Call Ollama for Text Generation

Sends a prompt to Ollama and returns the generated text.

Usage

call_ollama(
  prompt,
  model = "tinyllama",
  system = NULL,
  temperature = 0.3,
  max_tokens = 512,
  timeout = 120,
  verbose = FALSE
)

Arguments

prompt

Character string containing the prompt.

model

Character string specifying the Ollama model (default: "tinyllama").

system

Character string with system instructions (default: NULL).

temperature

Numeric value controlling randomness (default: 0.3).

max_tokens

Maximum number of tokens to generate (default: 512).

timeout

Timeout in seconds for the request (default: 60).

verbose

Logical, if TRUE, prints progress messages.

Value

Character string with the generated text, or NULL if failed.

See also

Other ai: call_gemini_chat(), call_llm_api(), call_openai_chat(), check_ollama(), describe_image(), generate_topic_content(), get_api_embeddings(), get_best_embeddings(), get_content_type_prompt(), get_content_type_user_template(), get_recommended_ollama_model(), list_ollama_models(), run_rag_search()

Examples

if (FALSE) { # \dontrun{
response <- call_ollama(
  prompt = "Summarize these keywords: machine learning, neural networks, AI",
  model = "tinyllama"
)
print(response)
} # }