Replies: 1 comment
-
Yes, I've tried that too, but LLMs always retain a form of independence, so it's complicated to force them to respect defined behaviors. Langchain offers several solutions. For example, you can use examples of input conversations to show the LLM how to respond, based on these examples. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I change qa templete to only say korean but answer is always english.
Beta Was this translation helpful? Give feedback.
All reactions