search

infiniflow / ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
https://ragflow.io
Apache License 2.0
24.16k stars 2.36k forks source link

[Question]: Document analysis with pictures and texts #3343

Open lvyoudashuju opened 2 weeks ago

lvyoudashuju commented 2 weeks ago

Describe your problem

How to parse a file with both pictures and text, for example, a file contains a text and a picture, and the picture is a pure picture

KevinHuSh commented 2 weeks ago

Is it a PDF file? The pure picture will attach to figure caption if it has.

lvyoudashuju commented 2 weeks ago

Yes. I just uploaded a pdf file with pictures and text, but it doesn’t seem right when parsed. 企业微信截图_17313787235623