Skip to content
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

PromptClip agent improvements #57

Open
1 task done
ashish-spext opened this issue Nov 6, 2024 · 0 comments
Open
1 task done

PromptClip agent improvements #57

ashish-spext opened this issue Nov 6, 2024 · 0 comments
Assignees
Labels
agent backend enhancement New feature or request

Comments

@ashish-spext
Copy link
Contributor

Confirm this is a new feature request

  • I've checked the current issues, and there's no record of this feature request

Describe the feature

1 - Better detection of content_type of prompt clip [1]
Here maybe we can test by improving the name of arg itself and description.

2 - Driving indexing parameters instead of hardcoding
For cases where user wants to change scene index prompt or give scene extraction config current design will fail.
Same goes for spoken index parameters.

What if we emit the message that video is not indexed instead of indexing in agent.
And then reasoning engine takes up the indexing either on defaults or asks users for configuration.
Also, currently we are taking up first available scene index we can make this dynamic by taking any of the available scene indexes.

[1] - #54 (comment)

Additional Context

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
agent backend enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants