From aa2631a0164827fb55bf8cafd4d4ce1239c433f4 Mon Sep 17 00:00:00 2001 From: Shishir Patil Date: Wed, 11 Oct 2023 11:53:37 -0700 Subject: [PATCH] updates --- index.html | 53 +++++++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 26 deletions(-) diff --git a/index.html b/index.html index ed9e0713..88ed6d06 100644 --- a/index.html +++ b/index.html @@ -42,7 +42,7 @@

Paper (Coming Soon) - Discord (Coming Soon) + Discord GitHub

@@ -50,7 +50,7 @@
-

Teach LLMs to manage their own memory and achieve unbounded context!

+

Teach LLMs to manage their own memory for unbounded context!

@@ -61,14 +61,12 @@
MemGPT system overview - In MemGPT (components shaded), a fixed-context LLM is augmented with a tiered memory system and a set of functions - that allow it to manage its own memory. - The LLM inputs the text (tokens) in main memory, and outputs text that is interpreted by a parser, - resulting either in a yield or a function call. - MemGPT uses functions to move data between main memory and disk memory. - When the LLM generates a function call, it can request immediate return of execution to chain together functions. - In the case of a yield, the LLM will not be run again until the next external event trigger - (e.g. a user message or scheduled interrupt). + In MemGPT, a fixed-context LLM is augmented with a tiered memory system and a set of functions that allow it to manage its own memory. + The LLM takes as input the text in main context (capped at the size of the standard LLM context window), and outputs text that + is interpreted by a parser, resulting either in a yield or a function call. MemGPT uses functions to move data between main + context and external context. When the LLM generates a function call, it can request immediate return of + execution to chain together functions. In the case of a yield, the LLM will not be run again until the next external + event trigger (e.g. a user message or scheduled interrupt).
@@ -97,18 +95,20 @@

Abstract

- Large language models (LLMs) have revolutionized AI but are constrained by limited context windows, - hindering their utility in tasks like extended conversations and document analysis. - Drawing inspiration from the hierarchical memory systems in traditional operating systems, - we introduce MemGPT (Memory-GPT). - Similar to how an operating system (OS) provides the illusion of large memory resources through - data movement between fast and slow memory, - MemGPT manages tiers of memory to effectively manage extended context within the language model's - limited context window, and utilizes interrupts to manage control flow between itself and the user. - We evaluate our OS-inspired design in two domains where the limited context windows of modern LLMs - severely handicaps their performance: document analysis, where MemGPT is able to analyze large documents - that far exceed the underlying LLM's context limit, and multi-session chat, where MemGPT enables - conversational agents to remember, reflect, and evolve dynamically through long-term interactions with their users. + Large language models (LLMs) have revolutionized AI but are constrained by + limited context windows, hindering their utility in tasks like extended conversa- + tions and document analysis. Drawing inspiration from the hierarchical memory + systems in traditional operating systems, we introduce MemGPT (Memory-GPT). + Similar to how an operating system (OS) provides the illusion of large memory + resources through data movement between fast and slow memory, MemGPT man- + ages tiers of memory to effectively manage extended context within the language + model's limited context window, and utilizes interrupts to manage control flow + between itself and the user. We evaluate our OS-inspired design in two domains + where the limited context windows of modern LLMs severely handicaps their per- + formance: document analysis, where MemGPT is able to analyze large documents + that far exceed the underlying LLM's context limit, and multi-session chat, where + MemGPT enables conversational agents to remember, reflect, and evolve dynam- + ically through long-term interactions with their users. Code and Data is available at https://memgpt.ai

@@ -121,10 +121,11 @@

Citation

- @inproceedings{pacher2023memgpt,
-   title={MemGPT: Towards an OS for LLMs}
-   author={Packer, Charles Avery}
-   year={2023},
+ @inproceedings{packer2023memgpt,
+   title={{MemGPT}: Towards LLMs as Operating Systems}
+   author={Packer, Charles and Fang, Vivian and Patil, Shishir G.
+   and Lin, Kevin and Wooders, Sarah and Gonzalez, Joseph E.}
+   year={2023}
}