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

Gisele T. · Reviewed ما يقرب من سنتين ago

Atharva G. · Reviewed ما يقرب من سنتين ago

Gabriel Henrique P. · Reviewed ما يقرب من سنتين ago

C.M. J. · Reviewed ما يقرب من سنتين ago

Cedric C. · Reviewed ما يقرب من سنتين ago

Navin S. · Reviewed ما يقرب من سنتين ago

Navin S. · Reviewed ما يقرب من سنتين ago

Vasundhara S. · Reviewed ما يقرب من سنتين ago

Alberto A. · Reviewed ما يقرب من سنتين ago

Good

Coin O. · Reviewed ما يقرب من سنتين ago

Eduardo G. · Reviewed ما يقرب من سنتين ago

Akkamgari S. · Reviewed ما يقرب من سنتين ago

Chethan N. · Reviewed ما يقرب من سنتين 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 ما يقرب من سنتين ago

Pedro Henrique M. · Reviewed ما يقرب من سنتين ago

nice

Icha Fadhlilah P. · Reviewed ما يقرب من سنتين ago

Airi Fabianne O. · Reviewed ما يقرب من سنتين ago

Sumam P. · Reviewed ما يقرب من سنتين ago

Jeff G. · Reviewed ما يقرب من سنتين ago

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

Sloppy C. · Reviewed ما يقرب من سنتين ago

Charles D. · Reviewed ما يقرب من سنتين ago

Lúcio L. · Reviewed ما يقرب من سنتين ago

Kayê O. · Reviewed ما يقرب من سنتين ago

ok

Ahmed A. · Reviewed ما يقرب من سنتين ago

Alan Fernando de O. · Reviewed ما يقرب من سنتين ago