call_llm: Call LLM API

In LLMR: Interface for Large Language Model APIs in R

Call LLM API

Description

Sends a message to the specified LLM API and retrieves the response.

Usage

call_llm(config, messages, verbose = FALSE, json = FALSE)

Arguments

config	An 'llm_config' object created by 'llm_config()'.
messages	A list of message objects (or a character vector for embeddings) to send to the API.
verbose	Logical. If 'TRUE', prints the full API response.
json	Logical. If 'TRUE', returns the raw JSON response as an attribute.

Value

The generated text response or embedding results with additional attributes.

Examples

## Not run: 
  # Voyage AI embedding Example:
  voyage_config <- llm_config(
    provider = "voyage",
    model = "voyage-large-2",
    embedding = TRUE,
    api_key = Sys.getenv("VOYAGE_API_KEY")
  )

  embedding_response <- call_llm(voyage_config, text_input)
  embeddings <- parse_embeddings(embedding_response)
  embeddings |> cor() |> print()


  # Gemini Example
  gemini_config <- llm_config(
    provider = "gemini",
    model = "gemini-pro",          # Or another Gemini model
    api_key = Sys.getenv("GEMINI_API_KEY"),
    temperature = 0.9,               # Controls randomness
    max_tokens = 800,              # Maximum tokens to generate
    top_p = 0.9,                     # Nucleus sampling parameter
    top_k = 10                      # Top K sampling parameter
  )

  gemini_message <- list(
    list(role = "user", content = "Explain the theory of relativity to a curious 3-year-old!")
  )

  gemini_response <- call_llm(
    config = gemini_config,
    messages = gemini_message,
    json = TRUE # Get raw JSON for inspection if needed
  )

  # Display the generated text response
  cat("Gemini Response:", gemini_response, "\n")

  # Access and print the raw JSON response
  raw_json_gemini_response <- attr(gemini_response, "raw_json")
  print(raw_json_gemini_response)

## End(Not run)

LLMR documentation built on June 8, 2025, 10:45 a.m.