- Fix the bug in BM25HTMLPruner. - Fix the bug for duplicate child tags. - Optimize the computing efficiency for super long HTML documents.
Thank LinXin04 for reporting some bugs.
0.0.3
- Add support for local embed inference. - **BM25HTMLPruner** for bm25 embedding
0.0.1
We provide a simple tookit to apply HtmlRAG in your own RAG systems. Please refer to the [user guide](https://github.com/plageon/HtmlRAG/blob/main/toolkit/README.md) for more details.