aigra_generate_items: Generate and review assessment items

In AIGRA: Agentic Item Generation, Review, and Analysis

Generate and review assessment items

Description

Runs the AIGRA Python backend pipeline to generate, solve, review, and export assessment items.

This user-facing wrapper accepts an AIGRA tabular item bank that has already been loaded into R as a data frame. To use CSV or XLSX files, first call aigra_read_template() and pass the resulting data frame to this function.

Usage

aigra_generate_items(
  data,
  model = "gemini-3.1-pro-preview",
  provider = "auto",
  gemini.API = NULL,
  openai.API = NULL,
  groq.API = NULL,
  anthropic.API = NULL,
  backend_path = NULL,
  ...
)

aigra_generate_items(
  data,
  model = "gemini-3.1-pro-preview",
  provider = "auto",
  gemini.API = NULL,
  openai.API = NULL,
  groq.API = NULL,
  anthropic.API = NULL,
  backend_path = NULL,
  ...
)

Arguments

data	A data frame with the standard AIGRA tabular columns.
model	Model name to use.
provider	LLM provider. Use "auto", "gemini", "openai", "groq", or "anthropic", depending on the backend configuration.
gemini.API	Optional Gemini API key.
openai.API	Optional OpenAI API key.
groq.API	Optional Groq API key.
anthropic.API	Optional Anthropic API key.
backend_path	Optional path to the AIGRA Python backend.
...	Additional arguments passed to aigra_generate_tabular_items().

Value

A data frame if read_csv is TRUE; otherwise invisibly returns latest CSV path.

A data frame or list returned by the AIGRA tabular generation backend.

Examples

## Not run: 
template <- aigra_read_template("template.xlsx")

result <- aigra_generate_items(
  data = template,
  provider = "gemini",
  model = "gemini-2.5-flash",
  source_language = "English",
  target_language = "English",
  n_clones = 1,
  max_items = 1
)

## End(Not run)

AIGRA documentation built on July 10, 2026, 5:06 p.m.