Starstruk Logo MarkStarstruk

v2.0.0

neuml/txtaiv2.0.0Jan 13, 2021by davidmezzetti

AI Summary

Major release bringing a zero-shot similarity pipeline, batch support for all modules, and integration with Hugging Face Datasets.

Key Highlights

  • Zero-shot similarity pipeline
  • Batch support for all modules
  • Integration with Hugging Face Datasets

Breaking Changes

  • Make API definitions consistent

New Features

  • Zero-shot similarity pipeline
  • Batch support for all modules
  • Add example notebook integrating Hugging Face Datasets
  • Add example notebook that adds semantic search to existing system
  • Upgrade to Transformers 4.x

Full Release Notes

txtai 2.0.0 is a major release with a significant number of new features. This release brings a new zero-shot similarity pipeline, a more streamlined and consistent API, batch support for all modules and integration with Hugging Face Datasets. 

In addition to Python, txtai has API support for [JavaScript](https://github.com/neuml/txtai.js), [Java](https://github.com/neuml/txtai.java), [Rust](https://github.com/neuml/txtai.rs) and [Go](https://github.com/neuml/txtai.go).

New Features
--------------------------
- [BREAKING CHANGES] Make API definitions consistent (#54)
- Zero-shot similarity pipeline (#21, #49)
- Add batch support for all modules (#18, #53)
- Add example notebook integrating Hugging Face Datasets (#26)
- Add example notebook that adds semantic search to existing system (#57)

Improvements
--------------------------
- Add API tests, increase test coverage (#42)
- Refactor pipeline component (#44)
- Upgrade to Transformers 4.x (#45)
- Review, organize and update example notebooks (#52)
- Allow setting ANN index parameters (#55)
- Modify API add method to stream data (#56)

Bug Fixes
--------------------------
- Fix language support issues (#39, #43)