appleboy/LLM Action

GitHub Action to interact with OpenAI Compatible LLM services

Trust Signals

name	description	required	default
base_url	Base URL for OpenAI Compatible API endpoint	no	https://api.openai.com/v1
api_key	API Key for authentication	yes	—
model	Model name to use	no	gpt-4o
skip_ssl_verify	Skip SSL certificate verification	no	false
system_prompt	System prompt to set the context. Supports plain text, file path, or URL (http://, https://). For files, use absolute/relative path or file:// prefix. Supports Go templates with environment variables (e.g., {{.GITHUB_REPOSITORY}}, {{.MODEL}}).	no	""
input_prompt	User input prompt for the LLM. Supports plain text, file path, or URL (http://, https://). For files, use absolute/relative path or file:// prefix. Supports Go templates with environment variables (e.g., {{.GITHUB_REPOSITORY}}, {{.MODEL}}).	yes	—
temperature	Temperature for response randomness (0.0-2.0)	no	0.7
max_tokens	Maximum tokens in the response	no	1000
tool_schema	JSON schema for structured output via function calling. Supports plain text, file path, or URL. Supports Go templates with environment variables (e.g., {{.GITHUB_REPOSITORY}}).	no	""
debug	Enable debug mode to print all parameters	no	false
headers	Custom HTTP headers to include in API requests. Format: "Header1:Value1,Header2:Value2" or multiline with one header per line. Useful for log analysis or custom authentication.	no	""

name	description
response	The response from the LLM
prompt_tokens	Number of tokens in the prompt
completion_tokens	Number of tokens in the completion
total_tokens	Total number of tokens used
prompt_cached_tokens	Number of cached tokens in the prompt (cost saving)
completion_reasoning_tokens	Number of reasoning tokens (for o1/o3 models)
completion_accepted_prediction_tokens	Number of accepted prediction tokens
completion_rejected_prediction_tokens	Number of rejected prediction tokens