> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.
# MarkdownPage
> A visual guide to the MarkdownPage schema used for document extraction and processing.
The `MarkdownDocument` schema is the cornerstone of VLM Run's document processing system, providing a standardized, machine-readable representation of complex documents. This technical reference guide details the schema's architecture, components, and implementation patterns.
## `MarkdownDocument` Data Model
The `MarkdownDocument` schema addresses the fundamental challenges in document processing:
1. **Structural Preservation**: Maintains document hierarchy and relationships
2. **Content Extraction**: Handles mixed content types (text, tables, figures, code)
3. **Spatial Understanding**: Preserves layout and positioning information
4. **Data Integrity**: Ensures accurate representation of structured elements
5. **Extensibility**: Supports custom annotations and metadata
### 1. `MarkdownPage`
A `MarkdownDocument` is a list of `MarkdownPage` objects, each representing a page in the document.
```mermaid theme={"theme":{"light":"github-light","dark":"dark-plus"}}
classDiagram
class MarkdownPage {
PageMetadata metadata
List~Table~ tables
List~Figure~ figures
String content
}
class PageMetadata {
+String language
+Integer page_number
}
class Table {
TableMetadata metadata
List~TableHeader~ headers
List~TableRowDict~ data
BoxCoords bbox
}
class Figure {
String id
String title
String caption
BoxCoords bbox
}
MarkdownPage "1" *-- "1" PageMetadata : has
MarkdownPage "1" *-- "*" Table : has
MarkdownPage "1" *-- "*" Figure : has
%% Add rounded edges styling
classDef default fill:#f9f9f9,stroke:#333,stroke-width:2px,rx:10,ry:10
classDef relationship fill:none,stroke:#666,stroke-width:1px
```
Here's an alternative way to visualize the `MarkdownPage` schema:
| Component | Field | Type | Description |
| -------------------- | ------------------ | -------------------- | --------------------------------------- |
| **MarkdownDocument** | | | |
| | `pages` | `List[MarkdownPage]` | Pages in the document |
| **MarkdownPage** | | | |
| | `metadata` | `PageMetadata` | Metadata of the page |
| | `tables` | `List[Table]` | Tables in the page |
| | `figures` | `List[Figure]` | Figures in the page |
| | `content` | `str` | Content of the page |
| **PageMetadata** | | | |
| | `language` | `str` | Language of the document |
| | `page_number` | `int` | Page number of the document (0-indexed) |
| **Table** | | | |
| | `metadata.title` | `str` | Title of the table |
| | `metadata.caption` | `str` | Caption of the table |
| | `metadata.notes` | `str` | Notes about the table |
| | `headers.id` | `str` | Unique identifier for the header |
| | `headers.column` | `int` | Column index of the header |
| | `headers.name` | `str` | Name of the header |
| | `headers.dtype` | `str` | Data type of the header |
| | `data.*` | `dict[str, Any]` | Maps column header ids to values |
| | `bbox` | `BoxCoords` | Bounding box of the table |
| **Figure** | | | |
| | `id` | `int` | Unique identifier for the figure |
| | `title` | `str` | Title of the figure |
| | `caption` | `str` | Caption of the figure |
| | `bbox` | `BoxCoords` | Bounding box of the figure |
***
### 2. `MarkdownTable`
Tables are represented with a `` tag in the markdown content, with the actual table content stored in the `tables` list. This allows for rich representation of table's data while maintaining the document's flow.
```mermaid theme={"theme":{"light":"github-light","dark":"dark-plus"}}
classDiagram
class Table {
TableMetadata metadata
List~TableHeader~ headers
List~TableRowDict~ data
BoxCoords bbox
}
class TableMetadata {
String title
String caption
String notes
}
class TableHeader {
String id
Integer column
String name
String dtype
}
class TableRowDict {
String id
Any value
}
class BoxCoords {
List~float~ xywh
}
Table "1" *-- "1" TableMetadata: has
Table "1" *-- "*" TableHeader: has
Table "1" *-- "*" TableRowDict: has
Table "1" *-- "1" BoxCoords: has
%% Add rounded edges styling
classDef default fill:#f9f9f9,stroke:#333,stroke-width:2px,rx:10,ry:10
classDef relationship fill:none,stroke:#666,stroke-width:1px
```
### 3. Charts and Figures
Charts and figures are represented with a `` tag in the content. The chart details are stored in the `figures` list, including properties like:
## Example Usage
Here's an example of how the `MarkdownPage` model is used to process a document:
```python Python theme={"theme":{"light":"github-light","dark":"dark-plus"}}
from pathlib import Path
from vlmrun.client import VLMRun
from vlmrun.client.types import PredictionResponse, MarkdownDocument
# Initialize client
client = VLMRun(api_key="")
# Process document
response: PredictionResponse = client.document.generate(
file=Path("document.pdf"),
domain="document.markdown",
batch=True,
)
# Access processed document
doc: MarkdownDocument = client.predictions.wait(response.id, timeout=120)
print(doc.model_dump_json(indent=2))
```
## Example JSON Response
Here's an example of how the MarkdownPage schema appears in a JSON response:
```json theme={"theme":{"light":"github-light","dark":"dark-plus"}}
{
"pages": [
{ // page 0
"metadata": {
"page_number": 0
},
"tables": [
{
"metadata": {
"title": "Sample Data Table",
"caption": "Table showing example data"
},
"content": "| Header 1 | Header 2 |\n|----------|----------|\n| Data 1 | Data 2 |\n| Data 3 | Data 4 |",
"headers": [
{
"id": "h1",
"column": 0,
"name": "Header 1",
"dtype": "string"
},
...
],
"data": [
{
"h1": "Data 1",
"h2": "Data 2"
},
...
]
}
],
"figures": [
{
"id": 0,
"title": "Sample Bar Chart",
"caption": "Example visualization",
"content": "..."
}
...
],
"content": "..."
},
{ // page 1
...
},
{ // page 2
...
},
...
]
}
```