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

C.M. J. · Reviewed almost 2 years ago

Cedric C. · Reviewed almost 2 years ago

Navin S. · Reviewed almost 2 years ago

Navin S. · Reviewed almost 2 years ago

Vasundhara S. · Reviewed almost 2 years ago

Alberto A. · Reviewed almost 2 years ago

Good

Coin O. · Reviewed almost 2 years ago

Eduardo G. · Reviewed almost 2 years ago

Akkamgari S. · Reviewed almost 2 years ago

Chethan N. · Reviewed almost 2 years 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 almost 2 years ago

Pedro Henrique M. · Reviewed almost 2 years ago

nice

Icha Fadhlilah P. · Reviewed almost 2 years ago

Airi Fabianne O. · Reviewed almost 2 years ago

Sumam P. · Reviewed almost 2 years ago

Jeff G. · Reviewed almost 2 years ago

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

Sloppy C. · Reviewed almost 2 years ago

Charles D. · Reviewed almost 2 years ago

Lúcio L. · Reviewed almost 2 years ago

Kayê O. · Reviewed almost 2 years ago

ok

Ahmed A. · Reviewed almost 2 years ago

Alan Fernando de O. · Reviewed almost 2 years ago

Daniel S. · Reviewed almost 2 years ago

Reginaldo B. · Reviewed almost 2 years ago

Matheus P. · Reviewed almost 2 years ago