From 20c05a7e7746bfba782923137385626768878942 Mon Sep 17 00:00:00 2001 From: chaohuang-ai Date: Sat, 7 Jun 2025 00:58:56 +0800 Subject: [PATCH] Update README.md --- README.md | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index 8a47f711..9789a203 100644 --- a/README.md +++ b/README.md @@ -1053,28 +1053,29 @@ When merging entities: ## Multimodal Document Processing (MinerU Integration) -LightRAG now supports multimodal document parsing and retrieval-augmented generation (RAG) via [MinerU](https://github.com/opendatalab/MinerU). You can extract structured content (text, images, tables, formulas, etc.) from PDF, images, and Office documents, and use them in your RAG pipeline. +LightRAG now supports comprehensive multi-modal document processing through [MinerU](https://github.com/opendatalab/MinerU) integration, enabling advanced parsing and retrieval-augmented generation (RAG) capabilities. This powerful feature allows you to handle multi-modal documents seamlessly, extracting structured content—including text, images, tables, and formulas—from various document formats for integration into your RAG pipeline. **Key Features:** -- Parse PDFs, images, DOC/DOCX/PPT/PPTX, and more -- Extract and index text, images, tables, formulas, and document structure -- Query and retrieve multimodal content (text, image, table, formula) in RAG -- Seamless integration with LightRAG core and RAGAnything - +- **Multimodal Document Handling**: Process complex documents containing mixed content types (text, images, tables, formulas) +- **Comprehensive Format Support**: Parse PDFs, images, DOC/DOCX/PPT/PPTX, and additional file types +- **Multi-Element Extraction**: Extract and index text, images, tables, formulas, and document structure +- **Multimodal Retrieval**: Query and retrieve diverse content types (text, images, tables, formulas) within RAG workflows +- **Seamless Integration**: Works smoothly with LightRAG core and RAG-Anything frameworks + **Quick Start:** 1. Install dependencies: ```bash pip install "magic-pdf[full]>=1.2.2" huggingface_hub ``` -2. Download MinerU model weights (see [MinerU Integration Guide](docs/mineru_integration_en.md)) -3. Use the new `MineruParser` or RAGAnything's `process_document_complete` to process files: +2. Download MinerU model weights (refer to [MinerU Integration Guide](docs/mineru_integration_en.md)) +3. Process multi-modal documents using the new MineruParser or RAG-Anything's process_document_complete: ```python from lightrag.mineru_parser import MineruParser content_list, md_content = MineruParser.parse_pdf('path/to/document.pdf', 'output_dir') # or for any file type: content_list, md_content = MineruParser.parse_document('path/to/file', 'auto', 'output_dir') ``` -4. Query multimodal content with LightRAG see [docs/mineru_integration_en.md](docs/mineru_integration_en.md). +4. Query multimodal content with LightRAG refer to [docs/mineru_integration_en.md](docs/mineru_integration_en.md). ## Token Usage Tracking