In a workflow with multiple LLM nodes, each node should have its own unique memory when processing data with memory enabled. However, currently, each LLM is accessing memory based on the response node's content. This can easily cause role confusion between the two LLMs. #4365
xiaobinwu24
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
In a workflow with multiple LLM nodes, each node should have its own unique memory when processing data with memory enabled. However, currently, each LLM is accessing memory based on the response node's content. This can easily cause role confusion between the two LLMs.
Beta Was this translation helpful? Give feedback.
All reactions