Skip to content

Conversation

@devin-ai-integration
Copy link
Contributor

Summary

Adds an optional effort parameter to the DeepSearchOptions type for deep search. This allows users to configure the effort level when using type: "deep":

  • "medium" (default): Faster, cheaper searches using deep_lite service
  • "high": Maximum quality using full deep service

This corresponds to the backend change in exa-labs/monorepo#11290.

Review & Testing Checklist for Human

  • Verify the param name effort matches the backend API expectation (check if camelCase conversion is needed)
  • Test a deep search call with effort: "high" against the API to confirm it's accepted

Notes

Requested by: William Li ([email protected])
Link to Devin run: https://app.devin.ai/sessions/6c21ac37bc6f4dbf8c37d31f7fbbc388

A corresponding PR was also created for exa-py to add the same parameter.

@devin-ai-integration
Copy link
Contributor Author

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment and CI monitoring

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.

1 participant