tidyllm (version 0.1.0)

ollama: Send LLMMessage to ollama API

Description

Send LLMMessage to ollama API

Usage

ollama(
  .llm,
  .model = "llama3",
  .stream = FALSE,
  .seed = NULL,
  .json = FALSE,
  .temperature = NULL,
  .num_ctx = 2048,
  .ollama_server = "http://localhost:11434",
  .timeout = 120
)

Value

Returns an updated LLMMessage object.

Arguments

.llm

An existing LLMMessage object or an initial text prompt.

.model

The model identifier (default: "llama3").

.stream

Should the answer be streamed to console as it comes (optional)

.seed

Which seed should be used for random numbers (optional).

.json

Should output be structured as JSON (default: FALSE).

.temperature

Control for randomness in response generation (optional).

.num_ctx

The size of the context window in tokens (optional)

.ollama_server

The URL of the ollama server to be used

.timeout

When should our connection time out