Remove circular dependencies:
Move utility classes from various packages to dedicated support packages:
- Move ToolCallbacks from ai.tool to ai.support
- Move UsageUtils to UsageCalculator in ai.support
- Move tool.util to tool.support
- Create new ToolDefinitions utility class
Support packages for the classes in question is more idomatic in spring than util packages.
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- Add error handling to SpringBeanToolCallbackResolver to return null
instead of throwing exceptions when resolving non-existing tools.
This make is consitent with other tool resolver implementations
and centralize the error handling in the tool calling manager.
- Add test to verify that the ToolCallbackResolver correctly
returns null for non-existing tools.
Related to #2667
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
- 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>
Since the builders for HTTP clients are mutable and shared, they should
only be configured with globally applicable settings. The current use
leaks specific details into other usages and affects newly instantiated
clients. This PR applies the clone() method right before mutation
happens as it probably is the strategy that avoids multiple unnecessary
copies.
feat: improve RestClient and WebClient instantiation and configuration across AI modules
- Ensure RestClient.Builder and WebClient.Builder are properly cloned before setting base URLs and headers in Mistral, OpenAI, and Ollama API classes to prevent side effects.
- Add WebClientAutoConfiguration to auto-configuration classes for Anthropic and Mistral AI modules.
- Update Mistral AI auto-configuration to inject and use WebClient.Builder.
- Clean up test and annotation usage (remove unnecessary @Nullable, fix test builder usage in AnthropicApiIT).
- Improve consistency and reliability of HTTP client configuration across model integrations.
Signed-off-by: Dariusz Jędrzejczyk <dariusz.jedrzejczyk@broadcom.com>
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
Co-authored-by: Christian Tzolov <christian.tzolov@broadcom.com>
- Enhanced Neo4jChatMemoryRepository to correctly restore custom metadata for SystemMessage using SystemMessage.Builder.
- Refactored and clarified Neo4jChatMemoryRepository implementation code.
- Added comprehensive integration tests for Neo4jChatMemoryConfig and Neo4jChatMemoryRepository, including:
-- Index creation verification
-- Custom label support
-- Getter validation for all configuration properties
-- Tests for saving and retrieving SystemMessage metadata
-- Tests ensuring saveAll(conversationId, Collections.emptyList()) clears all messages and removes the conversation node
-- Tests for handling of messages with empty content and empty metadata
-- Improved overall test coverage for Neo4j persistence and configuration edge cases
- Fixed resource management bugs in test classes (ensured proper driver/session closure).
- Improved index creation logic in Neo4jChatMemoryConfig for reliability and logging.
- Updated documentation to include Neo4jChatMemoryRepository usage and configuration
Signed-off-by: enricorampazzo <enrico.rampazzo@live.com>
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
* Update remaining Advisors and related classes to use the new APIs.
* In AbstractChatMemoryAdvisor, the “doNextWithProtectFromBlockingBefore()” protected method has been changed from accepting AdvisedRequest to ChatClientRequest. It’s a breaking change since the alternative was not part of M8.
* MessageAggregator has a new method to aggregate messages from ChatClientRequest. The previous method aggregating messages from AdvisedRequest has been removed. Warning since it wasn’t marked as deprecated in M8.
* In SimpleLoggerAdvisor, the “requestToString” input argument needs to be updated to use ChatClientRequest. It’s a breaking change since the alternative was not part of M8. Same thing about the constructor.
* The “getTemplateRenderer” method has been removed from BaseAdvisorChain. Each Advisor is encouraged to accept a PromptTemplate to achieve self-contained prompt augmentation operations.
* Remove deprecations in ChatClient and Advisors, and update tests accordingly.
* When building a Prompt from the ChatClient input, the SystemMessage passed via systemText() is placed first in the message list. Before, it was put last, resulting in errors with several model providers.
Relates to gh-2655
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* Remove deprecated APIs for JdbcChatMemory.
* Improve documentation about chat memory vs. chat history.
* Fix mismatch between docs vs code for max messages in MessageWindowChatMemory.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Remove deprecated constructor method Media(MimeType mimeType, URL url) from Media
- Remove deprecated builder method data(URL url) from Media builder
- Update references to use the builder and the data(URI) methods
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Remove deprecated constructors from OllamaApi and AnthropicApi
- Modify AnthropicApi's public constructor to be private so that only the builder method can use it to construct
- Update OllamApiAutoConfiguration and AnthropicChatAutoconfiguration to use the builder methods to construct the respective
Apis
- Fix other constructor usages to builder methods
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
Renames the ambiguous overloaded `tools` methods in `ChatClient.PromptRequestSpec`
to `toolNames` and `toolCallbacks` respectively. This improves clarity
and prevents potential issues with method dispatching based on argument types.
Updates relevant code examples and adds documentation to upgrade notes.
Signed-off-by: Mark Pollack <mark.pollack@broadcom.com>
- set timestamp manually to prevent saving equal timestamps while batch insert
- return DESC order into get query (in `JdbcChatMemory`)
- Update similar changes for JdbcChatMemoryRepository
This PR solves some problems with message ordering:
JdbcChatMemory fetches rows in DESC order, and MessageChatMemoryAdvisor get and add all messages in that order - from last to first. So messages list needs to be reversed.
After batch insert without specifying timestamp manually all rows have the same timestamp (because database sets current_timestamp by default). Sooo after fetching rows from database the message order is unpredictable - they have same timestamp.
Signed-off-by: Linar Abzaltdinov <abzaltdinov@gmail.com>
fix: correct name typo from 'AsynClients' to 'AsyncClients'
fix: correct name typo from 'Autoconfiguration' to 'AutoConfiguration', 'optoins' to 'options'
fix: correct name typo from 'Differnt' to 'Different'
fix: correct name typo from 'Compatability' to 'Compatibility'
fix: correct name typo from 'Evalutaor' to 'Evaluator'
fix: correct name typo from 'Empyt' to 'Empty'
fix: correct name typo from 'Chroma Vecor Store' to 'Chroma Vector Store'
fix: correct name typo from 'Specificaiton' to 'Specification'
fix: correct name typo from 'applicaiton' to 'application'
fix: correct name typo from 'apropriate' to 'appropriate'
fix: correct name typo from 'asigned' to 'assigned'
fix: correct name typo from 'capabilitity' to 'capability'
fix: correct name typo from 'configuraiton' to 'configuration'
fix: correct name typo from 'conntection' to 'connection'
fix: correct name typo from 'curent' to 'current'
fix: correct name typo from 'customised' to 'customized'
Signed-off-by: Changho Kim <dukso4885@gmail.com>
* The new spring.ai.model.* properties introduced in M7 were missing Spring Boot configuration metadata.
* Furthermore, the breaking change was not documented as the previous properties have been completely removed. Documentation has been added in the upgrade notes for this change.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
* ChatClient observations now include the full prompt content instead of just the userText and systemText. Furthermore, they include consistent telemetry for the tools passed via the ChatClient and a first-class conversation ID when using memory advisors. Incomplete or unsafe attributes have been deprecated.
* Adopted the new robust Advisor APIs for BaseAdvisor and RetrievalAugmentationAdvisor.
* Improved the prompt augmentation facilities in ChatClientRequest and Prompt for performance and immutability.
* Fixed integration test racing condition.
* Updated the documentation for ChatClient and Observability accordingly.
* Documented changes in upgrade notes.
* Introduced `prompt.augmentUserMessage(String text)` to directly replace the user message content.
* Added `prompt.augmentUserMessage(Function<UserMessage, UserMessage> augmenter)` for more granular updates using the `userMessage.mutate()` pattern, allowing modification of text, media, and metadata.
Relates to gh-2655
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Remove the deprecated FunctionCallback related classes, references
- Replace them with the corresponding ToolCallback usage
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- FunctionCallbackResolver is deprecated and replaced by ToolCallingManager's ToolCallbackResolver
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@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>
- Update ZhipuAI Chat Model to use ToolCalling Manager and ToolExecutionEligibilityPredicate
- Update ZhipuAI ChatOptions to implement ToolCallingChatOptions
- Update Autoconfiguration for ZhipuAI model to use ToolCallingAutoconfiguration
- Update tests
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Update Minimax Chat Model to use ToolCalling Manager and ToolExecutionEligibilityPredicate
- Update Minimax ChatOptions to implement ToolCallingChatOptions
- Update Autoconfiguration for MinimaxChat model to use ToolCallingAutoconfiguration
- Update tests
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
- Move Mistral Moderation model into separate autoconfiguration
- Add/update MistralModelConfigurationTests
Signed-off-by: Ricken Bazolo <ricken.bazolo@gmail.com>
- Move AzureOpenAiClientBuilderAutoConfiguration to a simple AzureOpenAiClientBuilderConfiguration
- This will make sure that the Azure OpenAI client builder will only be imported when the underlying Azure OpenAI auto-configuration is enabled
- Update tests
Signed-off-by: Ilayaperumal Gopinathan <ilayaperumal.gopinathan@broadcom.com>
This change modifies the voice parameter in OpenAI Audio Speech API from using the
Voice enum directly to using the string value of the enum. This provides more
flexibility for handling voice options, especially for custom voices or when voice
names come from configuration.
- Change voice parameter type from Voice enum to String
- Add overloaded methods to accept both enum and string values
- Update tests and documentation to reflect these changes
Signed-off-by: jonghoon park <dev@jonghoonpark.com>
Implement MistralAI moderation capabilities to detect potentially harmful content.
This allows Spring AI applications to use Mistral's content moderation services
to identify and filter inappropriate content before processing
- Add MistralAiModerationApi for interacting with Mistral's moderation endpoints
- Create MistralAiModerationModel implementing the ModerationModel interface
- Add configuration properties and auto-configuration for the moderation model
- Extend Categories and CategoryScores with additional moderation categories
- Add integration tests to verify moderation functionality
Signed-off-by: Ricken Bazolo <ricken.bazolo@gmail.com>
Introduce a new ToolExecutionEligibilityChecker interface to provide a more flexible way to determine
when tool execution should be performed based on model responses. This abstraction replaces the
hardcoded logic previously scattered across the codebase.
- Adds a new ToolExecutionEligibilityChecker interface in spring-ai-core
- Integrates the checker into OpenAiChatModel with appropriate defaults
- Updates OpenAiChatAutoConfiguration to support the new interface
- Provides a default implementation that maintains backward compatibility
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
refactor: Replace ToolExecutionEligibilityChecker with ToolExecutionEligibilityPredicate
- Replacing ToolExecutionEligibilityChecker with ToolExecutionEligibilityPredicate
- Changing from Function<ChatResponse, Boolean> to BiPredicate<ChatOptions, ChatResponse>
- Adding a DefaultToolExecutionEligibilityPredicate implementation
- Updating AnthropicChatModel and OpenAiChatModel to use the new predicate
- Updating auto-configurations to inject the new predicate
- Adding comprehensive tests for the new predicate implementation
The new approach provides a cleaner and more consistent way to determine when tool execution should be performed based on both prompt options and chat responses.
Add Bedrock Converse support
add mistral support
Add ollama and vertex gemini
add ToolExecutionEligibilityPredicate docs
Signed-off-by: Christian Tzolov <christian.tzolov@broadcom.com>
