X-PLUG/mPLUG-DocOwl

Multimodal LLMs for OCR-free document understanding

View on index · View in 3D Map

Related repos

• PDF processing toolkit for LLMs
• OCR for scanned PDFs with LLM-powered text correction
• open-source tool for parsing PDFs, Word, and PowerPoint for LLMs
• LLM-powered pipelines for complex document processing
• OCR for documents using PyTorch
• Converts PDFs into structured Markdown and Word files
• npm library for OCR using Llama 3.2 Vision, outputs markdown from images
• Converts files, performs OCR, and transcribes audio in a browser
• Parses PDFs into structured data