Hugging Face's logo

openbmb
/
VisRAG-Ret

Feature Extraction
Safetensors
English
minicpmv
VisRAG
custom_code
Model card Files Community
tcy6 commited on
Commit
335a244
·
verified ·
1 Parent(s): 108f391

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -12,6 +12,8 @@ tags:
12
  pipeline_tag: feature-extraction
13
  ---
14
  # VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
 
 
15
  [![arXiv](https://img.shields.io/badge/arXiv-2410.10594-ff0000.svg?style=for-the-badge)](https://arxiv.org/abs/2410.10594)
16
  [![Github](https://img.shields.io/badge/VisRAG-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white)](https://github.com/OpenBMB/VisRAG)
17
  **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.
 
12
  pipeline_tag: feature-extraction
13
  ---
14
  # VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
15
+ [![Hugging Face](https://img.shields.io/badge/VisRAG_Ret-fcd022?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/openbmb/VisRAG-Ret)
16
+ [![Hugging Face](https://img.shields.io/badge/VisRAG_Collection-fcd022?style=for-the-badge&logo=huggingface&logoColor=000)](https://huggingface.co/collections/openbmb/visrag-6717bbfb471bb018a49f1c69)
17
  [![arXiv](https://img.shields.io/badge/arXiv-2410.10594-ff0000.svg?style=for-the-badge)](https://arxiv.org/abs/2410.10594)
18
  [![Github](https://img.shields.io/badge/VisRAG-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white)](https://github.com/OpenBMB/VisRAG)
19
  **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.