MMDocRAG/MMDocIR

The code used to train and run inference with MMDocIR

16
/ 100
Experimental

This project helps researchers and developers evaluate and train systems designed to retrieve specific information from long, complex documents containing text, images, tables, and other layouts. It provides a standardized way to measure how well these systems can find relevant pages or even individual elements like figures or paragraphs within a document. The target users are those developing or benchmarking multi-modal document retrieval solutions.

No commits in the last 6 months.

Use this if you need a comprehensive benchmark to evaluate how accurately your system can pinpoint specific information (text, images, tables) within large, visually rich documents.

Not ideal if you're looking for an off-the-shelf document search solution for end-users, rather than a benchmark for developing retrieval systems.

document-retrieval information-extraction research-evaluation multi-modal-search academic-benchmarking
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

JavaScript

License

Last pushed

May 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/MMDocRAG/MMDocIR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.