UltraRAG
UltraRAG copied to clipboard
UltraRAG v2: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
对于demo中的VisRAG,正常的理解是不是应该是这样的: 普通的RAG输出只能是纯文本,但是VisRAG,在输出中除了包含纯文本外,还可以包含相关的image? 而不是说,只是把retrieve出来的几个页面的截图也提供出来? 例如,提问: 相机的快门按钮在哪里? 回答应该包含一段介绍,另外加上整个相机所有按钮标注的图片(如果pdf里有的话),而不是把整页的PDF截图输出。
我的笔记本缺少GPU,如何使用dockers在cpu中运行体验下该项目?
Is your feature request related to a problem? Please describe. Manually searching through audio/video files (e.g., finding specific speech or scenes) is very time-consuming. Describe the solution you'd like Support...
Summary This PR improves the OpenAI backend in UltraRAG by: 1. Making the handling of unsupported parameters more robust for newer OpenAI models (e.g. reasoning models like `o3-mini`) by dropping...
很早之前就星这个项目了,最近试了一下,感觉很不错。我目前尝试到的是对一个pipeline进行测试,测试完成之后,这个pipeline如何上线成一个可调用的API呢?
**Describe the bug** CUDA is out of memory while using the default Retriever Server with multimodal embedding model colpali-v1.3-merged to embed 6492 images. I suppose it's because the retriever attempts...
**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...