-
Notifications
You must be signed in to change notification settings - Fork 17
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
started work on abstraction layer, wrapped original implementaton #4
base: master
Are you sure you want to change the base?
started work on abstraction layer, wrapped original implementaton #4
Conversation
str: the task id""" | ||
pass | ||
|
||
def complete_task(self, task: PlannerTask, name: str = "PlannerGPT"): |
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.
Why do we need to pass name arg ?
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.
essentally this allows a storage implementation to keep multiple instances apart (thats once the name is actually injected, which it isn't yet)
"get_next_task", | ||
"Returns the task you are supposed to work on", | ||
{}, | ||
get_current_task |
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.
is this the right function to call ?
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.
yes, get next task is aliasing get_current_task, just so it is less likely to stumble over making the distinction
|
||
self.planner = Planner(get_planner( | ||
agent_id=settings.ai_name, | ||
implementation_name="SqlitePlanner" # TODO: make this configurable |
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.
should make this configureable before merge
DRAFT
Description
This PR bundles the work to abstract the implementations in the planner, which is supposed to allow other/more complex
storage implementations (for example sqliite)