-
-
Notifications
You must be signed in to change notification settings - Fork 138
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
Summarize actions to sentence + icon #741
Comments
/bounty $100 |
💎 $100 bounty • OpenAdaptAISteps to solve:
Thank you for contributing to OpenAdaptAI/OpenAdapt! Add a bounty • Share on socials
|
/attempt #741 Options |
@abrichr can you please explain the issue a bit more in detail? |
@shashank40 from the README, here is a screenshot of the dashboard: Here is a screenshot of Microsoft's recent updates to PowerAutomate: Notice the one-sentence action summaries. We would like to implement the same type of thing, i.e. convert an action dict, window dict, and screenshot into a sentence and an icon. You can use the prompt adapter for this, e.g.
I expect the prompt should live in a .j2 file. You will need another prompt to generate an icon. |
/attempt #741
|
/attempt #741 Options |
Related to OpenAdaptAI#741 Add functionality to summarize actions and generate icons for recordings. * **openadapt/adapters/prompt.py** - Add `generate_summary_and_icon` function to generate a summary and icon for a given action using the `prompt` function. * **openadapt/app/dashboard/api/recordings.py** - Import `generate_summary_and_icon` function. - Update `get_recording_detail` function to include summaries and icons for action events. * **openadapt/app/dashboard/app/recordings/detail/page.tsx** - Update `Recording` component to display summaries and icons for action events.
💡 @vishwamartur submitted a pull request that claims the bounty. You can visit your bounty board to reward. |
Feature request
When visualizing recordings, we would like to collapse each top level action into a one to two sentence description in a systematized way, ideally with an icon (eg prompt for a segment).
Motivation
Understanding recordings, humans and models.
The text was updated successfully, but these errors were encountered: