Sign in to confirm youā€™re not a bot
This helps protect our community. Learn more
RAGChat: Multimedia data ingestion
In this series, we dive deep into our most popular, fully-featured, and open-source RAG solution: https://aka.ms/ragchat Do your documents contain images or charts? Our RAG solution has two different approaches to handling multimedia documents, and we'll dive into both approaches in this session. The first approach is purely during ingestion time, where it replaces media in the documents with LLM-generated descriptions. The second approach stores images of the media alongside vector embeddings of the images, and sends both text and images to a multimodal LLM for question answering. Learn about both approaches in this session so that you can decide what to use for your app. This session is a part of a series! To learn more, click here: https://aka.ms/RAGDeepDive šŸ“Œ Get more RAG resources! https://aka.ms/thesource/RAG #MicrosoftReactor #learnconnectbuild #RAGDeepDive [eventID:24573]

Follow along using the transcript.

Microsoft Reactor

106K subscribers
Live chat replay is not available for this video.