This commit adds support for new Meta Llama 3.1 and 3.2 instruct models
to the LlamaChatBedrockApi enum. It includes model IDs for:
Llama 3.1: 8B, 70B, 405B
Llama 3.2: 1B, 3B, 11B, 90B
These additions allow users to specify the latest Llama models when
using the Bedrock API. The commit also updates the class Javadoc with
a link to AWS documentation for model IDs and bumps the @since version
to 1.0.0.
- Switch to OpenAIAsyncClient for streaming operations
- Modify AzureOpenAiChatModel constructor to accept OpenAIClientBuilder
- Update getChatCompletionsStream to use non-blocking async client
- Refactor related classes and tests to support OpenAIClientBuilder
- Revise AzureOpenAiAutoConfiguration to provide OpenAIClientBuilder
- Add AzureOpenAiChatClientTest to verify streaming functionality
- Adjust existing tests for compatibility with OpenAIClientBuilder
Resolves https://github.com/spring-projects/spring-ai/issues/981
This change improves support for asynchronous streaming operations
in the AzureOpenAiChatModel, addressing potential issues in reactive environments.
Implement service connection support for MongoDB Atlas using both
TestContainers and Docker Compose. This change enables easier
integration testing and local development with MongoDB Atlas.
- Leverage TestContainers 1.20.2 which introduces MongoDBAtlasLocalContainer
- Add TestContainers support using MongoDBAtlasLocalContainer
- Implement Docker Compose configuration for MongoDB Atlas
- Create connection details factories for both TestContainers and Docker Compose
- Update dependency management for MongoDB Atlas integration
- Add integration tests for both TestContainers and Docker Compose setups
- Update documentation to include MongoDB Atlas support
Testcontainers 1.20.2 offers `MongoDBAtlasLocalContainer`. Previous
image used during tests was pulling images in every execution. The
new image is cached locally and can be executed offline.
Resolves https://github.com/spring-projects/spring-ai/issues/832
Introduces retry functionality to VertexAI embedding and
chat models, enhancing their resilience against transient failures.
It also corrects a typo in the VertexAiEmbeddingConnectionDetails
class name.
Key changes:
* Add RetryTemplate to VertexAiTextEmbeddingModel and VertexAiGeminiChatModel
* Introduce spring-ai-retry dependency
* Refactor code to support retry logic
* Update auto-configuration classes to incorporate retry functionality
* Fix typo in VertexAiEmbeddingConnectionDetails class name
remove extraneous commented out code
Add missing copyright headers, author etc.
This commit introduces a major overhaul of the advisor system in Spring AI,
improving modularity, type safety, and consistency
Core Changes:
- Replace RequestAdvisor and ResponseAdvisor with CallAroundAdvisor and StreamAroundAdvisor
- Introduce AdvisedRequest and AdvisedResponse classes for better encapsulation
- Deprecate RequestResponseAdvisor in favor of new advisor types
- Remove AdvisorObservableHelper class
Advisor Implementation Updates:
- Update AbstractChatMemoryAdvisor, MessageChatMemoryAdvisor, PromptChatMemoryAdvisor,
QuestionAnswerAdvisor, SafeGuardAroundAdvisor, SimpleLoggerAdvisor, and
VectorStoreChatMemoryAdvisor to implement new advisor interfaces
- Remove CacheAroundAdvisor (functionality likely moved elsewhere)
- Make CallAroundAdvisor and StreamAroundAdvisor extend Ordered interface
Client and Chain Management:
- Modify DefaultChatClient to use new advisor chain approach
- Refactor DefaultAroundAdvisorChain for better ordering and observation
- Implement builder pattern for advisor chain construction in DefaultChatClient
- Separate call and stream advisors in DefaultAroundAdvisorChain
Observation and Context Handling:
- Update observation conventions and context handling in advisors
- Add order field to AdvisorObservationContext
- Modify DefaultAdvisorObservationConvention to include order in high cardinality key values
Testing and Integration:
- Refactor ChatClientAdvisorTests and add new AdvisorsTests
- Update integration tests to reflect new advisor structure
- Enhance AdvisorsTests to verify correct advisor execution order
New Features:
- Generalize the Protect From Blocking functionality across all advisors
- Add (experimental) Re2 advisor to enhance reasoning capabilities of LLMs
- Add disabled Re2 test in OpenAiChatClientIT
Documentation:
- Add Advisors documentation
- Enhance advisors documentation with order explanation and Re2 example
Advisor Ordering:
- Introduce Advisor constants for precedence ordering
- Update AbstractChatMemoryAdvisor to use new precedence constant
- Improve advisor ordering and management in DefaultAroundAdvisorChain.Builder
- Remove redundant reordering logic from DefaultAroundAdvisorChain
These changes aim to provide a more flexible and powerful advisor system,
allowing for easier implementation of complex AI-driven interactions
Co-authored-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
- Add new option 'maxCompletionTokens' to spring.ai.openai.chat.options
- Mark 'maxTokens' as deprecated
- Update documentation to reflect these changes in OpenAI chat configuration
Related to #1411 and #1412
An upper bound for the number of tokens that can be generated for a completion,
including visible output tokens and reasoning tokens.
Replaces max_tokens field which is now deprecated.
This commit adds comprehensive documentation for the BatchingStrategy
in vector stores and enhances the TokenCountBatchingStrategy class.
Key changes:
- Explain batching necessity due to embedding model thresholds
- Describe BatchingStrategy interface and its purpose
- Detail TokenCountBatchingStrategy default implementation
- Provide guidance on using and customizing batching strategies
- Note pre-configured vector stores with default strategy
- Add new constructor for custom TokenCountEstimator in
TokenCountBatchingStrategy
- Implement null checks with Spring's Assert utility
- Update docs with new customization options and code examples
This is related to https://github.com/spring-projects/spring-ai/issues/889
This commit addresses a bug where certain fields were being made
indirectly mandatory due to Assert.notNull checks in the Builder's
with* methods. Specifically:
- Removed Assert.notNull checks from withResponseFormat, withSeed,
withLogprobs, withTopLogprobs, and withEnhancements methods.
These checks were causing exceptions in AzureOpenAiChatModel.getDefaultOptions
when not all fields were set, leading to failures in methods like
ChatClient.create, even when using the AzureOpenAiChatModel constructor
with OpenAIClient.
The removal of these checks aligns with the @JsonInclude(Include.NON_NULL)
annotation on AzureOpenAiChatOptions, which already ignores null options.
This change maintains the intended flexibility while preventing unintended
mandatory requirements.
This commit introduces support for Oracle Cloud Infrastructure (OCI)
GenAI embedding models in Spring AI. It includes:
* New OCIEmbeddingModel class for interacting with OCI GenAI API
* Auto-configuration for easy setup and integration
* Properties for configuring OCI connection and embedding options
* Documentation updates explaining usage and configuration
* Integration tests to verify functionality
Signed-off-by: Anders Swanson <anders.swanson@oracle.com>
Correct the OllamaEmbeddingModel initialization and options syntax in
the ollama-embeddings.adoc file. Remove unnecessary .toMap() call and
fix typo in withTruncate method name.
- Removed the assertion checking for a non-null 'name' in ToolResponseMessage
- This change affects multiple AI model implementations:
AzureOpenAiChatModel, MiniMaxChatModel, MistralAiChatModel,
MoonshotChatModel, OpenAiChatModel, and ZhiPuAiChatModel
Resolves#1410
Update mongodb.adoc to include links to both beginner and intermediate
content for Spring AI and MongoDB integration. Add a new section
"Tutorials and Code Examples" with:
- Link to the Getting Started guide for basic integration
- Link to a detailed RAG tutorial for more advanced usage
This change provides users with a clear path from initial setup to
more complex implementations using the MongoDB Atlas Vector Store.
Modify getHost method to return a properly formatted URL string. This
ensures that the Chroma client can correctly connect to the service
when using Docker Compose.
Fixes#1395
Replace parallelStream with stream to prevent thread-unsafe appends to
the shared StringBuilder. This fixes the issue of intermingled key-value
pairs in the generated Document content. Also, replace StringBuffer
with StringBuilder for better performance in single-threaded context.
The change ensures correct ordering of extracted JSON keys and their
values in the resulting Document, improving the reliability and
readability of the parsed output.
This change introduces a new field for tracking reasoning tokens in the
OpenAI API response. It extends the Usage record to include
CompletionTokenDetails, allowing for more granular token usage
reporting. The OpenAiUsage class is updated to expose this new data,
and corresponding unit tests are added to verify the behavior.
This enhancement provides more detailed insights into token usage,
particularly for advanced AI models that separate reasoning from other
generation processes.
Replace Objects::nonNull and instanceof checks with StringUtils::hasText
for more efficient and cleaner content filtering. This change simplifies
the stream operation in the getContent method, improving readability
and potentially performance.
Resolves https://github.com/spring-projects/spring-ai/issues/1199
- Implement configurable maxDocumentBatchSize to prevent insert timeouts
when adding large numbers of documents
- Update PgVectorStore to process document inserts in controlled batches
- Add maxDocumentBatchSize property to PgVectorStoreProperties
- Update PgVectorStoreAutoConfiguration to use the new batching property
- Add tests to verify batching behavior and performance
This change addresses the issue of PgVectorStore inserts timing out due to
large document volumes. By introducing configurable batching, users can now
control the insert process to avoid timeouts while maintaining performance
and reducing memory overhead for large-scale document additions.
Add missing options from Azure ChatCompletionsOptions to Spring AI
AzureOpenAiChatOptions. The following fields have been added:
- seed
- logprobs
- topLogprobs
- enhancements
This change ensures better alignment between the two option sets,
improving compatibility and feature parity.
Resolves https://github.com/spring-projects/spring-ai/issues/889
- Add handling for cases where ChatCompletion has a stop reason but empty generations.
Creates a Generation with empty content and metadata when this occurs.
- Update AnthropicChatModelObservationIT to expect "end_turn" finish reason.
- Update javadoc.
- When ChatClientRequestSpec#prompt(Prompt) is used, unseal the prompt instance.
Convert the last message instance (if user message) into spec#user and spec#media
and add the remaining messages (excluding the last) to the spec#messages.
Add the prompt#options to the spec#options.
- Improve DefaultChatClient to handle UserMessage media and content separately.
- Update AbstractToolCallSupport to use new hasToolCalls() method.
- Add hasToolCalls() method to AssistantMessage.
- Enhance ChatClientTest with additional test cases for media handling.
- Disable Groq and Nvidia integration tests due to rate limiting and credit requirements.
This commit introduces a new proxyToolCalls option for various chat
models in the Spring AI project. When enabled, it allows the client to
handle function calls externally instead of being processed internally
by Spring AI.
The change affects multiple chat model implementations, including:
AnthropicChatModel
AzureOpenAiChatModel
MiniMaxChatModel
MistralAiChatModel
MoonshotChatModel
OllamaChatModel
OpenAiChatModel
VertexAiGeminiChatModel
ZhiPuAiChatModel
The proxyToolCalls option is added to the respective chat options
classes and integrated into the AbstractToolCallSupport class for
consistent handling across different implementations.
The proxyToolCalls option can be set either programmatically via
the <ModelName>ChatOptions.builder().withProxyToolCalls() method
or the spring.ai.<model-name>.chat.options.proxy-tool-calls
application property.
Documentation for the new option is also updated in the relevant
Antora pages.
Added ITs for proxy tool calls
Remove ChatClientPromptRequestSpec and all ChatClient.prompt() overloads can how take advantage of the full fluent API. Docs updated
Resolves#1367
This commit introduces a new overloaded method prompt(String content)
to the ChatClient API. It provides a convenient way to create prompts
using only a string of user content, simplifying the process for basic
chat interactions.
Fixes gh-1286
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Adds configuration properties to allow custom header specification
- Implements mechanism to apply custom headers to Azure OpenAI requests
- Enhances flexibility for users to customize API interactions
These changes allow users to add necessary headers for authentication,
tracking, or other purposes when interacting with Azure OpenAI services.
Resolves https://github.com/spring-projects/spring-ai/issues/1284
* Adding test to verify the user-agent header in the Azure OpenAi chat client
* Adding the user-agent header to the search client in Azure vector store
This commit introduces support for the Watsonx.ai embedding model.
It includes:
- Watsonx embedding options class with tests
- Watsonx embedding model implementation
- Auto-configuration and properties for the embedding model
- Tests for the Watsonx embedding model
- Documentation for using the Watsonx embedding model
Also removed use of deprecated APIs in WatsonAIChatModel
Introduce a new property for the MongoDB vector store:
spring.ai.vectorstore.mongodb.metadata-fields-to-filter
This property accepts comma-separated values specifying which metadata
fields can be used for filtering when querying the vector store. It
ensures that metadata indexes are created if they don't already exist.
This addition enhances query performance and flexibility by allowing
users to define filterable fields in advance.
Co-authored-by: Eddú Meléndez <eddu.melendez@gmail.com>
* Improve docs for OpenAI, Mistral AI, and Ollama chat models and function calling
* Improve docs for the Chat Client
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Sometimes, the MiniMax stream mode function calls might get split,
resulting in an empty tool call ID. This indicates that the previous
call is not finished, which is an unusual API design.
The issue occurs when tool calls return in a format like:
[{"id":"1","function":{"name":"a"}},{"id":"","function":{"arguments":"[1]"}}]
These need to be merged into:
[{"id":"1","name":"a","arguments":"[1]"}]
This commit addresses the merging process to handle split function calls.
authored-by: mxsl-gr <mxsl-gr@users.noreply.github.com>
Apply batching when adding Documents to the following vector stores:
- Azure vector store
- Cassandra
- MongoDB Atlas
- OpenSearch
- Oracle
- Pinecone
This improves efficiency by processing multiple Documents at once instead of individually, reducing the overhead for each operation.
Related to #1261
