X-PLUG/mPLUG-DocOwl

Document understanding via LLMs without OCR

View on index · View in 3D Map

Related repos

• open-source tool for parsing PDFs, Word, and PowerPoint for LLMs
• PDF processing toolkit for LLMs
• OCR for scanned PDFs with LLM-powered text correction
• LLM-powered pipelines for complex document processing
• extracts text from documents and images using OCR
• Converts plain text into ffmpeg commands using LLMs
• visually chunks and parses complex documents for LLMs, with markdown and table support
• OCR pipeline with local LLM field extraction
• Converts PDF documents to Markdown and Word formats
• Organizes documents with machine learning and OCR