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

Adding dummy_response option, allows for dry running #57

Merged
merged 3 commits into from
Aug 2, 2023
Merged

Conversation

HallerPatrick
Copy link
Collaborator

PR introduces a dummy_response option. Can be used instead of actual response of prompt node. Good for testing as user and developer.

I chose a more flexibel approach, such that the user can decide what value is returned.
Can be a callable lambda prompt: "Dummy movie response" or a string value. Open for alternatives.

Also adjusted the tests for DatasetGenerator in test_dataset_generator.py to not use a actual HF model. Can also be applied in other tests.

@HallerPatrick
Copy link
Collaborator Author

Helps with the haystack[inference] problem #56

@HallerPatrick HallerPatrick merged commit fa822eb into main Aug 2, 2023
6 checks passed
@whoisjones whoisjones deleted the dry_run branch August 4, 2023 15:21
whoisjones pushed a commit that referenced this pull request Oct 24, 2023
Adding dummy_response option, allows for dry running
whoisjones pushed a commit that referenced this pull request Oct 24, 2023
Adding dummy_response option, allows for dry running
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