Multimodal Retrieval Augmented Generation (RAG) using the Gemini API in Agent Platform Reviews

Vasundhara S. · Reviewed over 1 year ago

Alberto A. · Reviewed over 1 year ago

Good

Coin O. · Reviewed over 1 year ago

Eduardo G. · Reviewed over 1 year ago

Akkamgari S. · Reviewed over 1 year ago

Chethan N. · Reviewed over 1 year ago

While passing image data to gemini 1.5 pro model as stated in the notebook, it says "Unfortunately, I cannot process or "see" images and am unable to provide the analysis requested. I can only process the textual information provided. ". And proceeds to provide answers based on image descriptions only, or suggesting how to get answers. This somewhat contradicts the multimodal capability lab is trying to show. It looks like there is some issue with notebook code, which is converting images to string (just an object repr in python) before sending it to Gemini. So it just sends text instead of actual images.

Nij R. · Reviewed over 1 year ago

Pedro Henrique M. · Reviewed over 1 year ago

nice

Icha Fadhlilah P. · Reviewed over 1 year ago

Airi Fabianne O. · Reviewed over 1 year ago

Sumam P. · Reviewed over 1 year ago

Jeff G. · Reviewed over 1 year ago

at first there was problem with 'import fitz'. after kernel restart the problem went away

Sloppy C. · Reviewed over 1 year ago

Charles D. · Reviewed over 1 year ago

Lúcio L. · Reviewed over 1 year ago

Kayê O. · Reviewed over 1 year ago

ok

Ahmed A. · Reviewed over 1 year ago

Alan Fernando de O. · Reviewed over 1 year ago

Daniel S. · Reviewed over 1 year ago

Reginaldo B. · Reviewed over 1 year ago

Matheus P. · Reviewed over 1 year ago

Nicolas A. · Reviewed over 1 year ago

SYCOA2 Madhura Abnave G. · Reviewed over 1 year ago

Julio M. · Reviewed over 1 year ago

Rodrigo L. · Reviewed over 1 year ago