-
Notifications
You must be signed in to change notification settings - Fork 791
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
Added from_url method to fetch evaluation annotation from the api. #1795
Added from_url method to fetch evaluation annotation from the api. #1795
Conversation
Made some optimizations.
renamed the fn from_url to from_ragas_platform
src/ragas/dataset_schema.py
Outdated
return cls._process_dataset(dataset, metric_name) | ||
|
||
@classmethod | ||
def from_ragas_platform( |
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.
this brings to the point about what we are calling the thing at app.ragas.io - IMO is should be Ragas App and so the method should be from_ragas_app
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.
from_app is what I have named it right now, in case we need to be explicit, lets call it from_ragas_app
improve error handling in api responses with debug info enhance metric training with multiple data sources including run_id renamed the from_ragas_platform to from_app
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.
Just fix the ci by running make run-ci
and all looks good. Will discuss the change of docs later.
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.
The CI style is failing, let's fix that and merge this in 🙂
src/ragas/dataset_schema.py
Outdated
@@ -626,19 +626,16 @@ def from_json(cls, path: str, metric_name: t.Optional[str]) -> "MetricAnnotation | |||
@classmethod | |||
def from_app( | |||
cls, | |||
run_id: t.Optional[str] = None, | |||
evaluation_result: t.Optional[EvaluationResult] = None, | |||
run_id: str = None, |
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.
this will cause a type error since None
is not an str
type. The best way is to not have a default arg
Added from_url method to fetch evaluation annotation from the api.
Made some optimizations.