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

Atharva G. · Revisado há about 1 year

Gabriel Henrique P. · Revisado há about 1 year

C.M. J. · Revisado há about 1 year

Cedric C. · Revisado há about 1 year

Navin S. · Revisado há about 1 year

Navin S. · Revisado há about 1 year

Vasundhara S. · Revisado há about 1 year

Alberto A. · Revisado há about 1 year

Good

Coin O. · Revisado há about 1 year

Eduardo G. · Revisado há about 1 year

Akkamgari S. · Revisado há about 1 year

Chethan N. · Revisado há about 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 about 1 year

Pedro Henrique M. · Revisado há about 1 year

nice

Icha Fadhlilah P. · Revisado há about 1 year

Airi Fabianne O. · Revisado há about 1 year

Sumam P. · Revisado há about 1 year

Jeff G. · Revisado há about 1 year

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

Sloppy C. · Revisado há about 1 year

Charles D. · Revisado há about 1 year

Lúcio L. · Revisado há about 1 year

Kayê O. · Revisado há about 1 year

ok

Ahmed A. · Revisado há about 1 year

Alan Fernando de O. · Revisado há about 1 year

Daniel S. · Revisado há about 1 year