← ClaudeAtlas

chandra-ocrlisted

Chandra OCR 2 is an open-weights model from Datalab that converts page images and PDFs into Markdown, HTML or JSON layout chunks, keeping tables, math, forms with checkboxes and handwriting. Use when a user asks to OCR a scanned PDF, pull tables out of an image, read handwritten forms, or run a local or vLLM-served document OCR model with the chandra CLI or Python package.
trku052-png/social-media-youtube-skills · ★ 1 · Data & Documents · score 68
Install: claude install-skill trku052-png/social-media-youtube-skills
# Chandra OCR ## Overview [Chandra](https://github.com/datalab-to/chandra) (package `chandra-ocr` 0.2.0, model `datalab-to/chandra-ocr-2`) is a vision-language OCR model. For each page it produces HTML with layout labels (text, table, image, header, footer and so on), from which it derives Markdown, HTML and a list of layout chunks with bounding boxes. It covers 90+ languages, math, handwriting and checkbox forms. There are two inference methods: `vllm` (default; talks to a vLLM server, the base install is lightweight) and `hf` (loads the model locally with PyTorch and Transformers). Licensing: the code is Apache 2.0, but the model weights use a modified OpenRAIL-M licence (free for research, personal use and startups under 2 million USD funding or revenue; not for competing with Datalab's API). Check the README's "Commercial usage" section before using it in a company product. Datalab also sells a hosted API. ## Instructions ### Install ```bash python -m venv .venv && source .venv/bin/activate pip install chandra-ocr # CLI + vLLM client pip install "chandra-ocr[hf]" # adds torch, transformers, accelerate for local inference pip install "chandra-ocr[app]" # adds the Streamlit demo ``` ### Command line ```bash # HuggingFace backend, local GPU chandra scans/ ./ocr-output --method hf # vLLM backend: start the server first (launches a Docker container), then convert chandra_vllm chandra scans/lease-2026-014.pdf ./ocr-output --method vllm --page-range