Fixes: #938
Issue link: https://github.com/spring-projects/spring-ai/issues/938
This commit integrates Couchbase as a vector store option in Spring AI, providing:
- CouchbaseSearchVectorStore implementation with vector similarity search capabilities
- Support for metadata filtering with SQL++ expression conversion
- Spring Boot auto-configuration and starter module for easy integration
- Comprehensive documentation covering setup, configuration, and usage examples
- Integration tests using TestContainers with Couchbase 7.6
The implementation supports configuring dimensions, similarity functions (dot_product/l2_norm),
and optimization strategies (recall/latency). Schema initialization is now opt-in via
the initializeSchema property. Documentation includes both auto-configuration and
manual configuration instructions, along with property configuration details.
Signed-off-by: Abhiraj <abhiraj.official15@gmail.com>
co-authored-by: Laurent Doguin <laurent.doguin@gmail.com>
- Update ToolCallback import to use relative package path
- Remove qodana.yaml file from the project
Signed-off-by: gongzhongqiang <gongzhongqiang@apache.org>
This change ensures that @Tool annotated methods can be properly discovered even when the tool objects are wrapped
in Spring AOP proxies, which is common when using aspects or other proxy-based features.
- Enhance MethodToolCallbackProvider to properly handle AOP proxied tool objects by detecting proxies
and retrieving their target classes when scanning for @Tool annotated methods.
- Add test suite in MethodToolCallbackProviderAopTests.java to verify AOP proxy handling
Resolves#2356
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Adding `equals` and `hashCode` methods for proper object comparison.
- Implementing a deep `copy()` method, creating new instances of mutable collections (List, Set, Map, Metadata) to prevent shared state.
- Adding `AzureOpenAiChatOptionsTests` to verify `copy()`, builders, setters, and default values.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
- Reorganize sections to focus on Milestones vs Snapshots instead of specific versions
- Add Central Portal Snapshots repository configuration for both Maven and Gradle
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Fix Embedding equals() using Arrays.equals() for embedding array comparison
- Fix Embedding hashCode() using Arrays.hashCode() for proper array hashing
- Add final modifiers to fields in Embedding classes
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Add null check for isError() method in SyncMcpToolCallback
- Implement consistent error handling in AsyncMcpToolCallback to match SyncMcpToolCallback behavior
- Throw IllegalStateException with error content when tool calls fail
Resolves#2447
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Co-authored-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Add SseHttpClientTransportAutoConfigurationTests to verify conditional bean creation for HTTP client transports
- Add SseWebFluxTransportAutoConfigurationTests to verify conditional bean creation for WebFlux client transports
- Test both auto-configurations with various conditions including presence/absence of WebFluxSseClientTransport and MCP client enabled/disabled states
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Existing example displays a typo in the code example for Runtime Options:
ChatResponse response = chatModel.call(
new Prompt(
"Generate the names of 5 famous pirates.",
OpenAiChatOptions.builder()
.model("gpt-4-o")
.temperature(0.4)
.build()
));
Using gpt-4-0 generates this error:
org.springframework.ai.retry.NonTransientAiException: 404 - {
"error": {
"message": "The model `gpt-4-o` does not exist or you do not have access to it.",
"type": "invalid_request_error",
"param": null,
"code": "model_not_found"
}
}
Changing the model String in the example to "gpt-4o" resolves this.
Replace direct dependencies with ObjectProvider pattern in SSE transport auto-configurations.
- Uses ObjectProvider for ObjectMapper and WebClient.Builder dependencies
- Removes redundant @ConditionalOnMissingBean methods
- Provides fallback instantiation when dependencies are not available
Resolves#2440
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Add prefixedToolName utility method to ensure consistent tool name formatting
- E nforce alphanumeric, underscore, and hyphen characters only in tool names
- Limit tool names to 64 characters maximum
- Use original tool name in actual calls while using formatted names in definitions
- Add error handling for tool call responses in SyncMcpToolCallback
- Update tests to reflect the changes
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Remove deprecations from models, vector stores and usage
- Deprecations from FunctionCallback and ObservationContext/Convention will be in a separate PR
Models updates
- Remove AbstractToolCallSupport from the models which use ToolCallingManager
- Remove deprecated constructors and their usage
- Remove FunctionCallbackResolver and FunctionCallbacks usage in the models
- Add back deprecations for VectorStoreChatMemoryAdvisor until builder is fixed
- Update OpenAiPaymentTransactionIT to use ToolCallbackResolver in config
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Enhances MCP tool naming by prefixing tool names with their client + transport name
to prevent conflicts when multiple MCP clients expose tools with the same name.
- Modifies client info in McpClientAutoConfiguration to include transport name
- Updates SyncMcpToolCallback and AsyncMcpToolCallback to prefix tool names with client + transport name
- Adds test coverage for tools with identical names but different client info
Resolves#2393
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Implement the new ToolCallback.call(String, ToolContext) method in both Sync and Async MCP tool callbacks.
- Since MCP tools don't support tool context, the implementation ignores the context parameter and
delegates to the existing call(String) method. Added test to verify the behavior.
Resolves#2378
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
When streaming happens on an event loop, due to the fact that currently
tools can only be synchronous and blocking, every tool call needs to be
offloaded to a blocking-safe Scheduler.
Resolves#2341
Signed-off-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
When using the RetrievalAugmentationAdvisor with the VectorStoreDocumentRetriever, it’s now possible to provide a filter expression at request-time as an advisor context variable with key VectorStoreDocumentRetriever.FILTER_EXPRESSION.
Fixes gh-1776
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
This commit introduces the `JsoupDocumentReader` and `JsoupDocumentReaderConfig` classes, which provide functionality to read and parse HTML documents using the JSoup library.
The reader supports:
- Extracting text from specific HTML elements using CSS selectors.
- Extracting all text from the body of the document.
- Grouping text by element.
- Extracting metadata, including the document title, meta tags, and link URLs.
- Reading from various resource types (files, URLs, byte arrays).
- Configurable character encoding, selector, separator, and metadata extraction.
This new reader enhances Spring AI's ability to process web content and other HTML-based data sources.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
- Make MCP client initialization blocking with .block() call
- Upgrade MCP SDK version from 0.7.0 to 0.8.0-SNAPSHOT
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Updated `SearchRequest.java` to make the class non-final.
- Added `MilvusSearchRequest` with specific Milvus parameters such as `nativeExpression` and `searchParamsJson`.
- Modified `doSimilaritySearch` method in `MilvusVectorStore` to handle these new fields from `MilvusSearchRequest`.
Add unit tests for MilvusVectorStore and MilvusSearchRequest
Introduce comprehensive unit tests to validate the functionality of MilvusVectorStore and MilvusSearchRequest, including scenarios for native and filter expressions. Refactor MilvusVectorStore to improve filter expression handling by introducing a helper method for converted expressions.
Add detailed documentation for MilvusSearchRequest usage
Introduced sections explaining MilvusSearchRequest's parameters, `nativeExpression`, and `searchParamsJson`, with examples for enhanced clarity. This update provides guidance on leveraging Milvus-specific features for precise filtering and optimal search performance.
Signed-off-by: waileong <wai_leong1015@hotmail.com>
This enhancement adds a documentFormatter parameter to ContextualQueryAugmenter,
allowing users to customize how documents are formatted in the context.
If not specified, the original document formatting logic is preserved.
Signed-off-by: magicgone <magic4gone@gmail.com>
This commit enhances `AnthropicChatOptions` by:
- Adding `equals` and `hashCode` methods for proper object comparison.
- Implementing a deep `copy()` method, creating new instances of mutable collections (List, Set, Map, Metadata) to prevent shared state.
- Adding `AnthropicChatOptionsTests` to verify `copy()`, builders, setters, and default values.
Signed-off-by: Alexandros Pappas <apappascs@gmail.com>
Add capability to specify MIME types for MCP tool responses, with special handling for image content.
This enhancement allows tools to return different content types, particularly images, by:
- Adding a new toolResponseMimeType map property to configure response MIME types per tool
- Extending tool registration methods to accept and use MIME type information
- Adding special handling for image content in tool responses
- Updating documentation with the new configuration options
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
