V2 payload

setInput(event.target.value)} className="w-full min-h-[460px] resize-y border-0 bg-zinc-50 dark:bg-[#0d1117] p-4 text-[13px] leading-relaxed text-zinc-700 dark:text-zinc-300 outline-none" style={{
    fontFamily: 'ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, monospace'
  }} spellCheck={false} />
          {state.error && <div role="alert" className="mx-4 mb-4 rounded-md border border-red-200 bg-red-50 px-3 py-2 text-xs text-red-700 dark:border-red-800 dark:bg-red-950/40 dark:text-red-300">
              Invalid JSON: {state.error}
            </div>}
          <details className="border-t border-zinc-200 dark:border-zinc-800">
            <summary className="cursor-pointer px-4 py-3 text-xs font-medium text-zinc-600 dark:text-zinc-400 hover:text-zinc-900 dark:hover:text-zinc-200">
              V2 payload with defaults applied
            </summary>
            <pre className="m-0 max-h-[360px] overflow-auto whitespace-pre-wrap px-4 pb-4 text-[12px] leading-relaxed text-zinc-700 dark:text-zinc-300" style={{
    fontFamily: 'ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, monospace'
  }}>
              {state.filled ? JSON.stringify(state.filled, null, 2) : ''}
            </pre>
          </details>
        </div>
        <div className="bg-zinc-50 dark:bg-[#0d1117]">
          <div className="px-4 py-2 bg-zinc-100 dark:bg-zinc-900 border-b border-zinc-200 dark:border-zinc-800 flex items-center justify-between">
            <div className="flex items-center gap-2">
              <div className="flex gap-1.5">
                <div className="w-3 h-3 rounded-full bg-[#ff5f56]" />
                <div className="w-3 h-3 rounded-full bg-[#ffbd2e]" />
                <div className="w-3 h-3 rounded-full bg-[#27c93f]" />
              </div>
              <span className="text-xs text-zinc-500 ml-2 font-medium">V3 payload</span>
            </div>
            <button type="button" onClick={copyOutput} disabled={!outputText} className={`rounded-md border px-2.5 py-1 text-xs transition disabled:cursor-not-allowed disabled:opacity-50 ${copyStatus === 'error' ? 'border-red-300 text-red-700 hover:bg-red-50 dark:border-red-700 dark:text-red-300 dark:hover:bg-red-950/40' : 'border-zinc-300 text-zinc-700 hover:bg-zinc-200 dark:border-zinc-700 dark:text-zinc-300 dark:hover:bg-zinc-800 dark:hover:text-white'}`}>
              {copyStatus === 'success' ? 'Copied' : copyStatus === 'error' ? 'Copy failed' : 'Copy'}
            </button>
          </div>
          {state.warnings.length > 0 && <div role="status" className="m-3 rounded-md border border-amber-200 bg-amber-50 px-3 py-2 text-xs text-amber-800 dark:border-amber-800 dark:bg-amber-950/40 dark:text-amber-200">
              <strong>Warnings</strong>
              <ul className="my-1.5 list-disc space-y-1 pl-4">{state.warnings.map(warning => <li key={warning}>{warning}</li>)}</ul>
            </div>}
          <pre className="m-0 min-h-[460px] overflow-auto whitespace-pre-wrap p-4 text-[13px] leading-relaxed text-zinc-700 dark:text-zinc-300" style={{
    fontFamily: 'ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, monospace'
  }} dangerouslySetInnerHTML={{
    __html: highlight(outputText)
  }} />
        </div>
      </div>
    </div>;
};

Every Reducto endpoint exposes configuration options that control how documents are processed. This section covers all available configurations, from parse-level OCR and layout settings through extraction schemas and workflow orchestration.

## Configuration by Endpoint

<Tabs>
  <Tab title="Parse">
    Parse converts documents into structured content. Options are grouped by purpose:

| Group         | Purpose                           | Pages                                                                                                                     |
    | ------------- | --------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
    | `enhance`     | AI-powered accuracy               | [Agentic Modes](/configs/parse/agentic-modes), [Chart Extraction](/configs/parse/chart-extraction)                        |
    | `retrieval`   | RAG optimization                  | [Chunking Methods](/configs/parse/chunking-methods)                                                                       |
    | `formatting`  | Detecting styling & output format | [Table Formats](/configs/parse/table-output-formats), [Additional Document Data](/configs/parse/additional-document-data) |
    | `spreadsheet` | Excel/CSV handling                | [Spreadsheet Processing](/configs/parse/spreadsheet)                                                                      |
    | `settings`    | Processing controls               | [Processing Settings](/configs/parse/ocr-settings), [Page Ranges](/configs/parse/page-ranges)                             |

```python theme={null}
    result = client.parse.run(
        input=upload,
        enhance={...},
        retrieval={...},
        formatting={...},
        spreadsheet={...},
        settings={...}
    )
    ```
  </Tab>

<Tab title="Extract">
    Extract pulls structured data from documents using a JSON schema.

| Group          | Purpose                     | Pages                                                                                          |
    | -------------- | --------------------------- | ---------------------------------------------------------------------------------------------- |
    | `instructions` | Schema and system prompt    | (base config)                                                                                  |
    | `settings`     | Citations, array extraction | [Array Extraction](/configs/extract/array-extraction), [Citations](/configs/extract/citations) |
    | `parsing`      | Document processing         | All Parse options                                                                              |

```python theme={null}
    result = client.extract.run(
        input=upload,
        instructions={"schema": {...}, "system_prompt": "..."},
        settings={"deep_extract": True, "citations": {"enabled": True}},
        parsing={...}
    )
    ```
  </Tab>

<Tab title="Split">
    Split divides documents into logical sections.

| Group               | Purpose                | Pages                                               |
    | ------------------- | ---------------------- | --------------------------------------------------- |
    | `split_description` | Section definitions    | [Split Configuration](/configs/split/configuration) |
    | `split_rules`       | Splitting logic prompt | [Split Configuration](/configs/split/configuration) |
    | `settings`          | Table handling         | [Split Configuration](/configs/split/configuration) |
    | `parsing`           | Document processing    | All Parse options                                   |

```python theme={null}
    result = client.split.run(
        input=upload,
        split_description=[{"name": "...", "description": "..."}],
        split_rules="...",
        settings={"table_cutoff": "truncate"}
    )
    ```
  </Tab>

<Tab title="Classify">
    Classify determines document type based on natural language criteria.

| Group                   | Purpose               | Pages                                                     |
    | ----------------------- | --------------------- | --------------------------------------------------------- |
    | `classification_schema` | Category definitions  | [Classify Configuration](/configs/classify/configuration) |
    | `page_range`            | Pages used as context | [Classify Configuration](/configs/classify/configuration) |

```python theme={null}
    response = client.classify.run(
        input=upload,
        classification_schema=[
            {"category": "invoice", "criteria": ["billing info", "itemized charges"]},
            {"category": "contract", "criteria": ["legal terms", "signatures"]},
        ]
    )
    ```
  </Tab>

<Tab title="Edit">
    Edit fills forms and modifies documents.

| Option              | Purpose                       | Pages                                    |
    | ------------------- | ----------------------------- | ---------------------------------------- |
    | `edit_instructions` | Natural language instructions | (base config)                            |
    | `form_schema`       | Pre-defined field locations   | [Form Schema](/configs/edit/form-schema) |
    | `edit_options`      | Highlight color, overflow     | (base config)                            |

```python theme={null}
    result = client.edit.run(
        document_url=upload,
        edit_instructions="Fill name: John Doe, date: 2024-01-15",
        form_schema=[...],
        edit_options={"color": "#FF0000"}
    )
    ```
  </Tab>
</Tabs>

## Common Patterns

<AccordionGroup>
  <Accordion title="RAG-optimized parsing" icon="magnifying-glass">
    Variable chunking with embedding optimization for vector search:

```python theme={null}
    result = client.parse.run(
        input=upload,
        retrieval={
            "chunking": {"chunk_mode": "variable", "chunk_size": 1000},
            "embedding_optimized": True
        },
        formatting={"table_output_format": "dynamic"}
    )
    ```
  </Accordion>

<Accordion title="High-accuracy processing" icon="bullseye">
    Enable agentic mode for both text and tables:

```python theme={null}
    result = client.parse.run(
        input=upload,
        enhance={
            "agentic": [{"scope": "text"}, {"scope": "table"}]
        }
    )
    ```
  </Accordion>

<Accordion title="Complete extraction with citations" icon="quote-left">
    Deep Extract with source locations for long or complex documents (higher cost/latency):

```python theme={null}
    result = client.extract.run(
        input=upload,
        instructions={"schema": schema},
        settings={
            "deep_extract": True,
            "citations": {"enabled": True}
        }
    )
    ```
  </Accordion>
</AccordionGroup>

## Migrating from v2

If you're using the legacy configuration format, use this converter to transform your v2 config to v3:

See the [Migration Guide](/v/legacy/migration-guide) for complete mapping tables and examples.