Ask for human confirmation before calling Tools when using Agents in HTTP context #4891
alexandrubau
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
-
I am currently developing an app that serves LangChain library over a RESTful API.
I have implemented an OpenAI Tools Agent which successfully solves my requests by utilising the provided tools.
I would like to implement a feature that requests user's permission before calling some specific tools, since some of them may be destructive.
I know about this official guide but unfortunately it uses CLI context which is very different from the HTTP context which runs in a stateless environment.
How should I tackle this problem?
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions