LlamaIndex Webinar: Long-Term, Self-Editing Memory with MemGPT
Vložit
- čas přidán 30. 06. 2024
- Long-term memory for LLMs is an unsolved problem, and doing naive retrieval from a vector database doesn’t work.
The recent iteration of MemGPT (Packer et al.) takes a big step in this direction. Taking the LLM as an OS analog, the authors propose “virtual context management” to manage both memory in-context window and in external storage. Recent advances in function calling allow these agents to read and write from these data sources, and modify their own context.
We're excited to host Charles Packer, lead author of MemGPT. Charles presents an excellent overview of the project, gives a demo, and we also do a Q&A session in the middle and towards the end.
Timeline:
00:00 - 24:20 Presentation
24:20 - 41:18 Demo
41:18 Q&A
Nice project. This is awesome. Greetings from old Europe.
Pretty cool anyone know where I can get the persona temp prompt that generates perplexity like responses .. shown in the demo?
When will the developer portal be available?
how to use memgpt with llamaindex as memory