class Anthropic::Resources::Completions

def create(params)

Other tags:
    See: Anthropic::Models::CompletionCreateParams -

Returns:
  • (Anthropic::Models::Completion) -

Parameters:
  • request_options (Anthropic::RequestOptions, Hash{Symbol=>Object}, nil) --
  • betas (Array) -- Header param: Optional header to specify the beta version(s) you want to use.
  • top_p (Float) -- Body param: Use nucleus sampling.
  • top_k (Integer) -- Body param: Only sample from the top K options for each subsequent token.
  • temperature (Float) -- Body param: Amount of randomness injected into the response.
  • stop_sequences (Array) -- Body param: Sequences that will cause the model to stop generating.
  • metadata (Anthropic::Models::Metadata) -- Body param: An object describing metadata about the request.
  • prompt (String) -- Body param: The prompt that you want Claude to complete.
  • model (Symbol, String, Anthropic::Models::Model) -- Body param: The model that will complete your prompt.\n\nSee [models](https://do
  • max_tokens_to_sample (Integer) -- Body param: The maximum number of tokens to generate before stopping.

Overloads:
  • create(max_tokens_to_sample:, model:, prompt:, metadata: nil, stop_sequences: nil, temperature: nil, top_k: nil, top_p: nil, betas: nil, request_options: {}) 
def create(params)
  parsed, options = Anthropic::CompletionCreateParams.dump_request(params)
  if parsed[:stream]
    message = "Please use `#create_streaming` for the streaming use case."
    raise ArgumentError.new(message)
  end
  header_params = {betas: "anthropic-beta"}
  @client.request(
    method: :post,
    path: "v1/complete",
    headers: parsed.slice(*header_params.keys).transform_keys(header_params),
    body: parsed.except(*header_params.keys),
    model: Anthropic::Completion,
    options: {timeout: 600, **options}
  )
end