Document
* Introduced “score” attribute in Document API. It stores the similarity score.
* Consolidate “distance” metadata for Documents. It stores the distance measurement.
* Adopted prefix-less naming convention in Document.Builder and deprecated old methods.
* Deprecated the many overloaded Document constructors in favour of Document.Builder.
Vector Stores
* Every vector store implementation now configures a “score” attribute with the similarity score of the Document embedding. It also includes the “distance” metadata with the distance measurement.
* Fixed error in Elasticsearch where distance and similarity were mixed up.
* Added missing integration tests for SimpleVectorStore.
* The Azure Vector Store and HanaDB Vector Store do not include those measurements because the product documentation do not include information about how the similarity score is returned, and without access to the cloud products I could not verify that via debugging.
* Improved tests to actually assert the result of the similarity search based on the returned score.
Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
- Disable project-wide Checkstyle checks to unblock development
- Add documentation for enabling Checkstyle locally
- Fix remaining checkstyle violations in current codebase
Fixes#1669
This commit introduces a new Markdown document reader with several
key features and improvements:
* Add support for text with various formatting elements
* Implement handling for horizontal rules and hard line breaks
* Add functionality for inline and block code sections
* Incorporate blockquote handling
* Support ordered and unordered lists
* Introduce additional metadata capabilities
* Include JavaDocs
Update ETL documentation to reflect these new features and usage.
Fixes#105
