Multimodal Retrieval Augmented Generation (RAG) using the Gemini API in Agent Platform Reviews

Gisele T. · Reviewed כמעט 2 שנים ago

Atharva G. · Reviewed כמעט 2 שנים ago

Gabriel Henrique P. · Reviewed כמעט 2 שנים ago

C.M. J. · Reviewed כמעט 2 שנים ago

Cedric C. · Reviewed כמעט 2 שנים ago

Navin S. · Reviewed כמעט 2 שנים ago

Navin S. · Reviewed כמעט 2 שנים ago

Vasundhara S. · Reviewed כמעט 2 שנים ago

Alberto A. · Reviewed כמעט 2 שנים ago

Good

Coin O. · Reviewed כמעט 2 שנים ago

Eduardo G. · Reviewed כמעט 2 שנים ago

Akkamgari S. · Reviewed כמעט 2 שנים ago

Chethan N. · Reviewed כמעט 2 שנים 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 כמעט 2 שנים ago

Pedro Henrique M. · Reviewed כמעט 2 שנים ago

nice

Icha Fadhlilah P. · Reviewed כמעט 2 שנים ago

Airi Fabianne O. · Reviewed כמעט 2 שנים ago

Sumam P. · Reviewed כמעט 2 שנים ago

Jeff G. · Reviewed כמעט 2 שנים ago

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

Sloppy C. · Reviewed כמעט 2 שנים ago

Charles D. · Reviewed כמעט 2 שנים ago

Lúcio L. · Reviewed כמעט 2 שנים ago

Kayê O. · Reviewed כמעט 2 שנים ago

ok

Ahmed A. · Reviewed כמעט 2 שנים ago

Alan Fernando de O. · Reviewed כמעט 2 שנים ago