Starstruk Logo MarkStarstruk

v6.2.0

neuml/txtaiv6.2.0Nov 8, 2023by davidmezzetti

AI Summary

A performance-focused release that adds scalar quantization for reduced vector storage and enables SQL bind parameters for multimedia queries.

Key Highlights

  • Supports 1 to 8-bit scalar quantization for vectors
  • Enables SQL bind parameters for searching binary content
  • Adds binary indexes to Faiss ANN and scalar data support to torch/numpy backends

New Features

  • Scalar quantization support
  • Bind variable support for SQL
  • cls pooling option
  • Prefix parameter for object storage
  • Disable directory flattening parameter
  • Binary indexes to Faiss ANN
  • Quantization notebook

Full Release Notes

**This release adds binary quantization, bind parameters for multimedia SQL queries and performance improvements**

āš” Scalar quantization. Supports 1 bit (binary) through 8 bit quantization. Can dramatically reduce vector storage requirements.

šŸš€ SQL bind parameters. Enables searching binary content with SQL statements, along with being a standard best practice.

See below for full details on the new features, improvements and bug fixes.

New Features
--------------------------
- Add scalar quantization support to vectors (#583)
- Feature request: Bind variable support when searching with SQL using Content=True mode (#564)
- Add cls pooling option (#565)
- Add prefix parameter for object storage (#568)
- Add parameter to RetrieveTask to disable directory flattening (#569)
- Add support for binary indexes to Faiss ANN (#585)
- Add support for scalar data to torch and numpy ANN backends (#587)
- Add quantization notebook (#588)
- Add API extensions notebook (#591)
- Add env variable to disable macOS MPS devices (#592)

Improvements
--------------------------
- Allow searching for images (#404)
- Update LLM pipeline to support template parameter (#566)
- Update recommended models (#573)
- Is it possible to add chat history to extractor workflow? (#575)
- Extractor pipeline improvements (#577)
- Update documentation (#582)
- Move vector normalization to vectors module (#584)
- Update benchmarks to read configuration (#586)
- Update torch version in Dockerfile (#589)
- Update Faiss ANN to support IVF strings without number of cells (#594)
- Update documentation to note SQL bind parameters (#596)

Bug Fixes
--------------------------
- Inconsistency in Embeddings behavior in Applications (#571)