0
$\begingroup$

I am creating a LLM chat app with LangChain. I am keeping track of the chat history with a simple array that gets sent to the LLM with every prompt. I noticed LangChain also has classes that automatically keep track of the whole conversation, such as BufferMemory and ConversationBufferMemory

https://python.langchain.com/docs/modules/memory/types/buffer

It's not explained however if these classes automatically keep track of different users as well? What if two users connect to the script, will their conversations get mixed up with each other?

How do you keep track of multiple users in a Chat LLM application?

$\endgroup$
1
  • $\begingroup$ This becomes more like a system design question to distribute the app for multiple users. It can be redis to store cache, or you can keep the records in db for longer runs. $\endgroup$ Commented Mar 1 at 23:40

0

You must log in to answer this question.

Browse other questions tagged .