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

José Marcio de Castro B. · Reviewed около 1 года ago

Gustavo C. · Reviewed около 1 года ago

Gisele T. · Reviewed около 1 года ago

Atharva G. · Reviewed около 1 года ago

Gabriel Henrique P. · Reviewed около 1 года ago

C.M. J. · Reviewed около 1 года ago

Cedric C. · Reviewed около 1 года ago

Navin S. · Reviewed около 1 года ago

Navin S. · Reviewed около 1 года ago

Vasundhara S. · Reviewed около 1 года ago

Alberto A. · Reviewed около 1 года ago

Good

Coin O. · Reviewed около 1 года ago

Eduardo G. · Reviewed около 1 года ago

Akkamgari S. · Reviewed около 1 года ago

Chethan N. · Reviewed около 1 года 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 около 1 года ago

Pedro Henrique M. · Reviewed около 1 года ago

nice

Icha Fadhlilah P. · Reviewed около 1 года ago

Airi Fabianne O. · Reviewed около 1 года ago

Sumam P. · Reviewed около 1 года ago

Jeff G. · Reviewed около 1 года ago

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

Sloppy C. · Reviewed около 1 года ago

Charles D. · Reviewed около 1 года ago

Lúcio L. · Reviewed около 1 года ago

Kayê O. · Reviewed около 1 года ago