Lightningrod API

Train custom LLMs from messy historical data. No manual labeling required.

⚡ Get started in 5 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.

Get started API reference

my-llm.py

from lightningrod import LightningRod, BinaryAnswerType, QuestionPipeline, NewsSeedGenerator, ForwardLookingQuestionGenerator, WebSearchLabeler

lr = LightningRod(api_key="your-api-key")

dataset = lr.transforms.run(dataset_config)
model = lr.training.run(training_config)
evals = lr.evals.run(model_id=model.model_id)

client.chat.completions.create(
    model=model_id=training_run.model_id,
    messages=[{"role": "user", "content": "..."}]
)

Dataset Generation

Get started with the developer platform in 5 minutes.

LLM Fine Tuning

Browse, test, and implement APIs.

LLM Hosting

Learn more about hosting the developer platform.