claude: Call the Anthropic API to interact with Claude models

Description

Call the Anthropic API to interact with Claude models

Usage

claude(
  .llm,
  .model = "claude-3-5-sonnet-20240620",
  .max_tokens = 1024,
  .temperature = NULL,
  .top_k = NULL,
  .top_p = NULL,
  .metadata = NULL,
  .stop_sequences = NULL,
  .tools = NULL,
  .api_url = "https://api.anthropic.com/",
  .verbose = FALSE,
  .wait = TRUE,
  .min_tokens_reset = 0L,
  .timeout = 60,
  .stream = FALSE
)

Value

Returns an updated LLMMessage object.

Arguments

.llm: An existing LLMMessage object or an initial text prompt.
.model: The model identifier (default: "claude-3-5-sonnet-20240620").
.max_tokens: The maximum number of tokens to generate (default: 1024).
.temperature: Control for randomness in response generation (optional).
.top_k: Top k sampling parameter (optional).
.top_p: Nucleus sampling parameter (optional).
.metadata: Additional metadata for the request (optional).
.stop_sequences: Sequences that stop generation (optional).
.tools: Additional tools used by the model (optional).
.api_url: Base URL for the API (default: "https://api.anthropic.com/v1/messages").
.verbose: Should additional information be shown after the API call
.wait: Should we wait for rate limits if necessary?
.min_tokens_reset: How many tokens should be remaining to wait until we wait for token reset?
.timeout: Request timeout in seconds (default: 60).
.stream: Stream back the response piece by piece (default: FALSE).