Geração aumentada por recuperação (RAG, na sigla em inglês) multimodal usando a API Gemini na Agent Platform avaliações

Vasundhara S. · Revisado há over 1 year

Alberto A. · Revisado há over 1 year

Good

Coin O. · Revisado há over 1 year

Eduardo G. · Revisado há over 1 year

Akkamgari S. · Revisado há over 1 year

Chethan N. · Revisado há over 1 year

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. · Revisado há over 1 year

Pedro Henrique M. · Revisado há over 1 year

nice

Icha Fadhlilah P. · Revisado há over 1 year

Airi Fabianne O. · Revisado há over 1 year

Sumam P. · Revisado há over 1 year

Jeff G. · Revisado há over 1 year

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

Sloppy C. · Revisado há over 1 year

Charles D. · Revisado há over 1 year

Lúcio L. · Revisado há over 1 year

Kayê O. · Revisado há over 1 year

ok

Ahmed A. · Revisado há over 1 year

Alan Fernando de O. · Revisado há over 1 year

Daniel S. · Revisado há over 1 year

Reginaldo B. · Revisado há over 1 year

Matheus P. · Revisado há over 1 year

Nicolas A. · Revisado há over 1 year

SYCOA2 Madhura Abnave G. · Revisado há over 1 year

Julio M. · Revisado há over 1 year

Rodrigo L. · Revisado há over 1 year