op5dev/Prompt GitHub AI Models via GitHub Action

Prompt GitHub AI Models using inference request via GitHub Action API.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Jun 19, 2026
License
Apache 2.0

Pinned Snippet

workflow.ymlSHA-pinned
uses: op5dev/prompt-ai@4cacb93e4a1e101f3a89650b31a3582321f2461d # v2.0.0

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
modelModel ID to use for the inference request. (e.g., `openai/gpt-4.1-mini`)noopenai/gpt-4.1-mini
system-promptPrompt associated with the `system` role. (e.g., `You are a helpful software engineering assistant`)noYou are a helpful technical assistant, experienced in software engineering CI/CD workflows. Respond concisely, to the point, and in a single response without requesting subsequent user input.
user-promptPrompt associated with the `user` role. (e.g., `List best practices for workflows with GitHub Actions`)noList best practices for workflows with GitHub Actions.
max-tokensThe maximum number of tokens to generate in the completion. The token count of your prompt plus `max-tokens` cannot exceed the model's context length. (e.g., `100`)no""
temperatureThe sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. (e.g., range is `[0, 1]`)no""
top-pAn alternative to sampling with temperature called nucleus sampling. This value causes the model to consider the results of tokens with the provided probability mass. (e.g., range is `[0, 1]`)no""
frequency-penaltyA value that influences the probability of generated tokens appearing based on their cumulative frequency in generated text. (e.g., range is `[-2, 2]`)no""
modalitiesThe modalities that the model is allowed to use for the chat completions response. (e.g., from `text` and `audio`)no""
orgOrganization to which the request is to be attributed. (e.g., `github.repository_owner`)no""
presence-penaltyA value that influences the probability of generated tokens appearing based on their existing presence in generated text. (e.g., range is `[-2, 2]`)no""
response-format-schemaDesired format for structured JSON response. (TODO)""
seedIf specified, the system will make a best effort to sample deterministically such that repeated requests with the same seed and parameters should return the same result. (e.g., `123456789`)no""
stopA collection of textual sequences that will end completion generation. (e.g., `["\n\n", "END"]`)no""
streamA value indicating whether chat completions should be streamed for this request. (e.g., `false`)no""
stream-include-usageWhether to include usage information in the response. (e.g., `false`)no""
tool-choiceIf specified, the model will configure which of the provided tools it can use for the chat completions response. (e.g., 'auto', 'required', or 'none')no""
toolsA list of tools the model may request to call. (TODO)no""
payloadBody parameters of the inference request in JSON format. (e.g., `{"model"…`)no""
payload-filePath to a JSON file containing the body parameters of the inference request. (e.g., `./payload.json`)no""
show-payloadWhether to show the body parameters in the workflow log. (e.g., `false`)nofalse
show-responseWhether to show the response content in the workflow log. (e.g., `true`)notrue
github-api-versionGitHub API version. (e.g., `2022-11-28`)no2022-11-28
github-tokenGitHub token for authorization. (e.g., `github.token`)no${{ github.token }}
namedescription
responseResponse content from the inference request.
response-fileFile path containing the complete, raw response in JSON format.