-
Notifications
You must be signed in to change notification settings - Fork 12
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
Experiments to see if LLM embeddings can recapitulate subsumption #25
base: main
Are you sure you want to change the base?
Conversation
…ren't of interest)
…ren't of interest)
@@ -1595,6 +1601,66 @@ def _text_lookup(obj: Dict): | |||
db.update_collection_metadata(collection, object_type="OntologyClass") | |||
|
|||
|
|||
@ontology.command(name="subsumption") |
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.
We should decide on one place or another. I think in the agent itself is best since this is more of a custom analysis rather than a generic command?
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.
sure, glad to put this where ever is best
So you mean we can get rid of the click command and just put the glue code that calls SubsumptionEvalAgent
in the notebook?
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.
I'd be in favor of having this command available for easy results replication if lines 1647 onward go in the agent code Looked at the code again and I'm content with the current arrangement as it's already fairly generic
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.
+1 thanks @caufieldjh!
No description provided.