LlamaIndex Webinar: Long-Term, Self-Editing Memory with MemGPT

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 …

analog authors big context context window database editing iteration llamaindex llm llms long-term management memory retrieval unsolved vector vector database virtual webinar work