The saying /"/"a picture is worth a thousand words/"/" summarizes the enormous potential of visual data. But most Retrieval-Augmented Generation (RAG) applications rely only on text. This session applies RAG to multimodal use cases. It focuses on embedding and answering attributed questions to retrieve data. We'll start with a high-level architecture and quickly dive into a hands-on demo. Participants learn to create powerful LLM-based workflows and integrate them into existing applications.

Speakers: Shilpa Kancharla, Jeff Nelson

Sources:
Try Gemini in Vertex AI → https://goo.gle/3Vttolh

View more:
Watch all AI videos at Google I/O 2024 → https://goo.gle/io24-ai-yt
Watch all Cloud videos at Google I/O 2024 → https://goo.gle/io24-cloud-yt

Subscribe to Google Developers → https://goo.gle/developers

#GoogleIO

Event: Google I/O 2024

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.