Multimodal Retrieval Augmented Generation (RAG) using the Gemini API in Vertex AI Reviews

Gustavo C. · Reviewed בערך שנה אחת ago

Gisele T. · Reviewed בערך שנה אחת ago

Atharva G. · Reviewed בערך שנה אחת ago

Gabriel Henrique P. · Reviewed בערך שנה אחת ago

C.M. J. · Reviewed בערך שנה אחת ago

Cedric C. · Reviewed בערך שנה אחת ago

Navin S. · Reviewed בערך שנה אחת ago

Navin S. · Reviewed בערך שנה אחת ago

Vasundhara S. · Reviewed בערך שנה אחת ago

Alberto A. · Reviewed בערך שנה אחת ago

Good

Coin O. · Reviewed בערך שנה אחת ago

Eduardo G. · Reviewed בערך שנה אחת ago

Akkamgari S. · Reviewed בערך שנה אחת ago

Chethan N. · Reviewed בערך שנה אחת 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 בערך שנה אחת ago

Pedro Henrique M. · Reviewed בערך שנה אחת ago

nice

Icha Fadhlilah P. · Reviewed בערך שנה אחת ago

Airi Fabianne O. · Reviewed בערך שנה אחת ago

Sumam P. · Reviewed בערך שנה אחת ago

Jeff G. · Reviewed בערך שנה אחת ago

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

Sloppy C. · Reviewed בערך שנה אחת ago

Charles D. · Reviewed בערך שנה אחת ago

Lúcio L. · Reviewed בערך שנה אחת ago

Kayê O. · Reviewed בערך שנה אחת ago

ok

Ahmed A. · Reviewed בערך שנה אחת ago