- Introducing a new OpenAiApi native client for OpenAI API and get rid of the theokanning library.
Amongst others the OpenAiApi allows:
- easy base-url configuration (e.g. TAS-AI)
- Flux response for streaming OpenAI results.
- Exposes the http headers containing important metadata
- Pure Spring ecosystem, making it easier for Graal VM
- Define a new AiStreamClient interface returning Flux<AiResponse>
- Refactor OpenAiClient and to use the new OpenAiApi and implement the AiStreamClient.
- Use spring-retry to improve the OpenAI EmbeddingClient stability on 503 error.
- Remove the OpenAI http header interceptor as the OpenAiApi returns ResponseEntity<T> that provides direct access to the headers.
- Refactor the metadata headers and usage extraction.
- Remove redundant and obsolete classes.
- Fix dependency issue with Pinecone, netty-codec-http2 and Spring Boot 3.2
- Add Vertex AI Autoconfigurations for chat and embedding clients.
- Factor out the embeding client dimensions() computation into an abstract parent AbstractEmbeddingClient.
- Add ITs
- Vertex dos.
- Rename Generation#text to content and info to properties.
- Make Generation extend the AbstractMessage and default to ASSISTANT message type.
- Add vevertex-ai project with native api client for generation and embedding.
- Add unit and IT tests for the vertex-ai native client.
- Add AiClient and EmbeddingClient implementation for the the Vertex AI along with ITs.
- Add NOT expression type to the portable Filter.Expression model.
- Add NOT to the Antlr grammar and implement the related parser listener method to generate Filter NOT expressions.
- Add NOT support to the filter programming DSL.
- Implement FilterHelper.negation for logically transform any boolean expression with NOT statements into
semantically equivalent one with NOT applied to the leaf expressions.
- Add tests for paresers, converters and vectorsores ITs.
- Move the filter IN/NIN expansion logic to the FilterHelper
- Factor out the filter IN/NIN boolean expression expansion logic out of Weaviate up to the FilterHelper.
- add in/nin expantion FilterHelper tests
* Define GenerationMetadata property in AiResponse.
* Add OpenAI implementations of AiMetadata, RateLimit and Usage interfaces.
* Add REST Assured JsonPath dependency to spring-ai-openai module.
* Add OkHttp dependency to spring-ai-openai module.
* Add OkHttp Interceptor to parse OpenAI rate limit metadata from HTTP headers.
* Add OkHttp MockWebServer dependency to spring-ai-openai module, test scope
* Add Jakarta Servlet API dependency to spring-ai-openai module, test scope
* Add Spring Web MVC dependency to spring-ai-open-ai module., test scope
* Define OpenAI API response headers in an Enum.
* Add OpenAI test configuration using mock objects.
* Add integration test to assert successful extraction of OpenAI API response metadata.
* Include Spring Boot auto-configuration for (conditional) OpenAI metadata collection.
* Edit documentation and include information on AI metadata collected by Spring AI.
* Provide AI metadata implementation for Microsoft Azure OpenAI Service.
* Capture optional PromptMetadata in AiResponse.
* Define metadata for an AI generation choice.
* Capture AI choice metadata in Generation.
* Integrate ChoiceMetadata into AiResponse returned by OpenAI.
Fixes#98
- Implement ChromaApi client, based on Chroma REST API.
- Implement ChromaVectorStore, including support for filter expression conversion.
- Common VectorStoreUtil class to share to/from Float/Double list/array convertion as well as Json/Map convertions.
- Add ITs including for Basic Auth and Token autheticatios.
- Add ChromaApi security support for BasicAuth and Token.
- Fix an issue with Text filter expression parser, related to double-quoted identifiers.
- Add Chroma README.md.
- Add Chroma boot autoconfiguration
Resolves# #86
- Collapses all VectorStore similiaritySearch methdos into one with SearchRequest builder.
- Fix all affected code and tests.
- Bump the project version to 0.7.1.
- Add tests
- Add autoconfigurations for milvus, pinecone and pgvecor stores.
- Improve and unify the VectorStore ITs.
- Make use of TrasformersEmbeddingClient for auto-configurations ITs.
- Extend the VectorStore with similaritySearch using metadata filters using internal DSL and external DSL using Antlr
- Metdata support for Pinecone, Milvus, and pgvector vector stores
- PGVectorStore uses explict ::jsonpath casting for the pgvector filter expression to avoid injections
- Add unit tests for the filter converters, parser and DSL.
- Add ITs for the 3 vector stores
Resolves: #75
- Provides a rudimentary text extractions for multitude of document formats,
including PDF, Word Doc/Docx PowerPoint ppt/pptx and many more.
- Generates a single Document for the extracted text.
- No pre or post processing and cleansing for the text.
- Move the ExtractedTextFormatter from pdf reader to the core reader to enable reusability. Improve the tika reader
- Add a set of PDF readers fro per-page (PagePdfDocumentReader) and per-paragraph (ParagraphPdfDocumentReader) readers.
- Use a PDFLayoutTextStripper fork and PDFLayoutTextStripperByArea extension to preserve the structure of the extracted document.
- PdfDocumentReaderConfig and PageExtractedTextFormatter in standalone classes.
- Craeate a new document-readers top level model and the pdf-reader under.
- Add ContentFormatter and DefaultContentFormatter that can filter the metadata
and format the Document metadata and text according to predefined templates.
- Add content formatter tests
- Allow the TextSplitter to copy the document content-formatter to the children.
When the splitter breaks the parent Document into multiple chunks (e.g.
into a list of children Documents) copy the source content formatter to
the chunks by default. Use the copyContentFormatter flag to enable/disable copping.
- Add TextSplitter IT tests
- Add MetadataExtractors as DocumentTransformers.
- Bump spring-ai project version to 0.7.0-SNAPSHOT
- Configurable metadata-mode for EmbeddingClients
- Make the metadata mode configurable for the EmbeddingClient implementations.
- Use the EMBED mode by default.
Resolves#44
Leverage #28 to allow the vector stores to resolve the embedding dimensions dynamically.
The explicitly set dimensions (if set) precedence over other configurations.
If the embedding dimensions are not explicitly set, the embeddingClient is used
to determine them dynamically. If the client fails the it falls back to 1536.
- Add dimension method to the EmbeddingClient interface.
Default dimension implementation uses the embed method to produce results and counts the result dimensions.
- Add EmbeddingUtil#dimensions utilities that look up the model dimensions from a pre-defined (static) file.
If the requested model is unknown, fallback to the default behaviour.
- Override the dimensions method in the OpenAiEmbeddingClient and AzureOpenAiEmbeddingClient to implement local caching.
- Add unit and IT tests.
Resolves#28
