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

Alan Fernando de O. · Reviewed about 1 year ago

Daniel S. · Reviewed about 1 year ago

Reginaldo B. · Reviewed about 1 year ago

Matheus P. · Reviewed about 1 year ago

Nicolas A. · Reviewed about 1 year ago

SYCOA2 Madhura Abnave G. · Reviewed about 1 year ago

Julio M. · Reviewed about 1 year ago

Rodrigo L. · Reviewed about 1 year ago

Giulianne C. · Reviewed about 1 year ago

Edmar S. · Reviewed about 1 year ago

Andrea Y. · Reviewed about 1 year ago

HARSHIT S. · Reviewed about 1 year ago

Luciano N. · Reviewed about 1 year ago

easy

CRISTIANE T. · Reviewed about 1 year ago

Clecio B. · Reviewed about 1 year ago

Juliana O. · Reviewed about 1 year ago

thiago s. · Reviewed about 1 year ago

Gleyce Kesia M. · Reviewed about 1 year ago

Carla O. · Reviewed about 1 year ago

Alex S. · Reviewed about 1 year ago

Cleisson P. · Reviewed about 1 year ago

Sonali R. · Reviewed about 1 year ago

Fabio Luciano N. · Reviewed about 1 year 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. Also, the time given to understand this lab is much less, and should be increased.

Nij R. · Reviewed about 1 year ago

Mohamed A. · Reviewed about 1 year ago