- Add remaining deepseek modules
- Fix build order to put autoconfig modules after model modules to fix javadoc build
Signed-off-by: GR <gr@fastball.dev>
- Comment out AsyncCompletionSpecification and SyncCompletionSpecification imports
- Comment out completion parameters and processing in both sync and async server creation methods
- Downgrade MCP SDK version from 0.10.0-SNAPSHOT to 0.9.0
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Add support for completion specifications in both sync and async MCP servers by:
- Adding parameters for SyncCompletionSpecification and AsyncCompletionSpecification
- Implementing registration of completion specifications in server builders
- Updating capabilities builders to include completions
- Upgrading MCP SDK version to 0.10.0-SNAPSHOT
Signed-off-by: Christian Tzolov <christian.tzolov@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 new TemplateRenderer API providing the logic for rendering an input template.
- Update the PromptTemplate API to accept a TemplateRenderer object at construction time.
- Move ST logic to StTemplateRenderer implementation, used by default in PromptTemplate. Additionally, make start and end delimiter character configurable.
Relates to gh-2655
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Update multiple dependency versions including:
- Milvus from 2.5.4 to 2.5.7
- Azure Search from 11.6.1 to 11.7.6
- Weaviate client from 5.0.1 to 5.2.0
- Typesense from 0.5.0 to 1.3.0 (with matching code update)
- OpenSearch client from 2.10.1 to 2.23.0
- MariaDB from 3.5.1 to 3.5.3
- Couchbase from 3.7.8 to 3.8.0
- Neo4j Cypher DSL from 2024.0.2 to 2024.5.1
- Jedis from 5.1.0 to 5.2.0
Updates TypesenseVectorStore to use IndexAction enum instead of string literal.
Signed-off-by: Soby Chacko <soby.chacko@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>
- Update MCP SDK version to 0.9.0
- Add baseUrl and sseEndpoint properties to McpServerProperties
- Update WebFlux and WebMvc server transport providers to use new URL configuration properties
- Remove deprecated backward compatibility code and related tests
- Remove deprecated methods from McpToolUtils
- Update MCP SDK version to 0.9.0-SNAPSHOT
- Add tool filtering capability to MCP Tool Callback Providers
Introduces a BiPredicate-based filtering mechanism for both Sync and Async
MCP Tool Callback Providers, allowing selective tool discovery based on
custom criteria. This enables filtering tools by name, client, or
any combination of properties.
* Apply filter in getToolCallbacks() methods for both providers
* Add tests for various filtering scenarios
- Add utility method to retrieve MCP exchange from tool context
* Add constant TOOL_CONTEXT_MCP_EXCHANGE_KEY to replace hardcoded exchange string
* Implement getMcpExchange utility method to safely retrieve the MCP exchange object
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
Extract functionality from spring-ai-core into dedicated modules:
- spring-ai-commons: Common utilities and document handling
- spring-ai-model: Core model interfaces and implementations
- spring-ai-vector-store: Vector store abstraction and implementation
This modularization creates clearer responsibility boundaries and allows
consumers to include only what they need. The restructuring will make the
codebase easier to maintain and extend as the project grows.
- Rename Registration classes to Specification (SyncToolRegistration → SyncToolSpecification)
- Update transport classes to use Provider suffix (WebFluxSseServerTransport → WebFluxSseServerTransportProvider)
- Add exchange parameter to handler methods for better context passing
- Introduce McpBackwardCompatibility class to maintain backward compatibility
- Update MCP Server documentation to reflect new API patterns
- Add tests for backward compatibility
- Update mcp version to 0.8.0
- Add mcp 0.8.0 breaking change note-
The changes align with the MCP specification evolution while maintaining backward compatibility through deprecated APIs.
refactor: Extract MCP tool callback configuration into separate auto-configuration
Extracts the MCP tool callback functionality from McpClientAutoConfiguration into a
new dedicated McpToolCallbackAutoConfiguration that is disabled by default.
- Created new McpToolCallbackAutoConfiguration class that handles tool callback registration
- Made tool callbacks opt-in by requiring explicit configuration with spring.ai.mcp.client.toolcallback.enabled=true
- Removed deprecated tool callback methods from McpClientAutoConfiguration
- Updated ClientMcpTransport references to McpClientTransport to align with MCP library changes
- Added tests for the new auto-configuration and its conditions
refactor: standardize tool names to use underscores instead of hyphens
- Change separator in McpToolUtils.prefixedToolName from hyphen to underscore
- Add conversion of any remaining hyphens to underscores in formatted tool names
- Update affected tests to reflect the new naming convention
- Add comprehensive tests for McpToolUtils.prefixedToolName method
- Add integration test for payment transaction tools with Vertex AI Gemini
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Update dependencies and module names in maven pom.xml files affecting couchbase vector store support
- Rename artifact from spring-ai-couchbase-store-spring-boot-starter to spring-ai-starter-vector-store-couchbase
- Update imports and related cleanup
- Update corresponding documentation references
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Split model autoconfigurations based on the model
- Change the autoconfiguration class into model specific autoconfigurations - chat, embedding, image etc.,
- Update/add tests based on this change
- Make sure the conditional logic to enable the model auto configuration is at the class level so that the configuration properties as well as the models are not enabled when the model is explicitly disabled. By default, the condition will allow enabling the beans if not explicitly overridden.
- Remove spring-ai-spring-boot-autoconfigure as a dedicated auto-configuration module
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Conditionally enable invidividual models within the provider
- Introduce top level properties to support conditional logic
- The properties will have the format like "spring.ai.model.<chat/embedding/image etc.,>=<provider>" to enable specific chat/embedding/image/audio/moderation models by the provider. By default, these will be enabled when no specific properties are set. To disable, set any value other than the provider name for example, "none"
- For the auto configurations where the provider has multiple models, split the autoconfiguration into per model auto-configuration classes. This will enable the isolated auto-configurations for each provider and its model.
- This PR addresses this for OpenAI and others will follow in subsequent PRs
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Update the vector store starters with the new observation autoconfig dependency
Other maven configuraiton changes
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Move vector store auto-configuration classes to dedicated modules under auto-configurations/vector-stores/:
- Creates separate modules for Cassandra, Chroma, Elasticsearch, GemFire, HanaDB, MariaDB, MongoDB Atlas, Neo4j, OpenSearch, Oracle, PGVector, and Redis vector stores
- Updates package names to follow the pattern org.springframework.ai.vectorstore.<implementation>.autoconfigure
- Renames corresponding starter modules to follow the pattern spring-ai-starter-vector-store-<implementation>
- Updates import paths in affected classes
- Relocates test resources alongside their respective implementations
- Updates imports in spring-ai-spring-boot-docker-compose and spring-ai-spring-boot-testcontainers
This change improves modularity by allowing each vector store implementation to be
independently versioned and maintained, following the migration pattern established
with previous vector store autoconfiguraiton and starters .
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Move vector store auto-configuration classes to dedicated modules under auto-configurations/vector-stores/:
- Creates separate modules for Milvus, Pinecone, Qdrant, and Typesense vector stores
- Moves CommonVectorStoreProperties to spring-ai-core for better reusability
- Updates pom.xml dependencies to maintain proper relationships between modules
- Name the artifacts based on the pattern spring-ai-autoconfigure-vector-store-<implementation>.
For example - spring-ai-autoconfigure-vectore-store-milvus
- Package names follow the pattern org.springframework.ai.vectorstore.<implementation>.autoconfigure
- Naming the correspondinbg starter modules accordingly (spring-ai-starter-vector-store-milvus for example).
This change improves modularity by allowing each vector store implementation to be
independently versioned and maintained, continuing the migration pattern established
with previous vector stores.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Split spring-ai-spring-boot-autoconfigure into modules
- This PR addresses the restructuring of the following spring boot autoconfigurations:
- spring-ai retry -> common
- spring-ai chat client/model/memory -> chat
- spring-ai chat/embedding/image observation -> observation
- spring-ai chat/embedding models -> models
- Update the Spring AI BOM and boot starters with the new autoconfigure modules
- Rename the autoconfiguration and starters
- The package name for the models in autoconfiguration classes will have `org.springframework.ai.model.<name>.autoconfigure`
- Both the autoconfiguration and starters will have the prefix `spring-ai-autoconfigure-model` and `spring-ai-starter-model` respectively
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
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>
