> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bespokelabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Curator overview

> Curator is an open-source Python library for building synthetic data pipelines with LLMs.

Curator is an open-source Python library from Bespoke Labs. You use it to generate synthetic data with LLMs and to run LLM inference over large datasets. You can then use the data to fine-tune a model or to extract structured data.

## What Curator does

* You describe each step of a pipeline as a Python class with a `prompt` method and a `parse` method.
* You can ask for structured output with a Pydantic model.
* Curator sends requests in parallel, respects rate limits, and retries failed requests.
* Curator caches every response. If a run stops, you can start it again and Curator continues from where it stopped.
* Curator works with many providers and with local models through vLLM and Ollama. See the [backend list](/curator/api-reference#backends).
* You can use the batch APIs of OpenAI, Anthropic, Gemini, Mistral, and Azure OpenAI by setting one flag.
* You can watch your data in the hosted [Curator Viewer](/curator/viewer) while Curator generates it.
* You can run code that an LLM wrote with the [code executor](/curator/guides/code-execution).

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/curator/quickstart">
    Install Curator and run your first prompt.
  </Card>

  <Card title="Key concepts" icon="book" href="/curator/key-concepts">
    Learn how `prompt` and `parse` turn one dataset into another.
  </Card>

  <Card title="Batch inference" icon="layer-group" href="/curator/batch">
    Send large jobs to provider batch APIs at a lower price.
  </Card>

  <Card title="Source code" icon="github" href="https://github.com/bespokelabsai/curator">
    Read the code and the examples on GitHub.
  </Card>
</CardGroup>

If you have a question, ask in the [Bespoke Labs Discord](https://discord.com/invite/KqpXvpzVBS) or email [company@bespokelabs.ai](mailto:company@bespokelabs.ai).