v8.3.0

neuml/txtaiv8.3.0Feb 11, 2025by davidmezzetti

AI Summary

Adds support for GLiNER entity extraction, Kokoro TTS, and Static Vectors. It also introduces a semantic chunking pipeline and various improvements to existing features.

Key Highlights

Add support for GLiNER models
Add semantic chunking pipeline
Add Kokoro TTS support to TextToSpeech pipeline
Add staticvectors inference

New Features

GLiNER model support
Semantic chunking pipeline
Kokoro TTS support
Static vectors inference

Full Release Notes

**This release adds support for GLiNER, Chonkie, Kokoro TTS and Static Vectors**

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

New Features
--------------------------
- Add support for GLiNER models (#862) Thank you @urchade
- Add semantic chunking pipeline (#812) Thank you @bhavnicksm
- Add Kokoro TTS support to TextToSpeech pipeline (#854) Thank you @hexgrad
- Add staticvectors inference (#859)
- Add example notebook for Entity Extraction with GLiNER (#873)
- Add example notebook for RAG Chunking (#874)
- Add notebook that analyzes NeuML LinkedIn posts (#851)

Improvements
--------------------------
- Add new methods for audio signal processing (#855)
- Remove fasttext dependency (#857)
- Remove WordVectors.build method (#858)
- Detect graph queries and route to graph index (#865)
- Replace python-louvain library with networkx equivalent (#867)
- Word vector model improvements (#868)
- Improve parsing of table text in HTML to Markdown pipeline (#872)

Bug Fixes
--------------------------
- Update build script to workaround breaking change with latest version of Transformers and Python 3.9 (#852)
- Incorrect Endpoint Description in Swagger UI (FastAPI) (#860)
- Handle empty token list with word vectorization (#861)