In order to support edge cases due to different naming formats, this PR introduced an explicit normalization logic to ensure the correct matching when checking for the availability of a certain model. Integration tests have been added to cover the different scenarios, including models from Ollama and from Hugging Face.
Also fix the container creation on the useTestcontainers flag (christian)
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Consolidate the Ollama auto-pull logic at startup time, supporting the auto-pull for the default models specified via configuration properties and for optional models specified for initialization.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Upgrade Antora Maven plugin to 1.0.0-alpha.4 (replace
Replace the io.spring.maven.antora:antora-maven-plugin:0.0.4)
- Update playbook configuration for Antora 3.2.0-alpha.6
- Refine documentation layout and styling
- Enhance observability documentation with formatted tables
- Adjust Spring AI logo size and update integration diagram
* Fix configuration inheritance issue when default value is not specified.
* Make it possible to enable the auto-pull feature only for specific model types (e.g. for chat models only).
* Add the possibility to list explicit models to auto-pull at startup time.
Update Ollama model defaults and add new embedding model
* Change default chat model to Mistral
* Change default embedding model to mxbai-embed-large
* Add MXBAI_EMBED_LARGE to OllamaModel enum
* Remove DEFAULT_MODEL constant from OllamaOptions
* Update relevant classes to use new defaults
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
Co-authored-by:Christian Tzolov <ctzolov@vmware.com>
* Introduce support for Ollama model auto-pull at startup time
* Enhance support for Ollama model auto-pull at run time
* Update documentation about integrating with Ollama and managing models
* Adopt Builder pattern in Ollama Model classes for better code readability
* Unify Ollama model auto-pull functionality in production and test code
* Improve integration tests for Ollama with Testcontainers
- Enhance OllamaModelPuller with configurable retry timeout
- Update test cases to use LLAMA3_1 instead of LLAMA3_2
- Improve Ollama documentation with clearer prerequisites and model pulling instructions
- Update Spring AI introduction page with new logo and diagram
- Remove unnecessary main method from OllamaModelPuller
- Remove unnecessary spring-web dependencies
- Update third-party library versions
- Refactor API classes to use consistent header handling
- Remove ApiUtils class and inline its functionality
- Adjust RestClient and WebClient builder usage in autoconfiguration
- Replace direct RestClient.Builder injections with ObjectProvider<RestClient.Builder>
and WebClient.Builder injections with ObjectProvider<WebClient.Builder>
- Update ChromaVectorStoreAutoConfiguration to use ObjectProvider
- Rename MongoDbAtlasLocalContainerConnectionDetailsFactoryTest to IT
- Switch spring-ai-chroma-store dependency from spring-web to spring-webflux
- Simplify ChromaApi constructor by using method reference for default headers
- Adjust import order
Resolves#1066Resolves#524
* Extend the OllamaApi to support listing, copying, deleting, and pulling models programmatically.
* Improve setup for integration testing with Ollama and Testcontainers.
Enables gh-526
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Update ChatResponse.Builder to copy all metadata fields when using from()
- Expand test case to verify correct metadata copying in QA advisor
Resolves#1537
- correct response key from "generation" to "completion" in example code
The example response in the documentation incorrectly uses "generation" as the response key. This commit updates it to "completion" to accurately reflect the API's actual response format.
- Add detailed explanation of function calling mechanism
- Examples use only the portable, ChatClient API
- Include quick start guide with code examples
- Describe multiple ways to register custom functions as beans
- Explain how to enable functions by bean name
- Add section on registering functions dynamically
- Introduce new Tool Context feature for passing additional data
- Improve overall structure and readability of the document
- Only the catalog is updated. No existing links are changed
- Move 'AI Concepts' under 'Overview'
- Reorganize API sections for better hierarchy
- Move 'Vector Databases' into its own top-level section
- Reposition 'Function Calling', 'Multimodality', 'Testing', and 'Structured Output' as top-level items
- Remove redundant nesting in some sections
- Comment out 'Generic Model' section
- Rename AI Model API into AI Models
- Get rid of the API suffix
- Improve Multimodality doc
- Update feature listing
This commit enhances the Bedrock Anthropic model's output:
- Add response ID, model name, and usage data to ChatResponseMetadata
- Introduce DefaultUsage class for token usage information
- Update BedrockAnthropic3ChatModel to include new metadata
- Add Jackson annotations for serialization/deserialization
- Implement unit tests for DefaultUsage
These changes provide structured, serializable metadata in the
ChatResponse, improving the model's output with additional
information.
- Extend the OllamaApi.EmbeddingsResponse with total_duration,
load_duration and prompt_eval_count fields
- Rename OllamaUsage to OllamaChatUsage for clarity
- Add OllamaEmbeddingUsage to track embedding-specific usage metrics
- Update OllamaEmbeddingModel to use OllamaEmbeddingUsage
- Extend EmbeddingsResponse with additional metadata fields
- Update tests to reflect new usage tracking for embeddings
Resolves#1536
- Add line breaks and clarify context boundaries in user text advice.
This improve the performance of a Llama3.x
- Update corresponding test to reflect new formatting
