backguru-t/PR summary generator
Generate PR summarization with OpenAI when a PR is opened or updated.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| github_token | The GitHub token | yes | — |
| openai_api_key | OpenAI API key | yes | — |
| pull_request_id | Pull request id (otherwise attempt to extract it from the GitHub metadata) | no | "" |
| allowed_users | Comma-separated list of GitHub usernames this action will run for, if empty it will run for all users | no | "" |
| gpt_mode_3 | OpenAI model to use, needs to be compatible with the chat/completions endpoint | no | gpt-3.5-turbo |
| gpt_model_4 | OpenAI model to use, needs to be compatible with the chat/completions endpoint | no | gpt-4 |
| max_tokens | Maximum number of prompt tokens to use | no | 1000 |
| temperature | Temperature for the model, higher values will make the model more creative, lower values will make it more conservative | no | 0.6 |
| sample_prompt | Sample prompt to use for the model, refer to SAMPLE_PROMPT in the Python file. | no | "" |
| sample_response | A sample of an ideal response based on the sample prompt | no | "" |
Outputs
no outputs