Starstruk Logo MarkStarstruk

v7.3.0

neuml/txtaiv7.3.0Jul 15, 2024by davidmezzetti

AI Summary

This release adds streaming LLM and RAG support, a new RAG front-end application template, and text extraction improvements.

Key Highlights

  • Add support for streaming LLM generation
  • Add RAG API endpoint
  • Add RAG deepdive notebook
  • Add RAG example application
  • Rename Extractor pipeline to RAG

New Features

  • Streaming LLM generation
  • RAG API endpoint
  • RAG example application
  • Streaming RAG support

Full Release Notes

**This release adds a new RAG front-end application template, streaming LLM and streaming RAG support along with significant text extraction improvements**

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

New Features
--------------------------
- Add support for streaming LLM generation (#680)
- Add RAG API endpoint (#735)
- Add RAG deepdive notebook (#737)
- Add RAG example application (#743)

Improvements
--------------------------
- Improve textractor pipeline (#748)
- Can't specify embedding model via API? (#632)
- Configuration documentation update request (#705)
- RAG alias for Extractor (#732)
- Rename Extractor pipeline to RAG (#736)
- Support max_seq_length parameter with model pooling (#746)

Bug Fixes
--------------------------
- Fix issue with max tokens for llama.cpp components (#733)
- Fix issue with loading non-transformer LLM models in Extractor/RAG pipeline (#734)
- Fix issue with setting quantize=False in HFTrainer pipeline (#747)