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

Gabriel Henrique P. · Reviewed حوالي سنة ago

C.M. J. · Reviewed حوالي سنة ago

Cedric C. · Reviewed حوالي سنة ago

Navin S. · Reviewed حوالي سنة ago

Navin S. · Reviewed حوالي سنة ago

Vasundhara S. · Reviewed حوالي سنة ago

Alberto A. · Reviewed حوالي سنة ago

Good

Coin O. · Reviewed حوالي سنة ago

Eduardo G. · Reviewed حوالي سنة ago

Akkamgari S. · Reviewed حوالي سنة ago

Chethan N. · Reviewed حوالي سنة 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 حوالي سنة ago

Pedro Henrique M. · Reviewed حوالي سنة ago

nice

Icha Fadhlilah P. · Reviewed حوالي سنة ago

Airi Fabianne O. · Reviewed حوالي سنة ago

Sumam P. · Reviewed حوالي سنة ago

Jeff G. · Reviewed حوالي سنة ago

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

Sloppy C. · Reviewed حوالي سنة ago

Charles D. · Reviewed حوالي سنة ago

Lúcio L. · Reviewed حوالي سنة ago

Kayê O. · Reviewed حوالي سنة ago

ok

Ahmed A. · Reviewed حوالي سنة ago

Alan Fernando de O. · Reviewed حوالي سنة ago

Daniel S. · Reviewed حوالي سنة ago

Reginaldo B. · Reviewed حوالي سنة ago