The InfoQ Podcast
Sam Partee on Retrieval Augmented Generation (RAG)
Jan 29, 2024
Sam Partee, principal engineer at Redis, discusses Redis' vector database offering, different approaches to embeddings, enhancing language models with search components, and the use of hybrid search in Redis. They also explore the potential applications of retrieval augmented generation (RAG) technology and the challenges of running large language models on-prem.
32:15
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Redis is a suitable database for real-time platforms and chat conversations, but may not be practical for static use cases that don't require low latencies.
- Using hallucinated answers and searching for relevant context can improve search results in question and answer systems.
Deep dives
Redis as a Vector Database
The talk discusses how Redis introduced its vector database offering and the speaker's role in integrating it with other vector databases. The main focus is on sharing best practices and insights gained from working with customers and integration frameworks.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
