Starstruk Logo MarkStarstruk

v9.11.0

microsoft/TinyTroupev9.11.0Jul 1, 2026by davidmezzetti

AI Summary

This release introduces a new turbovec ANN backend and LiteParse text extraction capabilities. It also includes performance optimizations, migration from ggml-py to ggml-python, and fixes for specific tokenizer and FastAPI compatibility issues.

Key Highlights

  • Added turbovec ANN backend
  • Added text extraction with LiteParse
  • Migrated from ggml-py to ggml-python
  • Fixed FastAPI compatibility issues
  • Fixed tokenizer lowercase parameter

New Features

  • turbovec ANN backend
  • LiteParse text extraction

Full Release Notes

**This release adds support for the turbovec ANN backend and LiteParse text extraction**

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

New Features
--------------------------
- Add turbovec an ANN backend (#1109)
- Add text extraction with LiteParse (#1118)

Improvements
--------------------------
- Migrate from ggml-py to ggml-python (#1105)
- Revert noisy logging workaround when fixed upstream (#1106)
- Add reindex parameter for API (#1111)
- Use gliner fork to relax transformers version caps (#1112)
- Remove find from the default list of bash tools (#1113)
- Support multiple Dense layers for Late Interaction Pooling (#1117)
- Limit tabular pipeline to local CSV files (#1119)
- Update commonprefix to commonpath (#1120)

Bug Fixes
--------------------------
- fix(tokenizer): respect lowercase=False in ngramtokenize (#1114, thank you @JSap0914)
- FastAPI 0.137+ modified how routers work (#1115)