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

Letícia d. · Reviewed about 1 year ago

Dontha A. · Reviewed about 1 year ago

Anderson Z. · Reviewed about 1 year ago

José Marcio de Castro B. · Reviewed about 1 year ago

Gustavo C. · Reviewed about 1 year ago

Gisele T. · Reviewed about 1 year ago

Atharva G. · Reviewed about 1 year ago

Gabriel Henrique P. · Reviewed about 1 year ago

C.M. J. · Reviewed about 1 year ago

Cedric C. · Reviewed about 1 year ago

Navin S. · Reviewed about 1 year ago

Navin S. · Reviewed about 1 year ago

Vasundhara S. · Reviewed about 1 year ago

Alberto A. · Reviewed about 1 year ago

Good

Coin O. · Reviewed about 1 year ago

Eduardo G. · Reviewed about 1 year ago

Akkamgari S. · Reviewed about 1 year ago

Chethan N. · Reviewed about 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 about 1 year ago

Pedro Henrique M. · Reviewed about 1 year ago

nice

Icha Fadhlilah P. · Reviewed about 1 year ago

Airi Fabianne O. · Reviewed about 1 year ago

Sumam P. · Reviewed about 1 year ago

Jeff G. · Reviewed about 1 year ago

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

Sloppy C. · Reviewed about 1 year ago