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

feat(smart-apply): Adds custom model prompt for smart apply. #7328

Merged
merged 5 commits into from
Mar 5, 2025

Conversation

hitesh-1997
Copy link
Contributor

@hitesh-1997 hitesh-1997 commented Mar 4, 2025

Test plan

@hitesh-1997 hitesh-1997 changed the base branch from main to hitesh/smart-apply-intent March 5, 2025 00:00
@@ -15,27 +11,3 @@ export interface ModelParametersInput {
export interface ModelParameterProvider {
getModelParameters(args: ModelParametersInput): CompletionParameters
}

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Moved this to vscode/src/edit/adapters/default.ts

@hitesh-1997 hitesh-1997 changed the title Hitesh/smart apply qwen model feat(smart-apply): Adds custom prompt builder and LLM parameter provider for the custom model for smart apply. Mar 5, 2025
@hitesh-1997 hitesh-1997 changed the title feat(smart-apply): Adds custom prompt builder and LLM parameter provider for the custom model for smart apply. feat(smart-apply): Adds prompt for the custom model for smart apply. Mar 5, 2025
@hitesh-1997 hitesh-1997 changed the title feat(smart-apply): Adds prompt for the custom model for smart apply. feat(smart-apply): Adds custom model prompt for smart apply. Mar 5, 2025
Copy link
Contributor

@umpox umpox left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for splitting things out, LGTM.

Is there any way we can test this without running a local dev instance?

${getGuidelinesPrompt()}`
}

function getUserPrompt(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It would be useful to add some simple snapshot tests for this file, just to view the raw prompt output and check that it looks correct and isn't broken by someone forgetting to add a </ in future

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good point, let me add this in the follow up PR.

Base automatically changed from hitesh/smart-apply-intent to main March 5, 2025 13:00
@hitesh-1997
Copy link
Contributor Author

Thanks for splitting things out, LGTM.

Is there any way we can test this without running a local dev instance?

Currently the backend PR is not merged, we should be able to test this when the SG get deloyed tomorrow

@hitesh-1997 hitesh-1997 force-pushed the hitesh/smart-apply-qwen-model branch from e68c366 to 8f33ffb Compare March 5, 2025 13:08
@hitesh-1997 hitesh-1997 merged commit b28c13c into main Mar 5, 2025
20 of 22 checks passed
@hitesh-1997 hitesh-1997 deleted the hitesh/smart-apply-qwen-model branch March 5, 2025 13:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants