Any solutions on how to use multimodal rag?

General
1

i have a pdf that has alot of images, tables and charts. i see alot of solutions that solves this. but any workaround that we can use agno’s existing chunking, embedding functionalities while also utilize multimodal functionalities ?

2

Hey @reekko1, Thank you for reaching out and using Agno.
Please refer our docs: Multimodal Agents - Agno

Let me know incase you have any doubts