Replace spring-ai-client-chat dependency with spring-ai-model in model implementations
and memory repositories, and with spring-ai-commons in document readers. This change
improves the dependency structure by having components depend on the appropriate
abstraction level.
Additional changes:
- Add slf4j-api dependency to pdf-reader and spring-ai-retry
- Move spring-ai-client-chat to test scope in spring-ai-ollama
- Fix XML formatting in some pom.xml files
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Override adviseStream method in VectorStoreChatMemoryAdvisor to properly handle streaming responses
- Add tests to verify the fix works with both normal and problematic streaming scenarios
Fixes#3152
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- The fix overrides the adviseStream method to use ChatClientMessageAggregator to properly aggregate streaming chunks before storing them in memory, similar to how PromptChatMemoryAdvisor handles streaming responses
- Added test
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- Remove deprecated ChatMemory.get(String conversationId, int lastN) method
- Replace AbstractChatMemoryAdvisor with BaseChatMemoryAdvisor interface in api package
- Make constructors private in all memory advisor implementations to enforce builder usage
- Rename CHAT_MEMORY_CONVERSATION_ID_KEY to CONVERSATION_ID and move to ChatMemory interface
- In VectorStoreChatMemoryAdvisor:
- Rename DEFAULT_CHAT_MEMORY_RESPONSE_SIZE (100) to DEFAULT_TOP_K (20)
- Rename builder method chatMemoryRetrieveSize() to topK()
- Remove systemTextAdvise() builder method
- In PromptChatMemoryAdvisor:
- Remove systemTextAdvise() builder method
- Fix bug where only the last user message was stored from prompts with multiple messages
- Enhance logging in memory advisors to aid in debugging
- Add comprehensive tests for all advisor implementations:
- Unit tests for builder behavior
- Integration tests for the various chat memory advisors
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- Enhance MethodToolCallback to properly handle generic types by using parameterized types
- Add unit tests for generic type handling (List, Map<String,Integer>, nested generics)
- Add integration tests for both Anthropic and OpenAI clients to verify tool calls with generic argument types
Resolves#2462
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- For all the model response API objects, add `@JsonIgnoreProperties(ignoreUnknown = true)`
which provides flexibility to ignore any unknown properties which come as part of the response
Resolves#3026
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Introduced mutate() methods to OpenAiApi and OpenAiChatModel, enabling creation of new builder instances from existing objects.
- Allows safe modification and copying of configuration for APIs and models.
- Refactored internal fields and getters to support mutation/copy patterns.
- Updated integration tests to leverage mutate for dynamic client creation.
This PR adds support for retrieving web search annotations from the OpenAI API, as described in their [web search documentation](https://platform.openai.com/docs/guides/web-search). This allows us to access citation URLs and their context within generated responses when using models like `gpt-4o-search-preview`.
**Changes:**
* Added `annotations` (with `Annotation` and `UrlCitation` records) to `ChatCompletionMessage` in `OpenAiApi.java`.
* Updated `OpenAiChatModel` to populate the `annotations` field (via metadata) for both regular and streaming responses.
* Added integration tests (`webSearchAnnotationsTest`, `streamWebSearchAnnotationsTest`) to `OpenAiChatModelIT.java`.
* Added `GPT_4_O_SEARCH_PREVIEW` and `GPT_4_O_MINI_SEARCH_PREVIEW` to `OpenAiApi.ChatModel`.
* Added `WebSearchOptions` and related records to `OpenAiApi`.
* Minor updates to `ChatCompletionRequest` and its `Builder`.
Resolves#2449
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
Remove circular dependencies:
Move utility classes from various packages to dedicated support packages:
- Move ToolCallbacks from ai.tool to ai.support
- Move UsageUtils to UsageCalculator in ai.support
- Move tool.util to tool.support
- Create new ToolDefinitions utility class
Support packages for the classes in question is more idomatic in spring than util packages.
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
Fixes: #1378
- Add warnings for unsupported frequency/presence penalty in Anthropic API
- Add warnings for unsupported frequency/presence penalty and topK in BedrockProxyChatModel
- Add warning for unsupported topK in OpenAI chat models
- Implement frequency and presence penalty parameters for Vertex AI Gemini model
- Update Vertex AI Gemini options and tests
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Renamed all occurrences of supportStFunctions to validateStFunctions for clarity.
- Updated default field, constructor, and builder method to use new naming.
- Improved getInputVariables logic to better distinguish variables, function calls, and property access.
- Ensured built-in functions accessed as properties are only skipped when validateStFunctions is true.
- Enhanced builder usage to reflect new flag and naming.
- More tests added
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
Since the builders for HTTP clients are mutable and shared, they should
only be configured with globally applicable settings. The current use
leaks specific details into other usages and affects newly instantiated
clients. This PR applies the clone() method right before mutation
happens as it probably is the strategy that avoids multiple unnecessary
copies.
feat: improve RestClient and WebClient instantiation and configuration across AI modules
- Ensure RestClient.Builder and WebClient.Builder are properly cloned before setting base URLs and headers in Mistral, OpenAI, and Ollama API classes to prevent side effects.
- Add WebClientAutoConfiguration to auto-configuration classes for Anthropic and Mistral AI modules.
- Update Mistral AI auto-configuration to inject and use WebClient.Builder.
- Clean up test and annotation usage (remove unnecessary @Nullable, fix test builder usage in AnthropicApiIT).
- Improve consistency and reliability of HTTP client configuration across model integrations.
Signed-off-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Co-authored-by: Christian Tzolov <christian.tzolov@broadcom.com>
* Update remaining Advisors and related classes to use the new APIs.
* In AbstractChatMemoryAdvisor, the “doNextWithProtectFromBlockingBefore()” protected method has been changed from accepting AdvisedRequest to ChatClientRequest. It’s a breaking change since the alternative was not part of M8.
* MessageAggregator has a new method to aggregate messages from ChatClientRequest. The previous method aggregating messages from AdvisedRequest has been removed. Warning since it wasn’t marked as deprecated in M8.
* In SimpleLoggerAdvisor, the “requestToString” input argument needs to be updated to use ChatClientRequest. It’s a breaking change since the alternative was not part of M8. Same thing about the constructor.
* The “getTemplateRenderer” method has been removed from BaseAdvisorChain. Each Advisor is encouraged to accept a PromptTemplate to achieve self-contained prompt augmentation operations.
* Remove deprecations in ChatClient and Advisors, and update tests accordingly.
* When building a Prompt from the ChatClient input, the SystemMessage passed via systemText() is placed first in the message list. Before, it was put last, resulting in errors with several model providers.
Relates to gh-2655
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
This commit makes several improvements to the OpenAiImageOptions class:
1. Remove all deprecated methods from OpenAiImageOptions.Builder:
- Removed withN(), withModel(), withQuality(), withResponseFormat(),
withWidth(), withHeight(), withStyle(), and withUser() methods
- These were marked as @Deprecated(forRemoval = true, since = "1.0.0-M8")
2. Align OpenAiImageOptions structure with OpenAiChatOptions:
- Added fromOptions() static method for creating copies
- Added copy() instance method
- Updated Builder class to match pattern in OpenAiChatOptions
- Changed Builder field from private final to protected
- Added Builder constructor that takes an existing options object
3. Enhance setSize() method to maintain consistency:
- Updated setSize() to parse the size string and update width/height properties
- Added proper error handling for invalid formats
- Ensures consistent state between size, width, and height properties
4. Comprehensive test coverage improvements:
- Added tests for builder pattern with all fields
- Added tests for copy functionality
- Added tests for all setter methods
- Added tests for default values
- Added tests for equals(), hashCode(), and toString() methods
- Added specific tests for the updated setSize() behavior
- Fixed test expectations to match actual implementation behavior
These changes improve code consistency, maintainability, and test coverage
while removing deprecated methods that were scheduled for removal.
Signed-off-by: jonghoonpark <dev@jonghoonpark.com>
- Remove deprecated constructor method Media(MimeType mimeType, URL url) from Media
- Remove deprecated builder method data(URL url) from Media builder
- Update references to use the builder and the data(URI) methods
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Remove the deprecated constructors from PromptTemplate and replace the references using the builder methods
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Move evaluation core classes (Request, Response, Evaluator) to spring-ai-commons.
- Move chat-specific evaluators (FactChecking, Relevancy) to spring-ai-client-chat#evaluation package.
- Move OutputConverter implementations and related classes to spring-ai-model#converter package.
- Move MetadataEnricher transformer classes to spring-ai-model#transformer package.
- Move PromptAssert utility to spring-ai-rag#util package.
- Update relevant pom.xml files and adjust imports in affected classes.
- Document class movements in upgrade-notes.adoc for M8 release.
This refactoring improves module organization and separation of concerns.
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
Renames the ambiguous overloaded `tools` methods in `ChatClient.PromptRequestSpec`
to `toolNames` and `toolCallbacks` respectively. This improves clarity
and prevents potential issues with method dispatching based on argument types.
Updates relevant code examples and adds documentation to upgrade notes.
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
This reverts commit 4eeeb83d3f.
Revert "Make ImageOptions non-null when constructing ImagePrompt"
This reverts commit 0c0787b849.
Need to review more the impact of making these options not null.
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Extend the ChatClient with a new templateRenderer() method to pass a custom TemplateRenderer object used to render user and system templates.
- Evolve the QuestionAnswerAdvisor to accept a PromptTemplate for customising the RAG prompt and templating logic while maintaining backward compatibility.
- Introduce integration tests for the QuestionAnswerAdvisor.
- Document the TemplateRenderer API and how to use it to build PromptTemplate with custom templating logic.
- Document how to customise the templating logic used internally by the ChatClient via the TemplateRendererAPI.
Add validation tests and improve PromptTemplate resource handling
Enhance robustness and reliability of the PromptTemplate class with better
resource handling and comprehensive input validation:
- Add dedicated validation tests for builder methods with null/invalid inputs
- Improve renderResource method to gracefully handle edge cases:
- Null resources return empty string
- ByteArrayResource handling with proper charset (UTF-8)
- Empty resources check with proper existence test
- Better error handling with logging instead of exception propagation
- Add input validation assertions to all Builder methods
- Fix typo in deprecated annotation comment ("fahvor" → "favor")
Update documentation to clarify template rendering in different contexts:
- Add clear notes about TemplateRenderer usage in ChatClient vs Advisors
- Document how advisor template customization differs from ChatClient template rendering
- Add comprehensive API upgrade notes for template-related deprecations
- Include detailed migration examples for PromptTemplate and QuestionAnswerAdvisor
Fixes gh-355, gh-1687, gh-2448, gh-1849, gh-1428
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- The commit removes deprecated methods and parameters, including
- requestOptions in image observation context and proxyToolCalls in Vertex AI
- Gemini options. Updates code to use ImagePrompt.getOptions() instead of
- the separate parameter for more consistent API design.
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>
* 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>
- 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>
