OCR
Turn documents, scans and PDFs into LLM-ready text — OCR and document-parsing models and pipelines.
datalab-to 11.5k · 20 days agoDatalab's SOTA open OCR model: images/PDFs to structured HTML/Markdown/JSON with layout, tables, forms, checkboxes, handwriting and math, in 90+ languages. Local HF or vLLM inference.
lumina-ai-inc 4k · 3 months agoDocument intelligence API in Rust: layout analysis, OCR with bounding boxes, and semantic chunking that turn PDFs, PPTs and Word docs into RAG-ready structured chunks.
opendatalab 74.8k · yesterdayHeavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.
allenai 19.1k · 3 months agoOpen toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.
baidu 14.3k · 13 days agoBaidu's open OCR VLM that parses entire multi-page documents in one shot — 'unlimited' long-horizon parsing pushing DeepSeek-OCR further. MIT weights on HF; serve via transformers, vLLM or SGLang.
xberg-io 8.7k · yesterdayRust-core document-intelligence engine with 15 language bindings: turns 96 formats — PDF, Office, images, audio, code — into clean text, tables and RAG-ready chunks. Library, CLI, REST or MCP.