Call LLM API

Calls different LLM providers (OpenAI, Gemini) through a single interface. Automatically routes to the appropriate provider-specific function.

Usage

call_llm_api(
  provider = c("openai", "gemini"),
  system_prompt,
  user_prompt,
  model = NULL,
  temperature = 0,
  max_tokens = 150,
  api_key = NULL
)

Arguments

provider

Character string: "openai" or "gemini"

system_prompt

Character string with system instructions

user_prompt

Character string with user message

model

Character string specifying the model (provider-specific defaults apply)

temperature

Numeric temperature for response randomness (default: 0)

max_tokens

Maximum number of tokens to generate (default: 150)

api_key

Character string with API key (required for openai/gemini)

Value

Character string with the model's response

See also

sanitize_llm_input() to clean text before prompting; get_best_embeddings() for vector embeddings; run_rag_search() for RAG search (retrieval + generation)

Examples

if (interactive()) {
# Using OpenAI
response <- call_llm_api(
  provider = "openai",
  system_prompt = "You are a helpful assistant.",
  user_prompt = "Generate a topic label",
  api_key = Sys.getenv("OPENAI_API_KEY")
)

# Using Gemini
response <- call_llm_api(
  provider = "gemini",
  system_prompt = "You are a helpful assistant.",
  user_prompt = "Generate a topic label",
  api_key = Sys.getenv("GEMINI_API_KEY")
)
}
#> No OpenAI API key found. Provide your key using one of these methods:
#>   1. Sys.setenv(OPENAI_API_KEY = "your-key-here")
#>   2. Add OPENAI_API_KEY=your-key-here to your .Renviron file
#>   3. Pass directly via the api_key parameter