorganize models into categories.
- Add new models (o4-mini, o3, o1-pro, gpt-4.1 series, realtime previews).
- Update descriptions, context windows, max tokens, and knowledge cutoffs.
- Add links to official model documentation.
- Remove deprecated/preview models.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
- The ModelOptionsUtils merges the ToolCallingChatOptions with the provider chat options
- The underlying beanwrapper implementation expects the boolean option to have the getter method starting with "get" instad of "is" which makes the current `isInternalToolExecutionEnabled` not used by the merge operation at all. To fix this, rename the `isInternalToolExecutionEnabled` method to `getInternalToolExecutionEnabled` and deprecate the existing `isInternalToolExecutionEnabled` method.
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Docker Desktop 4.40 has released a Docker Model Runner, which is OpenAI compatible.
- Add docs for Docker Model Runner
Signed-off-by: Eddú Meléndez <eddu.melendez@gmail.com>
- Replace class-by-class scanning with comprehensive package-level scanning to capture
all JSON-annotated classes within each model's package hierarchy.
- Update tests to verify registered types and add specific type assertions.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
This change modifies the voice parameter in OpenAI Audio Speech API from using the
Voice enum directly to using the string value of the enum. This provides more
flexibility for handling voice options, especially for custom voices or when voice
names come from configuration.
- Change voice parameter type from Voice enum to String
- Add overloaded methods to accept both enum and string values
- Update tests and documentation to reflect these changes
Signed-off-by: jonghoon park <dev@jonghoonpark.com>
Implement MistralAI moderation capabilities to detect potentially harmful content.
This allows Spring AI applications to use Mistral's content moderation services
to identify and filter inappropriate content before processing
- Add MistralAiModerationApi for interacting with Mistral's moderation endpoints
- Create MistralAiModerationModel implementing the ModerationModel interface
- Add configuration properties and auto-configuration for the moderation model
- Extend Categories and CategoryScores with additional moderation categories
- Add integration tests to verify moderation functionality
Signed-off-by: Ricken Bazolo <ricken.bazolo@gmail.com>
- Accumulate token usage metrics when toolcalling is used
- Fix for both call() and stream() methods
- Add/update tests
Resolves#1992
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- The `thinking` option is added to `AnthropicChatOptions` and `ChatCompletionRequest`.
- The `AnthropicApi` and `AnthropicChatModel` now handle `THINKING` and `REDACTED_THINKING` content blocks in responses. New tests verify parsing of these blocks.
- Updated method signatures on ChatCompletionRequestBuilder, deprecating old builders with `with*` prefix in favor of those without.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
Introduce a new ToolExecutionEligibilityChecker interface to provide a more flexible way to determine
when tool execution should be performed based on model responses. This abstraction replaces the
hardcoded logic previously scattered across the codebase.
- Adds a new ToolExecutionEligibilityChecker interface in spring-ai-core
- Integrates the checker into OpenAiChatModel with appropriate defaults
- Updates OpenAiChatAutoConfiguration to support the new interface
- Provides a default implementation that maintains backward compatibility
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
refactor: Replace ToolExecutionEligibilityChecker with ToolExecutionEligibilityPredicate
- Replacing ToolExecutionEligibilityChecker with ToolExecutionEligibilityPredicate
- Changing from Function<ChatResponse, Boolean> to BiPredicate<ChatOptions, ChatResponse>
- Adding a DefaultToolExecutionEligibilityPredicate implementation
- Updating AnthropicChatModel and OpenAiChatModel to use the new predicate
- Updating auto-configurations to inject the new predicate
- Adding comprehensive tests for the new predicate implementation
The new approach provides a cleaner and more consistent way to determine when tool execution should be performed based on both prompt options and chat responses.
Add Bedrock Converse support
add mistral support
Add ollama and vertex gemini
add ToolExecutionEligibilityPredicate docs
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Avoid overlapping package names
Changed in spring-ai-commons package from org.sf.ai.model to org.sf.ai.content
Refactor advisor module name to be spring-ai-advisors-vector-store
Moved advisors into org.springframework.ai.chat.client.advisor.vectorstore
- Created top level memory directory
- Create new module spring-ai-model-chat-memory-neo4j and moved neo4j memory classes out of the vectorstore module
Updated neo4j autoconfiguation
- Add missing formats "wav" and "pcm" which OpenAI supports but SpringAI does not have serializers for
Signed-off-by: gabriel duncan <gabrielduncan@Mac.attlocal.net>
