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

# ZeroEval Python SDK

> LLM Stats is powered by ZeroEval, our in-house evaluation library

<Card title="Start with the SDK quickstart" icon="rocket" href="/python-sdk/quickstart" horizontal>
  Build your first dataset, run a task, and compute quality metrics.
</Card>

<Info>
  **About the stack:** LLM Stats runs on top of **ZeroEval**, the evaluation
  library developed by the same team behind LLM Stats.
</Info>

## What You Can Do

<CardGroup cols={2}>
  <Card title="Upload benchmark data" icon="upload" href="/python-sdk/datasets/uploading-data">
    Add data via git, CSV import, or the browser editor.
  </Card>

  <Card title="Load and inspect data" icon="table-columns" href="/python-sdk/datasets/loading">
    Pull datasets, access rows with dot notation, and work with slices/subsets.
  </Card>

  <Card title="Run evals" icon="play" href="/python-sdk/evals/running-evals">
    Execute tasks with configurable workers, retries, and checkpoints.
  </Card>

  <Card title="Score quality" icon="chart-line" href="/python-sdk/evals/scoring-and-metrics">
    Add row, column, and run-level evaluations for robust measurement.
  </Card>

  <Card title="Inspect signals and traces" icon="waveform-lines" href="/python-sdk/evals/signals-and-traces">
    Emit runtime signals during execution and inspect them through traces.
  </Card>

  <Card title="Call models via the gateway" icon="bolt" href="/gateway/introduction">
    OpenAI-compatible chat, plus unified image, video, TTS, and STT endpoints.
  </Card>
</CardGroup>

## Recommended Path

<Steps>
  <Step title="Install and authenticate">
    Follow [`/python-sdk/installation`](/python-sdk/installation) to install
    `zeroeval` and configure `ZEROEVAL_API_KEY`.
  </Step>

  <Step title="Complete the first eval">
    Run the walkthrough in [`/python-sdk/quickstart`](/python-sdk/quickstart).
  </Step>

  <Step title="Upload benchmark data">
    Push data via git, import CSVs, or use the browser editor. Learn about
    subsets, versioning, and the recommended repository layout.
  </Step>

  <Step title="Productionize eval execution">
    Add scoring, repetition, and resume/reliability controls.
  </Step>
</Steps>

## Documentation Scope

* **Getting Started**: setup and first run
* **Datasets**: creation, loading, versioning, subsets, multimodal
* **Evals**: execution, scoring, metrics, repetitions, resume
* **Examples**: end-to-end text and multimodal workflows