Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
-
Updated
Jun 16, 2026 - Python
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
MinerU (PDF to Markdown converter) — portable, no-installation-required, one-click launch bundle.
Extract tables precisely from PDFs and convert them to clean HTML for RAG pipelines, running fast on CPU without external dependencies.
A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; the API is FastAPI + LangChain with a multi-agent pipeline, Sentry tunneling, & sensible production defaults (CORS, rate limits, session disk cleanup)
PDF table extraction for RAG — convert to clean HTML. Fast, local, no GPU.
A small web app that finds relevant documents and produces query-focused summaries using Gemini. Supports PDF upload with one-time multimodal preprocessing into per-page Markdown + metadata.
🔄 Optimize model loading in ComfyUI with flexible node connections and controlled sequences for better performance and memory management.
`pdf2struct` extracts structured JSON from PDF documents.
🤖 Process SCAIL-pose data with ComfyUI nodes, utilizing VitPose for accurate face and hand detection in an efficient, streamlined setup.
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具,将PDF转换成Markdown和JSON格式。
🖼️ Segment characters in images with ComfyUI using a Vision LLM agent, enhancing your projects with detailed and high-quality masks.
🎶 Generate multilingual AI music with lyrics in English, Chinese, Japanese, Korean, and Spanish using ComfyUI's HeartMuLa model.
Implements Unreal Engine 5 network protocol in Python to connect, authenticate, and replicate actors with UE5 Lyra Starter Game servers.
🎨 Build interactive Blazor applications with A2UI, a secure and portable protocol for rich UI rendered natively across platforms without code execution risks.
Study and verify the U24 Yang-Mills mass gap with open data, code, and tests for coupling spectra, Wilson loops, and bounds
Build a minimalist, stylish brand mall template using uni-app, Vue2, and Tuniao UI for quick e-commerce and fashion store front development.
Add a description, image, and links to the pdf-extractor-rag topic page so that developers can more easily learn about it.
To associate your repository with the pdf-extractor-rag topic, visit your repo's landing page and select "manage topics."