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

# Processing Parameters

> Configure core processing, figures, metadata, footnotes, spreadsheets, word boxes, and chunks.

Processing parameters sit on **Extract**. Configure them before the extraction runs, then reuse the resulting `extraction_id` in Schema, Tables, Split, MCP tools, or saved pipelines.

<Info>
  This page explains when to use each setting. For the full endpoint schema, see the
  [Extract API](/current/api-reference/endpoint/extract).
</Info>

## Quick Map

| Need                                                                          | Read                                                                                           | API field                                                           | Try it                                                                                                             |
| ----------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
| Steer extraction, refine tables/text/formatting/layout, or control selections | [Core Processing](/current/concepts/processing-parameters-core)                                | `refine`, `refine_prompt`, `additional_prompt`, `detect_selections` | Start with refinement off; enable only the modes you need                                                          |
| Recover native file properties and deterministic structure                    | [Document Metadata](/current/concepts/processing-parameters-document-metadata)                 | `extensions.document_metadata`                                      | Use an original PDF, Office file, or camera image                                                                  |
| Link footnote markers to their explanation text                               | [Footnote References](/current/concepts/processing-parameters-footnotes)                       | `extensions.footnote_references`                                    | [Attention Is All You Need](https://platform.runpulse.com/dashboard/examples/3be15d23-d622-4f27-9843-ec2929140eec) |
| Parse workbooks without phantom rows or hidden-sheet surprises                | [Spreadsheet Processing](/current/concepts/processing-parameters-spreadsheets)                 | `spreadsheet.*`                                                     | [Complex Table Document](https://platform.runpulse.com/dashboard/examples/0e36367a-16d2-49c8-99ab-a6fe0df70409)    |
| Validate exact word positions for review, redaction, or QA                    | [Word-Level Bounding Boxes](/current/concepts/processing-parameters-word-level-bounding-boxes) | `extensions.alt_outputs.wlbb`                                       | [Bank Statement](https://platform.runpulse.com/dashboard/examples/637e5678-30b1-45fa-acc4-877f2d636419)            |
| Prepare text for RAG, retrieval, or agent memory                              | [Chunking](/current/concepts/processing-parameters-chunking)                                   | `extensions.chunking.*`                                             | [Attention Is All You Need](https://platform.runpulse.com/dashboard/examples/3be15d23-d622-4f27-9843-ec2929140eec) |

<Tip>
  Do not enable every parameter by default. Add the settings your downstream workflow actually uses, especially for high-volume or regulated pipelines where result size, latency, and auditability matter.
</Tip>

## Parameter Guides

<CardGroup cols={2}>
  <Card title="Core Processing" icon="sliders" href="/current/concepts/processing-parameters-core">
    Configure extraction prompts, refinement modes, and selection detection.
  </Card>

  <Card title="Document Metadata" icon="file-search" href="/current/concepts/processing-parameters-document-metadata">
    Recover native properties before conversion, rendering, or OCR.
  </Card>

  <Card title="Footnote References" icon="quote-right" href="/current/concepts/processing-parameters-footnotes">
    Link footnote markers to the text they qualify.
  </Card>

  <Card title="Spreadsheet Processing" icon="file-spreadsheet" href="/current/concepts/processing-parameters-spreadsheets">
    Control hidden rows, hidden sheets, raw values, and phantom ranges.
  </Card>

  <Card title="Word-Level Bounding Boxes" icon="scan-text" href="/current/concepts/processing-parameters-word-level-bounding-boxes">
    Return exact word coordinates for review, QA, and overlays.
  </Card>

  <Card title="Chunking" icon="scissors" href="/current/concepts/processing-parameters-chunking">
    Prepare extraction output for RAG, search, agents, and review queues.
  </Card>
</CardGroup>

## Good Defaults

For self-serve exploration, start in the Platform and inspect the output tabs before saving a reusable extraction configuration.

For production, prefer:

* `async: true` for large files, multi-step workflows, and agent tools.
* `storage.enabled: true` when later Schema, Tables, or Split steps need to reuse the extraction.
* Document metadata when native file properties or deterministic file structure are needed downstream.
* Footnotes and page chunks when citations or audit trails matter.
* Word-level boxes only for workflows that actually render or validate word coordinates.
* Spreadsheet trimming for exported workbooks with inflated used ranges.

<CardGroup cols={2}>
  <Card title="Extract API" icon="brackets-curly" href="/current/api-reference/endpoint/extract">
    Full request and response fields.
  </Card>

  <Card title="Build A Platform Pipeline" icon="workflow" href="/current/platform-reference/build-first-pipeline">
    Configure, run, and reuse processing settings in the Platform.
  </Card>
</CardGroup>