⚡ Get started in 10 minutes

Configure your use case and let us handle the nitty-gritty parts of the underlying infrastructure.

Our SDK handles the complete LLM pipeline end-to-end: from dataset generation, to training and inference.

Start with $50 Free Quickstart

generate_dataset.py

from datetime import datetime
import lightningrod as lr

answer_type = lr.BinaryAnswerType()
pipeline = lr.QuestionPipeline(
    seed_generator=lr.NewsSeedGenerator(
        start_date=datetime(2025, 1, 1),
        end_date=datetime(2025, 2, 1),
        search_query="AI regulation",
    ),
    question_generator=lr.ForwardLookingQuestionGenerator(
        instructions="Generate questions about future AI regulations and rulings",
        answer_type=answer_type,
    ),
    labeler=lr.WebSearchLabeler(answer_type=answer_type),
)

client = lr.LightningRod(api_key="your-api-key")
dataset = client.transforms.run(pipeline, max_questions=100)