v3.2.0

neuml/txtaiv3.2.0Aug 17, 2021by davidmezzetti

AI Summary

Introduces the Trainer pipeline, modularizes the installation process, and enhances the Labels pipeline to support standard text classification models.

Key Highlights

Trainer pipeline added
Modularized txtai install
Labels pipeline standard text classification support

New Features

Enhance Labels pipeline to support standard text classification models
Trainer pipeline
Modularize txtai install
Evaluate if faiss-cpu can be used as default
Vector method for sentence-transformers

Full Release Notes

This release adds the following new features, improvements and bug fixes.

New Features
--------------------------
- Enhance Labels pipeline to support standard text classification models (#95)
- Add Trainer pipeline (#96)
- Modularize txtai install (#97)
- Evaluate if faiss-cpu can be used as default across all platforms (#98)
- Add vector method for sentence-transformers (#101)

Improvements
--------------------------
- Add book search example application (#91)
- Add wiki search example application (#92)
- Change tokenization to default to false for TransformerVectors (#99)
- Infer vector method using path (#100)
- Improve performance when running models through transformers (#102)
- Update notebooks and example applications (#103)

Bug Fixes
--------------------------
- Clear workflow batch during processing bug (#90)