search

gpt-open / rag-gpt

RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.
Apache License 2.0
228 stars 25 forks source link

Extract images and tables from a PDF. #68

Open Le1234125 opened 1 month ago

Le1234125 commented 1 month ago

Does rag gpt support parsing images and tables in PDFs?

Le1234125 commented 1 month ago

Does rag gpt support parsing images and tables in PDFs?

blmdxiao commented 1 month ago

This is possible with strategies such as OCR, which was previously validated by local testing. However, the corresponding model needs to be deployed, and the requirements for the entire deployment resource will be relatively high, and it has not been published on github for the time being.

blmdxiao commented 1 month ago

If you have specific requirements for private deployment and would like to discuss further, we can communicate regarding your needs.

Email: blmdxiao@gmail.com WeChat: Alex_Bob_1988

blmdxiao commented 1 month ago

We will consider integrating llama-parse for parsing PDF and other files.

blmdxiao commented 3 weeks ago

Add the file parsing capability of llama-parse https://github.com/gpt-open/rag-gpt/pull/70