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

# Quickstart

> Get up and running with Reverie in minutes.

## Installation

<CodeGroup>
  ```bash Recommended theme={null}
  pip install -e ".[all]"
  ```
</CodeGroup>

## Quick Start

### Option 1: Web UI (Recommended)

A browser-based interface for the full training pipeline — upload data, configure training, and view results without writing code.

```bash theme={null}
# Launch
reverie ui
```

Opens at [http://127.0.0.1:7860](http://127.0.0.1:7860). Customize host and port with `--host` and `--port`:

```bash theme={null}
reverie ui --host 0.0.0.0 --port 8000
```

<Note>
  The Web UI requires foundation model dependencies to run training. Install with `pip install -e ".[all]"` for both UI and model support.
</Note>

### Option 2: CLI

```bash theme={null}
reverie train \
    --model standard-model \
    --data ./data/synthetic_data.parquet \
    --labels ./data/synthetic_labels.csv \
    --label-column label \
    --output ./results
```

<Note>
  Use the Web UI for your first run. Use the CLI when you want reproducible runs in scripts.
</Note>