Feature/human-in-the-loop-teleprompt

[burtenshaw]

📝 Changes Description

This is a WIP PR to start a discussion on involving human feedback in DSPy. If labellers could add feedback on a prompt during teleprompting it would support working in specific domains, and with lower quality or unlabelled data.

✅ Contributor Checklist

• [] Pre-Commit checks are passing (locally and remotely)
• [] Title of your PR / MR corresponds to the required format
• [] Commit message follows required format {label}(dspy): {message}

⚠️ Warnings

Anything we should be aware of ?