Create an OpenAI-compatible LLM Object

Usage

create_OpenAI(
  model_name,
  system_prompt = SYSTEM_PROMPT_DEFAULT,
  temperature = TEMPERATURE_DEFAULT,
  output_schema = NULL,
  name = NULL,
  base_url = OPENAI_URL_DEFAULT,
  api_key = NULL,
  api_key_env = OPENAI_API_KEY_ENV_DEFAULT,
  keychain_service = NULL,
  organization = NULL,
  project = NULL,
  timeout = OPENAI_TIMEOUT_DEFAULT,
  extra_headers = NULL,
  extra_body = NULL,
  enable_thinking = NULL,
  validate_model = FALSE
)

Arguments

model_name: Character: The name of the LLM model to use.
system_prompt: Character: The system prompt to use.
temperature: Numeric [0, 2]: The temperature for the model.
output_schema: Optional Schema: Output schema created using schema.
name: Optional character: Name for the LLM object.
base_url: Character: Base URL of the OpenAI-compatible server.
api_key: Optional character: API key.
api_key_env: Character: Environment variable containing the API key.
keychain_service: Optional character: macOS Keychain service containing the API key.
organization: Optional character: OpenAI organization id.
project: Optional character: OpenAI project id.
timeout: Numeric (0, Inf): Request timeout in seconds.
extra_headers: Optional list: Additional HTTP headers.
extra_body: Optional list: Additional request body fields.
enable_thinking: Optional logical: Whether to enable model thinking for compatible local servers.
validate_model: Logical: Whether to validate model availability using the models endpoint.

Value

OpenAI LLM object

Author

EDG

Examples

llm <- create_OpenAI(
   model_name = "local-model",
   base_url = "http://localhost:1234/v1",
   system_prompt = "You are a meticulous research assistant.",
   validate_model = FALSE
)