Generate verified datasets at scale.

import lightningrod as lr

# Get antitrust news to train a domain expert
seeds = lr.NewsSeedGenerator(
    query="antitrust investigation",
    start_date="2025-01-01"
)

# Define the scope and style of the questions
questioner = lr.QuestionGenerator(
    instructions="Write forward-looking, self-contained questions with explicit dates/entities.",
    examples=[
        "What is the likely outcome of the DOJ lawsuit?",
        "Which specific Sherman Act violations are cited?"
    ]
)

# Verify answers against live sources
labeler = lr.WebSearchLabeler()

# Run pipeline
pipeline = lr.Pipeline(seeds, questioner, labeler)
dataset = pipeline.batch(100)