About Chat memory manager

Describe the problem/error/question

Question about how to use the chat memory manager.

What is the error message (if any)?

I am trying to inset the chat into the chat memory by using the llm chain instead of using the conversational agent. The reason of using this is becoz I want to reduce the token usage that forcing some thinking step become hard logic.

While I trying, I found out that chatmemory + zep cannot insert any information into the chat. I am here looking for more detailed documentation of this node.

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)


Share the output returned by the last node

Information on your n8n setup

  • **n8n version : ** latest
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main) : own
  • Running n8n via (Docker, npm, n8n cloud, desktop app): docker
  • Operating system: linux

Hey @Rico_Yu,

What sort of details are you after on the node?

I am also struggling to create persistent chat memory using Zep and a Langchain Conversational Agent. Zep looked like a great solution but can’t figure it out from the documentation or forum. Any example of how this should be configured would be great.

I have the same problem, did I manage to solve it?

@jon can you help us?


they go through chat memory but it is not activated

Yup. Memory manager doesn’t seem to work with Zep, which is a shame because it would be perfect. Has someone found a workaround or fix for this?

I can confirm the Chat Memory Manager node is NOT working with Zep still.

With an HTTP request node I can get the chat history just fine:

With the Chat Memory Manager node the exact same sessionId returns nothing:


Tried many different ways to give the sessionId, tried to insert messages to existing session, tried to insert message to a new session, but nothing works. I don’t think Zep is getting the requests from the at all.

Is this a known issue @Jon ?

3 Likes

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.