-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
refactor(agent): Agent modular refactoring #1487
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
r+
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great, The enhancement of the memory module and role module makes the agent framework capabilities more robust and complete. 🚀
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
r+
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
Description
1. Refactor
Refactor the agent code into four core modules according to the paper A survey on large language model based autonomous agents
2. More flexible Profile module
A more flexible Profile module implementation that supports creating agent profiles from environment variables, databases, and other implementations.
Note: In order to be more clear and intuitive, use jinja2 to render the prompt template of agent profile.
3. Unified memory framework support
Supports sensory memory, short-term memory, long-term memory and hybrid memory.
How Has This Been Tested?
Run all python codes in the
examples/agents
directory.Snapshots:
No snapshots.
Checklist: