WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-24 08:32:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fixup Grammar (#2037)

Browse Source
This commit is contained in:
William FH
2024-10-07 16:56:13 -07:00
committed by GitHub
parent 45957cc72a
commit 90b8b4d745
1 changed files with 0 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/concepts/memory.md
-6
View File
@@ -14,12 +14,6 @@ Both are important to understand and implement for your application.
## Short-term memory
Short-term memory refers to remembering previous turns within a single conversation thread. LangGraph manages short-term memory as part of the agent's state, which is persisted using checkpoints scoped by the thread ID. For example, in a chatbot, the state would contain the conversation history as a list of messages.
However, long conversations pose challenges for LLMs due to context window limitations and performance degradation over long contexts. Managing short-term memory involves balancing precision and recall with latency and cost requirements.
Common techniques for managing conversation history include:
Short-term memory lets your application remember previous turns within a single [thread](persistence.md#threads) or conversation. A [thread](persistence.md#threads) organizes multiple turns in a session or interaction, similar to the way an email or slack thread groups messages in a single conversation.
LangGraph manages short-term memory as part of the agent's state, persisted via thread-scoped checkpoints. This state can normally includes the conversation history along with other stateful data, such as uploaded files, generated artifacts, and other results from side-effects. By storing these in the graph's state, the bot can access the full context for a given conversation while maintaining separation between different threads.