Release (v0.1.7) - 2025-12-04
Release v0.1.7:
- Added ground truth generation and T5 finetuning pipeline
- Updated the UI to have Select + Dig Deeper framework
- Refactored code to simplify extraction
- Added Playwright Fetcher
- Added support for schema.org metadata pull from schema compliant dataset pages
- Enhanced Retrieval of Sections with rule-based id_pattern matching