openbmb
/

VisRAG-Ret

Feature Extraction

Model card Files Files and versions Community

tcy6 commited on 1 day ago

Commit

10ed72e

•

1 Parent(s): 5ab8164

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -12,6 +12,8 @@ tags:
 pipeline_tag: feature-extraction
 ---
 # VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
 **VisRAG** is a novel vision-language model (VLM)-based RAG pipeline. In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM.Compared to traditional text-based RAG, **VisRAG** maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process.
 <p align="center"><img width=800 src="https://github.com/openbmb/VisRAG/blob/master/assets/main_figure.png?raw=true"/></p>

 pipeline_tag: feature-extraction
 ---
 # VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
+[![arXiv](https://img.shields.io/badge/arXiv-2410.10594-ff0000.svg?style=for-the-badg)](https://arxiv.org/abs/2410.10594)
+[![Github](https://img.shields.io/badge/VisRAG-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white)](https://github.com/OpenBMB/VisRAG)
 **VisRAG** is a novel vision-language model (VLM)-based RAG pipeline. In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM.Compared to traditional text-based RAG, **VisRAG** maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process.
 <p align="center"><img width=800 src="https://github.com/openbmb/VisRAG/blob/master/assets/main_figure.png?raw=true"/></p>