The RelevancyEvaluator is key for validating RAG flows. This pull request improves it by making the PromptTemplate configurable, improving the format of the default one, introducing a Builder, and extending the documentation with more details on how to use it.
I added some unit tests. The RelevancyEvaluator is used in lots of integration tests in the project to test the QuestionAnswerAdvisor and RetrievalAugmentationAdvisor, that also help assessing the evaluator itself.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Add context about reactive/imperative applications
* Fix typos and improve formatting
* Highlight Spring Boot 3.4 bug as IMPORTANT note
* Clarify tool calling impact on Micrometer observations
The current implementation of ConcatenationDocumentJoiner should sort the final document list by score in descending order, so to keep the most relevant documents at the front of the list. This PR fixes that.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
There seems to be some models not handling correctly the non-nullability of toolCallArguments when defining a tool call. For example, the Ollama implementation is always null-safe (if no tool argument, then '{}' is used). Other implementations might produce a null value.
This PR relaxes the toolCallArguments validation to support null toolCallArguments within ToolCallingObservationContext.
Fixes gh-3234
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Currently, the MCP Tool autoconfiguration defines the SyncMcpToolCallbackProvider and AsyncMcpToolCallbackProvider beans returning the ToolCallbackProvider interface. That generates autowiring warnings in IDEs when trying to inject the specific class.
The Spring Boot project recommends being specific. 'When declaring a @Bean method, provide as much type information as possible in the method’s return type. For example, if your bean’s concrete class implements an interface the bean method’s return type should be the concrete class and not the interface. Providing as much type information as possible in @Bean methods is particularly important when using bean conditions as their evaluation can only rely upon to type information that is available in the method signature.'
See https://docs.spring.io/spring-boot/reference/features/developing-auto-configuration.html#features.developing-auto-configuration.condition-annotations.bean-conditions
This PR ensures concrete classes are used.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Update Observability section with details about tool calling observability support
- Move "Migrating to ToolCallback API" guide from Tool Calling section to Upgrade Notes
- Update Observability section with details about tool calling observability support
Related to #3230
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Before this commit, the underlying `JdbcTemplate` is created like `new JdbcTemplate(providedJdbcTemplate.getDataSource())`, it means that settings on provided `JdbcTemplate` will lose.
Signed-off-by: Yanming Zhou <zhouyanming@gmail.com>
Before this commit, the underlying `JdbcTemplate` is created like `new JdbcTemplate(providedJdbcTemplate.getDataSource())`, it means that settings on provided `JdbcTemplate` will lose.
Signed-off-by: Yanming Zhou <zhouyanming@gmail.com>
Fixes: #3187
This commit addresses the issue with Spring environment variables that directly
mirror Spring AI application properties, which can confuse users into thinking
they should always set environment variables that match Spring property names.
Instead, we've replaced all instances of SPRING_* prefixed environment variables
in the documentation with custom-named alternatives that are referenced using
Spring Expression Language (SpEL) or retrieved programmatically.
Each documentation section now shows multiple configuration approaches:
- Direct property setting in application.properties/yml
- Using custom environment variables with SpEL
- Accessing environment variables programmatically
This gives users more flexibility while making it clear that using SPRING_*
prefixed environment variables is not required or recommended.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Add support for configuring request timeout in MCP server with a default of 20 seconds.
This timeout applies to all requests made through the client, including tool calls,
resource access, and prompt operations.
- Add requestTimeout property to McpServerProperties with default of 20s
- Configure server builder with the timeout value
- Add tests for default and custom timeout configurations
- Update documentation with the new property
Resolves#3205
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Fixes: #886
Add ability to configure path prefix for OpenSearch API endpoints via properties.
This allows connecting to OpenSearch instances running behind a reverse proxy
with a non-root path, similar to Spring Elasticsearch's path-prefix property.
- Add pathPrefix property to OpenSearchVectorStoreProperties
- Apply pathPrefix to OpenSearchClient when configured
- Add documentation and unit tests
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
The features are disabled by default and users need to explicitly
enable them. Probably it makes more sense to log on INFO level so that
users don't need to change the log level if they use the default
behavior of Spring Boot.
See gh-3003
See gh-3127
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>
samples() duplicates N(), both setting the same field.
Keeping only N() simplifies the builder API and aligns with ImageOptions.
Signed-off-by: Jhzlo <kjh0010703@naver.com>
Replaces redundant or conflicting stylePreset assignments with a single mergeOption call using runtime style and default stylePreset.
Signed-off-by: Jhzlo <kjh0010703@naver.com>
- Add capability configuration to enable/disable tools, resources, prompts, and completions individually
- Refactor server configuration to conditionally register capabilities based on configuration
- Add support for server instructions configuration
- Update documentation with new capability options and completion management
- Add tests for new capabilities and configurations
Resolves#3207
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>
- 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>
Fixes: 3160
https://github.com/spring-projects/spring-ai/issues/3160
When using a filter expression with IN operator on a collection field in
CassandraVectorStore.similaritySearch, a ClassCastException was thrown because
the code attempted to format individual collection elements using the collection's
codec instead of the element type's codec.
This fix modifies doValue to detect when we are formatting elements inside a
collection type and use the appropriate element type codec. While Cassandra
does not support using the IN operator directly on collection columns, this fix
ensures we generate syntactically correct CQL rather than throwing a Java
exception.
The change specifically addresses ListType collections by using the element type
codec for individual elements within the list.
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
Fixes: #3181https://github.com/spring-projects/spring-ai/issues/3181
When using CassandraVectorStore with an invalid index name and
initializeSchema=false, the application would throw a generic
NoSuchElementException from Optional.get() with message "No value present"
when trying to access the index metadata.
Changes:
- Added explicit validation of index existence in checkSchemaValid() method
- Improved error handling in getIndexSimilarity() method to provide a clear
error message when an index doesn't exist
- Added integration test to verify proper error handling with invalid index names
Signed-off-by: Soby Chacko <soby.chacko@broadcom.com>
- Updated computeRequestFilterExpression to check if the context value is already
a Filter.Expression object before attempting to parse it as a string
- Added docs for FILTER_EXPRESSION key that it accepts both String and Filter.Expression
- Added test
Fixes#3179
- Restructure navigation with clearer hierarchy using "Reference" and "Guides" sections
- Remove deprecated model-specific function calling documentation
- Update all model references to point to centralized Tool Calling documentation
- Rename "Docker Compose" to "Development-time Services" for clarity
- Move "Testing" under Reference section
- Add link to "Awesome Spring AI" community resources
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
GHA workflows are automatically executed on forks where they fail.
This change prevents this (only for those workflows that are
automatically triggered, e.g.: on push or schedule).
- Added a dataSource(DataSource) method to the builder
- Now, if no dialect is specified, the implementation will attempt to detect it from the effective DataSource (either set directly or obtained from the JdbcTemplate).
- Updated builder logic to default to the DataSource from the JdbcTemplate if dataSource() is not called, ensuring dialect detection works out-of-the-box.
- The builder now prefers a directly provided DataSource, but remains backwards compatible with JdbcTemplate-based configuration.
- Added tests
Fixes#3148
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- Fix the QdrantValueFactory to handle "java.util.List" type
- Update the integration test to use List type values
Resolves#3164
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Fixes GH-3151
Follow-up of commit ca843e85887aa1da6300c77550c379c103500897,`includeCompletion` is renamed to `logCompletion`.
Signed-off-by: Yanming Zhou <zhouyanming@gmail.com>
