Weaviate Podcast cover image

Charles Packer on MemGPT - Weaviate Podcast #73!

Weaviate Podcast

NOTE

Giving the bot freedom in following instructions and improving models

The speaker suggests that the bot should have a scratch pad and a separate section of memory called a rag component. They believe that as the models improve, they should give the bot more freedom and let it figure out what the scratch pad is for. However, they caution against splitting it up too much. They also mention that the chatbot version could benefit from a rag component, which is like a smart contact that pulls information from a database. Overall, they recommend adding the rag component to improve the chatbot service.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner