zsxkib / dolphin
(Updated 3 weeks, 2 days ago)
- Public
- 0 runs
Run zsxkib/dolphin with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| image |
string
|
Input document image to parse (JPG, JPEG, PNG formats supported).
|
|
| parsing_level |
string
(enum)
|
page
Options: page, element |
Parsing level: 'page' for full document analysis, or 'element' for specific element parsing.
|
| element_type |
string
(enum)
|
text
Options: text, table, formula |
Type of element if parsing_level is 'element'. Choose from 'text', 'table', 'formula'. Ignored if parsing_level is 'page'.
|
| max_batch_size |
integer
|
16
Min: 1 |
Maximum number of document elements to parse in a single batch (primarily relevant for 'page' parsing).
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Input document image to parse (JPG, JPEG, PNG formats supported)."
},
"element_type": {
"enum": [
"text",
"table",
"formula"
],
"type": "string",
"title": "element_type",
"description": "Type of element if parsing_level is 'element'. Choose from 'text', 'table', 'formula'. Ignored if parsing_level is 'page'.",
"default": "text",
"x-order": 2
},
"parsing_level": {
"enum": [
"page",
"element"
],
"type": "string",
"title": "parsing_level",
"description": "Parsing level: 'page' for full document analysis, or 'element' for specific element parsing.",
"default": "page",
"x-order": 1
},
"max_batch_size": {
"type": "integer",
"title": "Max Batch Size",
"default": 16,
"minimum": 1,
"x-order": 3,
"description": "Maximum number of document elements to parse in a single batch (primarily relevant for 'page' parsing)."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "object",
"title": "DolphinOutput",
"properties": {
"json_content": {
"type": "object",
"title": "Json Content"
},
"text_content": {
"type": "string",
"title": "Text Content"
},
"markdown_content": {
"type": "string",
"title": "Markdown Content"
}
},
"description": "Output model for DOLPHIN document parsing results.\n\nWhen using page-level parsing, the API returns both structured JSON data\nand formatted Markdown content. For element-level parsing, it returns\nthe extracted text content directly."
}