About this session
RAG is a key concept for getting LLMs to understand your private sources of data. But the current RAG stack is quite naive, consisting of vector-based retrieval and a one-shot call to the LLM for synthesis. LLMs are developing intelligent reasoning capabilities; how can we apply these capabilities on top of your documents for much more advanced question-answering? This talk will cover some initial directions towards that.
Add to Calendar
Jan 31, 2024
Jan 31, 2024
America/Los_Angeles
Adding Agentic Layers to RAG
RAG is a key concept for getting LLMs to understand your private sources of data. But the current RAG stack is quite naive, consisting of vector-based retrieval and a one-shot call to the LLM for synthesis. LLMs are developing intelligent reasoning capabilities; how can we apply these capabilities on top of your documents for much more advanced question-answering? This talk will cover some initial directions towards that.
Main Stage | The Hibernia | 1 Jones St, San Francisco, CA 94102