OpenAI's API returns additional token usage metrics that provide deeper
insight into API consumption. This adds support for:
- acceptedPredictionTokens: Tokens from accepted model predictions
- audioTokens: Tokens used for audio processing
- rejectedPredictionTokens: Tokens from rejected model predictions
These fields help track resource utilization and costs more accurately
by breaking down token usage by type. Added @JsonIgnoreProperties to
maintain compatibility with future OpenAI API additions.
Fixes warning logging in RetryUtils.SHORT_RETRY_TEMPLATE to reduce noise
in test output.
The DEFAULT_RETRY_TEMPLATE uses exponential backoff starting at 2s with max 3min
delay between retries, making tests run unnecessarily long. This change
introduces SHORT_RETRY_TEMPLATE with fixed 100ms backoff to speed up test
execution while preserving the same retry behavior and error handling.
- Add a new test case for testing function call with advisor in BedrockConverseChatClientIT
- Add a new test case for testing tool proxy function call in OpenAiChatClientProxyFunctionCallsIT
- Remove unused model property from BedrockConverseProxyChatProperties
Add support for proper Kotlin functions handling
by adapting kotlin.jvm.functions.Function1 to
java.util.function.Function and kotlin.jvm.functions.Function2 to
java.util.function.BiFunction.
It also removes the dependency on Spring Cloud Function and
net.jodah:typetools which are replaced by leveraging
Spring Framework ResolvableType capabilities.
Added withInputType Kotlin extension
- Add a Kotlin extension function for
FunctionCallbackWrapper.Builder.withInputType allowing
to specify withInputType<T>() instead of
withInputType(T::class.java).
- Add Kotlin documentation
- Disable project-wide Checkstyle checks to unblock development
- Add documentation for enabling Checkstyle locally
- Fix remaining checkstyle violations in current codebase
Fixes#1669
Add @JsonIgnore annotation to the jsonSchema field in Function classes across
multiple AI provider APIs (MiniMax, MistralAI, OpenAI, ZhiPuAI) to exclude
it from JSON serialization.
- The doSimilaritySearch method did not pass the databaseName parameter in milvus 2.3.4 and before, resulting in the use of the default database; The current milvus upgrade to 2.3.5 supports passing the databaseName parameter
- Update doSimilaritySearch to set the database name from the Milvus configuration
Introduces support for Amazon Bedrock Converse API through a new BedrockProxyChatModel
implementation. This enables integration with Bedrock's conversation models with features
including:
- Support for sync/async chat completions
- Stream response handling
- Tool/function calling capabilities
- System message support
- Image input support
- Observation and metrics integration
- Configurable model parameters and AWS credentials
Adds core support classes:
- BedrockUsage: Implements Usage interface for token tracking
- ConverseApiUtils: Utility class for handling Bedrock API responses including:
- Tool use event aggregation and processing
- Chat response transformation from stream outputs
- Model options conversion
- Support for metadata aggregation
- URLValidator: Utility for URL validation and normalization with support for:
- Basic and strict URL validation
- URL normalization
- Multimodal input handling
- Enhanced FunctionCallingOptionsBuilder with merge capabilities for both ChatOptions
and FunctionCallingOptions
- Added BEDROCK_CONVERSE to AiProvider enum for metrics tracking
- Extended AWS credentials support with session token capability
- Added configurable session token property to BedrockAwsConnectionProperties
Adds new auto-configuration support:
- BedrockConverseProxyChatAutoConfiguration for automatic setup of the Bedrock Converse chat model
- BedrockConverseProxyChatProperties for configuration including:
- Model selection (defaults to Claude 3 Sonnet)
- Timeout settings (defaults to 5 minutes)
- Temperature and token control
- Top-K and Top-P sampling parameters
- Integration with existing BedrockAwsConnectionConfiguration for AWS credentials
Updates to testing infrastructure:
- Adds comprehensive test suite for Bedrock Converse properties and auto-configuration
- Integration tests for chat completion and streaming scenarios
- Property validation tests for configuration options
- Temporarily disabled other Bedrock tests due to AWS quota limitations
- Added ObjectMapper configuration for proper JSON handling
Added new spring-ai-bedrock-converse-spring-boot-starter module
Updates module configuration in parent POM and BOM to include new bedrock-converse
modules and starters. Adds necessary auto-configuration imports for seamless integration
with Spring Boot applications.
Unrelated changes:
- Disabled several Bedrock model tests (Jurassic2, Llama, Titan) due to AWS quota limitations
- Disabled PaLM2 tests due to API decommissioning by Google
Resolves#809, #802
Add docs and fix configs
- Move timeout configuration from chat properties to connection properties
- Add comprehensive documentation for Bedrock Converse API usage and configuration
- Update tests to reflect configuration changes
Co-authored-by: maxjiang153 <maxjiang153@users.noreply.github.com>
Standardize AWS credential handling in integration tests
- Improve how we manage AWS credentials across our integration test
suite and ensures consistent test configuration. We're replacing individual
environment variable checks with @RequiresAwsCredentials
annotation and standardizing the use of BedrockTestUtils for context creation
in tests
We also align all AWS regions to US_EAST_1 for consistency and add missing
dependency versioning for Oracle Free.
These changes make our AWS tests more easier to maintain.
Key changes:
- Replace @EnabledIfEnvironmentVariable with @RequiresAwsCredentials
- Standardize context creation via BedrockTestUtils
- Set AWS region to US_EAST_1
- Add Oracle Free dependency version in pom.xml
This change uses `session.executeWrite` and `session.executeRead` to interact with the database.
Those methods use build-in retries for several Neo4j specific error states.
Doing will improve the overall user experience in this case as the no other external retry mechanism should be used.
Doing so is fine, as the Neo4j vector store is not subject to Springs general transaction management.
* Add new QueryAugmentor API, a component for augmenting a user query with contextual data.
* Implement ContextualQueryAugmentor that combines the content of each document and add it to the original user prompt, with support for the scenario where the context is empty.
* Extend RetrievalAugmentationAdvisor to use the new augmentation building block.
* Introduce utility to assist in validating arguments for prompt-related operations.
Relates to gh-#1603
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
The system text advise prompt is only joined with the value of the system text if it's non-null and non-empty.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Introduced null-safety for all ChatClient APIs and verified via extensive auto-tests.
* Made the final message list computed by ChatClient consistent and predictable across the different options for providing messages (prompt(), messages(), user(), prompt()) and verified via extensive auto-tests.
* Added even more auto-tests to cover as many scenarios and edge cases as possible.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Following removal of Spring Boot's ConstructorBinding, convert record types
to regular POJOs to maintain JSON serialization. Update API classes:
- Convert FunctionTool and Function records to standard Java classes with
getters/setters
- Update test assertions to use getter methods instead of record accessors
- Fix failing tests in MiniMax, OpenAi and ZhiPu API implementations
This keeps core API models independent of Spring Boot while ensuring proper
serialization through standard Java beans.
- MistralAIApi FunctionTool ConstructorBinding removal changes
* Establish new package for Modular RAG components.
* Add new Query API, representing a query in the context of a RAG flow.
* Define Retrieval package for the RAG building blocks handling the data retrieval operations.
* Relocate DocumentRetriever to Retrieval package and implement VectorStoreDocumentRetriever.
* Introduce RetrievalAugmentationAdvisor as the successor of QuestionAnswerAdvisor. It uses the Retrieval building blocks described in the previous point.
* Make Advisor APIs null-safe and update tests accordingly.
Relates to gh-#1603
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
When using a non-default database, MilvusVectorStore's doDelete method wasn't
passing the specified databaseName in DeleteParam, causing searches to fall back
to the default database where collections couldn't be found. Added explicit
databaseName parameter to fix this issue.
- Add databaseName to DeleteParam builder
- Upgrade milvus-sdk from 2.3.4 to 2.3.5
chatclient.adoc
- Replaced javaCopySimpleLoggerAdvisor with SimpleLoggerAdvisor
- Fixed typo in the multiline String for ChatClient example
etl-pipeline.adoc
- Fixed indent in the ParagraphPdfDocumentReader example
imageclient.adoc
- Fixed indent of override annotation in the ImageGeneration example
testing.adoc
- Added a semicolon to the Evaluator interface
Signed-off-by: jitokim <pigberger70@gmail.com>
- Define the version for Azure Cosmos DB
- Add dependencies for the azure-cosmos-db-store module and boot starter
- Include the artifacts in spring-ai-bom
Signed-off-by: jitokim <pigberger70@gmail.com>
* GH-513 fix: Support custom field names for Milvus VectorStore collection
- Add configuration properties to override the default field names for doc_id, content, metadata and embedding
- Add support to allow auto-id when enabled
- Add tests
Resolves#513
* Fix package modifier
