关于“使用 Vertex AI 的 Gemini API，執行多模態檢索增強生成 (RAG) 功能”的评价

Atharva G. · 评论about 1 year之前

Gabriel Henrique P. · 评论about 1 year之前

C.M. J. · 评论about 1 year之前

Cedric C. · 评论about 1 year之前

Navin S. · 评论about 1 year之前

Navin S. · 评论about 1 year之前

Vasundhara S. · 评论about 1 year之前

Alberto A. · 评论about 1 year之前

Good

Coin O. · 评论about 1 year之前

Eduardo G. · 评论about 1 year之前

Akkamgari S. · 评论about 1 year之前

Chethan N. · 评论about 1 year之前

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. · 评论about 1 year之前

Pedro Henrique M. · 评论about 1 year之前

nice

Icha Fadhlilah P. · 评论about 1 year之前

Airi Fabianne O. · 评论about 1 year之前

Sumam P. · 评论about 1 year之前

Jeff G. · 评论about 1 year之前

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

Sloppy C. · 评论about 1 year之前

Charles D. · 评论about 1 year之前

Lúcio L. · 评论about 1 year之前

Kayê O. · 评论about 1 year之前

ok

Ahmed A. · 评论about 1 year之前

Alan Fernando de O. · 评论about 1 year之前

Daniel S. · 评论about 1 year之前