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

# Ingest

> Build or refresh a knowledge base with the CLI ingest workflow.

`ragrails ingest` runs extraction, chunking, embedding, and storage in one command.

Use it when you want the normal indexing path without managing intermediate JSON files.

## Sources

<CodeGroup>
  ```bash Documents theme={null}
  ragrails ingest --docs files/refund-policy.pdf \
    --vector-db qdrant --collection support --url http://localhost:6333

  ragrails ingest --folder files/policies \
    --vector-db qdrant --collection support --url http://localhost:6333
  ```

  ```bash Website theme={null}
  ragrails setup-url --browser chromium
  ragrails ingest --source-url https://example.com/help/refunds \
    --vector-db qdrant --collection support --url http://localhost:6333
  ```

  ```bash REST API theme={null}
  ragrails ingest --api-url https://api.example.com/refund-policy \
    --vector-db qdrant --collection support --url http://localhost:6333
  ```

  ```bash Markdown theme={null}
  ragrails ingest \
    --markdown "# Refund policy\n\nCustomers can request a refund within 30 days." \
    --vector-db qdrant --collection support --url http://localhost:6333
  ```
</CodeGroup>

## Combine Sources

```bash theme={null}
ragrails ingest \
  --docs files/handbook.pdf \
  --source-url https://example.com/docs \
  --api-url https://api.example.com/refund-policy \
  --markdown "# Manual note\n\nEscalations use the support queue." \
  --vector-db qdrant \
  --collection support \
  --url http://localhost:6333 \
  --provider voyage \
  --model voyage-3 \
  --concurrency parallel
```

`--concurrency parallel` runs independent document, URL, and API extraction groups in parallel before chunking.

## Output

```text theme={null}
Sources  : 3
Chunks   : 24
Embedded : 24
Stored   : 24
Failed   : 0
```

## Options

| Option                                                    | Default                | Description                                                      |
| --------------------------------------------------------- | ---------------------- | ---------------------------------------------------------------- |
| `--markdown`                                              | none                   | Markdown text to ingest. Repeatable.                             |
| `--docs`                                                  | none                   | Document file to parse. Repeatable.                              |
| `--folder`                                                | none                   | Folder of supported documents. Mutually exclusive with `--docs`. |
| `--source-url`                                            | none                   | URL to scrape. Repeatable.                                       |
| `--api-url`                                               | none                   | API endpoint to fetch.                                           |
| `--vector-db`                                             | `qdrant`               | `qdrant`, `qdrant_cloud`, `pinecone`, or `weaviate`.             |
| `--collection`                                            | config or none         | Collection, index, or class name.                                |
| `--url`                                                   | config or none         | Vector database URL.                                             |
| `--provider` / `--model`                                  | `voyage` / `voyage-3`  | Embedding provider and model.                                    |
| `--batch-size`                                            | `64`                   | Embedding and storage batch size.                                |
| `--chunk-size` / `--chunk-overlap` / `--min-chunk-length` | `2000` / `200` / `100` | Chunking config.                                                 |
| `--concurrency`                                           | `serial`               | `serial` or `parallel`.                                          |

## When to Use Stage Commands

Use stage commands when you need to inspect extraction output, tune chunking before embedding, persist artifacts, or review embedded JSON before storage.

<CardGroup cols={2}>
  <Card title="Extraction" icon="file-input" href="/usage/cli/extraction">Run source extraction directly.</Card>
  <Card title="Pipeline Overview" icon="route" href="/usage/cli/pipeline-overview">See all stage boundaries.</Card>
</CardGroup>