Document Rag setup using lang chain ?

[bhanu1106]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

no code available

Description

I need to build a Multimodal RAG setup which takes pdf documents as input . As the pdf documents may contain images too, I was thinking to build Multimodal RAG instead of usual RAG . Is this the correct approach ? If so can I build this using lang chain ? Could anyone provide any documentation links for the document multimodal rag setup using lang chain ?

System Info

N/A