Imagine you are in a situation where you have documents containing complex graphs or diagrams packed with information and you want to extract this data to answer questions or queries. Go through the lab created by Bhushan Garware to learn how you can get started with such a request: https://goo.gle/3UZ4IRj
In this lab, you'll perform the following:
Data loading using LangChain document_loaders
Generate text summaries using Google's gemini-pro model
Generate image summaries using Google's gemini-pro-vision model
Create multi-vector retrieval using Google's textembedding-gecko model
Develop Multi-modal RAG chain for question answering
If you want to join the full, instructor-led, free, virtual, hands-on session as part of the "Building Generative AI applications using Gemini and Gemma" season of Code Vipassana, register here: https://goo.gle/4dImY8U