Github Create Inference Chat Completions

• seedinteger
  If 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.
• stoparray
  Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
• modelstring

  Required
  ID of the specific model to use for the request. Format: {publisher}/{model_name}, e.g., openai/gpt-4o, anthropic/claude-3.5-sonnet.
• toolsarray
  A list of tools (functions) the model may call. The model will choose when and how to call these functions based on the conversation context.
• top_pnumber
  An alternative to temperature called nucleus sampling. Range: [0.0, 1.0]. The model considers tokens with top_p probability mass.
• streamboolean
  If true, partial message deltas will be sent as data-only server-sent events as they become available.
• messagesarray

  Required
  The collection of context messages associated with this chat completion request. Each message must have a role (assistant, developer, system, or user) and content.
• max_tokensinteger
  Maximum number of tokens to generate in the completion. The total length of input tokens and generated tokens is limited by the model's context length.
• modalitiesarray
  List of supported modalities for this request. Supported values: text, audio.
• temperaturenumber
  Controls the apparent creativity of generated completions. Range: [0.0, 1.0]. Lower values make output more deterministic, higher values more random.
• tool_choicestring
  Controls which (if any) tool is called by the model.
• stream_optionsobject
  Options for streaming responses.

• data

  Required
  Data from the action execution
• errorstring
  Error if any occurred during the execution of the action
• successfulboolean

  Required
  Whether or not the action execution was successful or not

No verified related use cases are linked yet.

No published Skills explicitly reference this Action yet.