What you can do with Indra

4 use cases

• Turn a folder of scanned PDFs into markdown files

  Batch-convert scanned PDFs to one markdown file each, using all CPU cores.

  • Indra
  • Research
  • Intermediate
  View prompt

  In the repo datalab-to/indra, install indra-ocr with pip and run `indra-ocr <folder>/*.pdf --out results/`. Expected output: one .md file per input PDF in results/. Verify that each .md file is non-empty and that the CLI exit code is 0, or list the files that failed.

  Share Save

• Get OCR lines and boxes as JSON for a data pipeline

  Extract each line with its box, confidence, and layout label as JSON.

  • Indra
  • Research
  • Intermediate
  View prompt

  Using the repo datalab-to/indra, install indra-ocr and run `indra-ocr <input-file> --format json` on <input-file>. Expected output: JSON with lines (box, text, confidence) and blocks (label, bbox, text) per page. Verify that the block labels in the output match the labels listed in the README, such as Text, Table, and Form.

  Share Save

• Check OCR results on each page in a local viewer

  Drop in a scan and see lines, blocks, and reading order drawn over the page.

  • Indra
  • Research
  • Beginner
  View prompt

  In the repo datalab-to/indra, install indra-ocr and start `indra-ocr-viewer --port 8765`. Expected output: a local web page at http://localhost:8765 that shows OCR lines and layout blocks for a dropped file. Verify that the page loads and that line confidences are visible.

  Share Save

• Read mixed-language and handwritten scans in one run

  OCR scans in many scripts and handwriting, with a CJK-only or RTL-only fallback when needed.

  • Indra
  • Research
  • Advanced
  View prompt

  Using the repo datalab-to/indra, install indra-ocr and run `indra-ocr <file>.pdf --mode ocr --timings` on <file>.pdf. Expected output: markdown with the text in each script and per-page timings on stderr. Verify the text for each script against the source page, since handwriting accuracy is limited.

  Share Save

How to use Indra

1. Check you have what it needs: Python 3.10 or newer (the README says it is tested on Linux and macOS); pip to install the indra-ocr package; An internet connection for the first run, which downloads about 76 MB of models from Hugging Face.
2. Open datalab-to/indra on GitHub and read the README and license.
3. Run pip install indra-ocr.
4. Move the scanned PDFs into one folder and open a terminal in that folder.
5. Run indra-ocr *.pdf --out results/ to write one .md file per input.
6. Open a few files in results/ and compare them with the original pages.

These steps come from our top use case, Turn a folder of scanned PDFs into markdown files, which also has a copy-paste agent prompt.

Indra alternatives · Best AI repos for Research

About this repo

• Who it is forPeople with scanned PDFs or photographed pages who need searchable text on a laptop or CPU-only server, and developers who want OCR output with boxes and layout labels in their own pipelines.
• Why it is hot
• LanguagePython
• Sourcegithub.com/datalab-to/indra · Back to Hot repos

Requirements

• Python 3.10 or newer (the README says it is tested on Linux and macOS)
• pip to install the indra-ocr package
• An internet connection for the first run, which downloads about 76 MB of models from Hugging Face
• The PDFs or images to read

Related repos

• #5 this week Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier Speaker Mem R1 SpeakerMem-R1 is a Python research repo with a speaker-centered memory package, benchmark runners, writer-training recipes, and evaluation outputs for multi-party dialogue.
• Trended earlier DSH Council A DSH Council plugin that asks several AI models to answer a question independently, review each other's answers anonymously, and produce one inspectable final recommendation inside DeepSeek Harness.