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

# Quickstart

> Deduplicate a CSV in 30 seconds, then run the full pipeline.

This page gets you from install to a deduplicated file in a couple of minutes. For a deeper tour of the headline package, see the [GoldenMatch quickstart](/docs/goldenmatch/quickstart).

## Install

<CodeGroup>
  ```bash pip theme={null}
  pip install goldenmatch
  ```

  ```bash npm theme={null}
  npm install goldenmatch
  ```
</CodeGroup>

## Deduplicate a file

The fastest path is zero-config. GoldenMatch detects column types, assigns scorers, picks a blocking strategy, and writes golden records.

```bash CLI theme={null}
goldenmatch dedupe customers.csv
```

The same in Python:

```python theme={null}
import goldenmatch as gm

result = gm.dedupe("customers.csv")
print(result)  # DedupeResult(records=5000, clusters=847, match_rate=12.0%)
result.golden.write_csv("deduped.csv")
```

And in TypeScript:

```typescript theme={null}
import { dedupe } from "goldenmatch";

const rows = [
  { id: 1, name: "John Smith", email: "john@example.com", zip: "12345" },
  { id: 2, name: "Jon Smith",  email: "john@example.com", zip: "12345" },
  { id: 3, name: "Jane Doe",   email: "jane@example.com", zip: "54321" },
];

const result = dedupe(rows, { fuzzy: { name: 0.85 }, blocking: ["zip"], threshold: 0.85 });
console.log(result.stats);
```

## Run the whole pipeline

To profile, standardize, and deduplicate in one call, use GoldenPipe. It runs GoldenCheck, conditionally routes through GoldenFlow, then deduplicates with GoldenMatch.

```bash theme={null}
pip install goldenpipe
```

```python theme={null}
import goldenpipe as gp

result = gp.run("customers.csv")
print(result.status)     # "success"
print(result.reasoning)  # why each stage ran or was skipped
```

## Optional extras

GoldenMatch ships a single core install plus opt-in extras:

```bash theme={null}
pip install goldenmatch[llm]          # Claude / OpenAI borderline scoring
pip install goldenmatch[duckdb]       # out-of-core backend
pip install goldenmatch[ray]          # distributed backend (50M+ rows)
pip install goldenmatch[web]          # localhost browser workbench
pip install goldenmatch[mcp]          # MCP server for Claude Desktop
```

Run the interactive setup wizard to configure GPU, API keys, and database connections:

```bash theme={null}
goldenmatch setup
```

<Tip>
  Try it on bundled sample data first with `goldenmatch demo`.
</Tip>

## Next steps

<CardGroup cols={2}>
  <Card title="Auto-config" icon="robot" href="/docs/goldenmatch/auto-config">
    How zero-config converges on a defensible config.
  </Card>

  <Card title="Backends and scale" icon="gauge-high" href="/docs/goldenmatch/backends-and-scale">
    Polars, DuckDB, chunked, and Ray.
  </Card>
</CardGroup>