[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
docs: fix broken and unstable links in documentation
Tolga Karatas786b6d4ee71d
diff --git a/README.md b/README.mdindex d0fc6bb..33ddea8 100755--- a/README.md+++ b/README.md@@ -373,8 +373,8 @@ LEANN implements a robust, multi-layer fallback pipeline for processing document4. [**Docling OCR**](https://github.com/docling-project/docling): The ultimate fallback from IBM Research for scanned PDFs and complex multimodal layouts.Dedicated extractors are also used for:-- **Office**: Structural extraction for `.docx` ([python-docx](https://github.com/python-openxml/python-docx)), `.pptx` ([python-pptx](https://github.com/python-openxml/python-pptx)), and `.xlsx` ([openpyxl](https://github.com/ericgazoni/openpyxl)).-- **Mindmaps**: Hierarchical node extraction for [FreeMind](http://freemind.sourceforge.net/)/[Freeplane](https://www.freeplane.org/) (`.mm`).+- **Office**: Structural extraction for `.docx` ([python-docx](https://github.com/python-openxml/python-docx)), `.pptx` ([python-pptx](https://github.com/scanny/python-pptx)), and `.xlsx` ([openpyxl](https://github.com/ericgazoni/openpyxl)).+- **Mindmaps**: Hierarchical node extraction for [FreeMind](http://freemind.sourceforge.net/)/[Freeplane](https://github.com/freeplane/freeplane) (`.mm`).<p align="center"><img src="videos/paper_clear.gif" alt="LEANN Document Search Demo" width="600">diff --git a/docs/features.md b/docs/features.mdindex a7182bb..82d9038 100644--- a/docs/features.md+++ b/docs/features.md@@ -12,8 +12,8 @@- **📑 Multi-Format Support**: Native handling of `.pdf`, `.txt`, `.md`, `.docx`, `.pptx`, `.xlsx`, and `.mm` (Mindmaps).- **🚀 Advanced PDF Pipeline**: Intelligent fallback chain featuring [PyMuPDF](https://github.com/pymupdf/PyMuPDF), [pypdf](https://github.com/py-pdf/pypdf), [pdfplumber](https://github.com/jsvine/pdfplumber), and [**Docling OCR**](https://github.com/docling-project/docling) (IBM Research) for high-fidelity document parsing.-- **💼 Office Document Extractors**: Structural awareness for Word ([python-docx](https://github.com/python-openxml/python-docx)), Excel ([openpyxl](https://github.com/ericgazoni/openpyxl)), and PowerPoint ([python-pptx](https://github.com/python-openxml/python-pptx)) preserving tables, slides, and sheets.-- **🧠 Mindmap Parsing**: Hierarchical node extraction for [FreeMind](http://freemind.sourceforge.net/) and [Freeplane](https://www.freeplane.org/) (`.mm`) preserving semantic relationships in zettelkasten-like structures.+- **💼 Office Document Extractors**: Structural awareness for Word ([python-docx](https://github.com/python-openxml/python-docx)), Excel ([openpyxl](https://github.com/ericgazoni/openpyxl)), and PowerPoint ([python-pptx](https://github.com/scanny/python-pptx)) preserving tables, slides, and sheets.+- **🧠 Mindmap Parsing**: Hierarchical node extraction for [FreeMind](http://freemind.sourceforge.net/) and [Freeplane](https://github.com/freeplane/freeplane) (`.mm`) preserving semantic relationships in zettelkasten-like structures.- **📱 Integrated Source Connectors**: Dedicated CLI commands for Apple Mail, Calendar, iMessage, WeChat, and more.## ⚡ Performance & Scalability