OpenBMB/VisRAG

Parsing-free RAG supported by VLMs

49
/ 100
Emerging

Embeds document images directly using VLMs rather than parsing text first, preserving original formatting and information integrity across multi-image retrieval scenarios. EVisRAG 2.0 introduces evidence-guided reasoning with Reward-Scoped GRPO, enabling token-level optimization of visual perception and multi-step reasoning in VLMs. The framework provides plug-and-play components (VisRAG-Ret for retrieval, EVisRAG for generation) compatible with various VLM backbones and integrates with UltraRAG for end-to-end deployment.

932 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

932

Forks

71

Language

Python

License

Apache-2.0

Last pushed

Dec 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/OpenBMB/VisRAG"

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