total-disruption/unlimited-ocr
Public
95
runs
Run total-disruption/unlimited-ocr 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
|
Страница документа или картинка (PNG/JPEG/WebP)
|
|
| prompt |
string
|
<image>document parsing.
|
Промпт модели, должен содержать <image>
|
| resolution |
None
|
gundam
|
Режим картинки
|
| max_length |
integer
|
32768
Min: 1024 Max: 32768 |
Лимит длины (промпт + ответ) в токенах
|
| no_repeat_ngram_size |
integer
|
35
|
Запрет повтора n-грамм такой длины (0 — выкл.)
|
| ngram_window |
integer
|
128
|
Окно поиска повторов в токенах
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "\u0421\u0442\u0440\u0430\u043d\u0438\u0446\u0430 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0430 \u0438\u043b\u0438 \u043a\u0430\u0440\u0442\u0438\u043d\u043a\u0430 (PNG/JPEG/WebP)"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "<image>document parsing.",
"x-order": 1,
"description": "\u041f\u0440\u043e\u043c\u043f\u0442 \u043c\u043e\u0434\u0435\u043b\u0438, \u0434\u043e\u043b\u0436\u0435\u043d \u0441\u043e\u0434\u0435\u0440\u0436\u0430\u0442\u044c <image>"
},
"max_length": {
"type": "integer",
"title": "Max Length",
"default": 32768,
"maximum": 32768,
"minimum": 1024,
"x-order": 3,
"description": "\u041b\u0438\u043c\u0438\u0442 \u0434\u043b\u0438\u043d\u044b (\u043f\u0440\u043e\u043c\u043f\u0442 + \u043e\u0442\u0432\u0435\u0442) \u0432 \u0442\u043e\u043a\u0435\u043d\u0430\u0445"
},
"resolution": {
"enum": [
"gundam",
"base"
],
"type": "string",
"title": "resolution",
"description": "\u0420\u0435\u0436\u0438\u043c \u043a\u0430\u0440\u0442\u0438\u043d\u043a\u0438",
"default": "gundam",
"x-order": 2
},
"ngram_window": {
"type": "integer",
"title": "Ngram Window",
"default": 128,
"minimum": 0,
"x-order": 5,
"description": "\u041e\u043a\u043d\u043e \u043f\u043e\u0438\u0441\u043a\u0430 \u043f\u043e\u0432\u0442\u043e\u0440\u043e\u0432 \u0432 \u0442\u043e\u043a\u0435\u043d\u0430\u0445"
},
"no_repeat_ngram_size": {
"type": "integer",
"title": "No Repeat Ngram Size",
"default": 35,
"minimum": 0,
"x-order": 4,
"description": "\u0417\u0430\u043f\u0440\u0435\u0442 \u043f\u043e\u0432\u0442\u043e\u0440\u0430 n-\u0433\u0440\u0430\u043c\u043c \u0442\u0430\u043a\u043e\u0439 \u0434\u043b\u0438\u043d\u044b (0 \u2014 \u0432\u044b\u043a\u043b.)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output"
}