-
Notifications
You must be signed in to change notification settings - Fork 4
Adding support for QPY as the circuit exchange mechanism #60
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
Conversation
…d format auto-detection
…server) for better LLM comprehension
… the main qiskit-mcp-server
vabarbosa
left a comment
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 looks good and i was able to test and run some examples
| "depth_reduction": depth_reduction, | ||
| "two_qubit_gate_reduction": two_qubit_reduction, |
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 curious since i am not too familiar, but could there be a case where either of these values are negative? and if so, would that have any impact on what is being returned here?
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, we can find examples in which a particular method does not improve and gives worse results than others. That would be the negative value there.
The impact will be for the agent/LLM to know that something is worse. I'm not sure every LLM would be able to interpret clearly the sign, so I'll review it with a few models in the future. Thanks!
Description
Adding support for QPY as the circuit exchange format between methods and servers
Linked Issue(s)
Fixes #59
Type of change
Please delete options that are not relevant.
How Has This Been Tested?
Automated tests
Checklist: