Is RAG Really Dead?
Watch the recording for this session: Is RAG (Really) Dead? | RAG with Long Context LLMs | LangChain x Timescale
With the advent of Large Language Models with context windows of 1 million tokens (and soon more?!), many have declared the utility of retrieval augmented generation (RAG) dead and no longer necessary. But is this actually true? Or simply short-sighted?
Join Timescale and special guest presenter Lance Martin (@RLanceMartin), engineer at LangChain, for a 60 minute live deep dive into the present and future of the popular technique for building AI applications: Retrieval Augmented Generation (RAG).
Topic: Is RAG Really Dead?
Date: Thursday, 21 March 2024
Time: 12:00 ET | 9:00 PT | 17:00 CET
Presenters: Lance Martin (LangChain) and Avthar Sewrathan (Timescale).
In this live session, you’ll learn:
The limitations of long context LLMs from "needle in a haystack" evaluations.
Potential future trends in RAG in a world with long context LLMs.
Techniques for indexing with long context in mind, like RAPTOR and multi-representation.
Going beyond simple RAG by adding cycles (C-RAG) and self-reflection (Self-RAG).
Resources and tutorials to further your learning journey.
Whether you're exploring GenAI for work, already built production AI systems, or simply curious about the latest in techniques for building AI applications, this one-hour event (with Q+A) promises to enrich your understanding and spark ideas to take your projects to the next level.
Can't make it live? No sweat, register and we'll send you the recording via email afterward.
ABOUT TIMESCALE: Timescale is a mature cloud PostgreSQL platform engineered for demanding workloads like time-series, vector, events and analytics data. Timescale offers hosted PostgreSQL databases with pgvector and Timescale Vector to help you build AI applications at scale with PostgreSQL as your vector database. Learn more.