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

Gisele T. · Reviewed почти 2 лет ago

Atharva G. · Reviewed почти 2 лет ago

Gabriel Henrique P. · Reviewed почти 2 лет ago

C.M. J. · Reviewed почти 2 лет ago

Cedric C. · Reviewed почти 2 лет ago

Navin S. · Reviewed почти 2 лет ago

Navin S. · Reviewed почти 2 лет ago

Vasundhara S. · Reviewed почти 2 лет ago

Alberto A. · Reviewed почти 2 лет ago

Good

Coin O. · Reviewed почти 2 лет ago

Eduardo G. · Reviewed почти 2 лет ago

Akkamgari S. · Reviewed почти 2 лет ago

Chethan N. · Reviewed почти 2 лет 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 почти 2 лет ago

Pedro Henrique M. · Reviewed почти 2 лет ago

nice

Icha Fadhlilah P. · Reviewed почти 2 лет ago

Airi Fabianne O. · Reviewed почти 2 лет ago

Sumam P. · Reviewed почти 2 лет ago

Jeff G. · Reviewed почти 2 лет ago

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

Sloppy C. · Reviewed почти 2 лет ago

Charles D. · Reviewed почти 2 лет ago

Lúcio L. · Reviewed почти 2 лет ago

Kayê O. · Reviewed почти 2 лет ago

ok

Ahmed A. · Reviewed почти 2 лет ago

Alan Fernando de O. · Reviewed почти 2 лет ago