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

# Parse

> Convert documents into structured JSON with text, tables, figures, and bounding boxes.

## Overview

The Parse endpoint converts any document into structured JSON. It extracts text, tables, figures, and metadata with precise bounding boxes for every element.

**Credits:** 1 credit per page

## Basic Usage

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST "https://platform.aifano.com/parse" \
    -H "Authorization: Bearer $AIFANO_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"input": "https://example.com/report.pdf"}'
  ```

  ```python Python theme={null}
  import requests

  result = requests.post(
      "https://platform.aifano.com/parse",
      headers={"Authorization": f"Bearer {AIFANO_API_KEY}"},
      json={"input": "https://example.com/report.pdf"}
  ).json()

  for chunk in result["result"]["chunks"]:
      print(chunk["content"][:200])
  ```
</CodeGroup>

## Input Options

The `input` field accepts:

| Format           | Example                        | Description                             |
| ---------------- | ------------------------------ | --------------------------------------- |
| Public URL       | `https://example.com/doc.pdf`  | Any publicly accessible document URL    |
| Presigned URL    | `https://s3.amazonaws.com/...` | AWS S3 presigned URLs                   |
| Aifano reference | `aifano://abc123.pdf`          | File uploaded via `/upload`             |
| Job reference    | `jobid://job_abc123`           | Reuse parsed result from a previous job |

## Configuration Options

### Enhance

Use vision language models to improve accuracy for specific block types:

```json theme={null}
{
  "input": "aifano://document.pdf",
  "enhance": {
    "agentic": [
      { "scope": "table" },
      { "scope": "figure", "prompt": "Describe the chart data points" }
    ],
    "summarize_figures": true
  }
}
```

### Chunking & Retrieval

Configure how content is chunked for RAG pipelines:

```json theme={null}
{
  "input": "aifano://document.pdf",
  "retrieval": {
    "chunking": {
      "chunk_mode": "variable",
      "chunk_size": 1000
    },
    "embedding_optimized": true
  }
}
```

| Chunk Mode      | Description                           |
| --------------- | ------------------------------------- |
| `disabled`      | No chunking (default)                 |
| `variable`      | Variable-size chunks based on content |
| `section`       | One chunk per document section        |
| `page`          | One chunk per page                    |
| `block`         | One chunk per block                   |
| `page_sections` | Sections within pages                 |

### Formatting

Control output format for tables and special content:

```json theme={null}
{
  "input": "aifano://document.pdf",
  "formatting": {
    "table_output_format": "html",
    "add_page_markers": true,
    "merge_tables": true,
    "include": ["hyperlinks", "signatures"]
  }
}
```

### Settings

Fine-tune OCR and processing behavior:

```json theme={null}
{
  "input": "aifano://document.pdf",
  "settings": {
    "ocr_system": "standard",
    "extraction_mode": "hybrid",
    "page_range": { "start": 1, "end": 10 },
    "document_password": "secret123"
  }
}
```

| Setting             | Options              | Description                                               |
| ------------------- | -------------------- | --------------------------------------------------------- |
| `ocr_system`        | `standard`, `legacy` | Standard supports all languages; legacy for Germanic only |
| `extraction_mode`   | `hybrid`, `ocr`      | Hybrid combines OCR + embedded text for best accuracy     |
| `page_range`        | `{start, end}`       | Process only specific pages                               |
| `document_password` | string               | Password for encrypted PDFs                               |

## Response Structure

```json theme={null}
{
  "job_id": "job_abc123",
  "duration": 3.21,
  "usage": { "num_pages": 10, "credits": 10 },
  "result": {
    "type": "full",
    "chunks": [
      {
        "content": "# Section Title\n\nParagraph text...",
        "embed": "Section Title. Paragraph text...",
        "blocks": [
          {
            "type": "Title",
            "content": "Section Title",
            "bbox": { "left": 0.1, "top": 0.05, "width": 0.8, "height": 0.04, "page": 1 },
            "confidence": "high"
          }
        ]
      }
    ]
  }
}
```

### Block Types

| Type             | Description                    |
| ---------------- | ------------------------------ |
| `Title`          | Document or section title      |
| `Section Header` | Sub-section heading            |
| `Text`           | Body text paragraph            |
| `Table`          | Tabular data                   |
| `Figure`         | Image or chart                 |
| `List Item`      | Bulleted or numbered list item |
| `Header`         | Page header                    |
| `Footer`         | Page footer                    |
| `Page Number`    | Page number                    |
| `Key Value`      | Key-value pair                 |
| `Comment`        | Annotation or comment          |
| `Signature`      | Signature block                |

## Async Processing

For large documents, use the async variant:

```bash theme={null}
curl -X POST "https://platform.aifano.com/parse_async" \
  -H "Authorization: Bearer $AIFANO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": "aifano://large-document.pdf"}'
```

See [Async Processing](/documentation/async-processing) for details on polling and webhooks.