indra vs pdf-craft
OCR and scanned-PDF tools compared
indra and pdf-craft both use OCR to make PDF content easier to reuse. indra focuses on CPU-based extraction with layout details, while pdf-craft emphasizes turning scanned documents into Markdown or EPUB, with optional translation.
indra: Fast CPU OCR with Datalab’s Indra Model
Indra OCR uses Datalab’s compact model with ONNX Runtime to turn PDFs and images into markdown, text, or structured JSON on CPU. It adds line boxes, layout labels, and reading order for fast document parsing without a GPU.
pdf-craft: Convert Scanned PDFs with DeepSeek OCR
PDF Craft is a Python library and online service for turning scanned books, research papers, and technical documents into editable Markdown or reader-friendly EPUB. Built around DeepSeek OCR, it also supports translation and translated PDF output.
| indra | pdf-craft | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | MIT |
| Stars | 421 | 6.4k |
| Forks | 33 | 466 |
| Last analyzed | Oct 16, 2026 | Oct 18, 2026 |
Key differences
- indra uses a compact ONNX Runtime model designed for CPU use; pdf-craft supports remote OCR and can run OCR locally with suitable NVIDIA GPU and CUDA-enabled PyTorch.
- indra outputs Markdown, plain text, or structured JSON with line boxes, layout labels, and reading order; pdf-craft creates Markdown with image assets or EPUBs with metadata and a table of contents.
- pdf-craft includes translation workflows for EPUBs and translated PDF output; indra focuses on OCR and document extraction.
- indra supports Linux and macOS and combines OCR with digital PDF text extraction; pdf-craft offers synchronous and asynchronous Python APIs and saves extraction results in `.pcex` files.
- indra is licensed under Apache-2.0, with model weights under a modified OpenRAIL-M license; pdf-craft is licensed under MIT.
- indra's supplied project-health data describes a repository only a few days old, with contributions from one person; pdf-craft has 6.3k stars and 460 forks.
Choose indra if you…
- process clean printed PDFs on CPU without GPU infrastructure.
- need structured extraction with line coordinates, layout labels, and reading order.
- use a local viewer to inspect OCR overlays and extracted output.
Choose pdf-craft if you…
- turn scanned books or documents into editable Markdown or EPUB.
- need translation or bilingual EPUB and translated PDF workflows.
- integrate OCR and conversion through synchronous or asynchronous Python APIs.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.