Update README.md
Browse files
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 |
[](https://arxiv.org/abs/2410.10594)
|
| 16 |
[](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 |
+
[](https://huggingface.co/openbmb/VisRAG-Ret)
|
| 16 |
+
[](https://huggingface.co/collections/openbmb/visrag-6717bbfb471bb018a49f1c69)
|
| 17 |
[](https://arxiv.org/abs/2410.10594)
|
| 18 |
[](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.
|