Gemini Multimodal RAG Applications with LangChain

In this session, we'll present a novel approach for building visual question-answering assistants using LangChain and the Gemini multimodal language model.
Watch how easy it is to build applications and bring your questions for live Q&A!
Join, learn, and get your questions answered with the Google Cloud Community: goo.gle/ai-community
Share your feedback and suggestions for future sessions: goo.gle/gcc-event-feedback

[@arindambanerjee7079]

Can you put the link of your notebook for a multi modal RAG?

[@sarathtech91]

Fantastic session. Also, can we get Aditya Rane to do more sessions? And can you please share the notebook shown in the presentation? Thanks.

[@out_and_about08]

Can you share the notebook? thanks

[@dipteshbosedb]

Excellent Demo. Loved this session.

[@ramzihamdi1963]

can you share the notebook? plz thanks

[@alannoeasmis4942]

Nice tutorial! From Argentina

[@Clementdijoux]

great video, can you put the notebook !

[@jatinkashyap1491]

Are you running that notebook on Colab Enterprise?

[@PRIYASINGH-kq9fc]

Can you please provide the notebook link for Multi Modal RAG?

[@vishvaschauhan4963]

I wanna pass image as question and want to ask details about matching image. What embedding it will refer to ? -- they tricked us with using text embedding model ... Not impressed

[@ananyashukla4080]

Can i use cloud storage in place of docstore ?

[@cullenharris1837]

Revolutionary

[@cullenharris1837]

How can we access the notebook?

[@KarnageKumar]

@GoogleCloudEvents Collab notebook link please