v8.2.0

neuml/txtaiv8.2.0Jan 9, 2025by davidmezzetti

AI Summary

This release simplifies LLM chat messages, adds attribute filtering to Graph RAG, and enables multi-cpu/gpu vector encoding.

Key Highlights

  • Encoding using multiple-GPUs
  • Graph RAG - Add extra attributes
  • Add defaultrole to LLM pipeline
  • Enhanced Docs: LLM Embedding Examples

New Features

  • Multi-GPU vector encoding
  • Graph RAG attribute filtering
  • LLM pipeline default role support

Full Release Notes

**This release simplifies LLM chat messages, adds attribute filtering to Graph RAG and enables multi-cpu/gpu vector encoding**

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

New Features
--------------------------
- Add defaultrole to LLM pipeline (#841)
- Feature Request: Graph RAG - Add extra attributes (#684)
- Support graph=True in embeddings config (#848)
- Support pulling attribute data in graph.scan (#849)
- Encoding using multiple-GPUs (#541)
- Add vectors argument to Model2Vec vectors (#846)
- Enhanced Docs: LLM Embedding Examples (#843, #844) Thank you @igorlima!

Improvements
--------------------------
- Pin build script to pillow==10.4.0 (#800)
- Ensure generated datetimes are in UTC (#840)
- Update RAG notebooks to add clarifying notes on LLM inference (#847)