Skip to main content

General OCR

API Documentation for General OCR

Extract text from an image.

http statuserror codeerror parametersdescription
200--Successful Response
400image_not_supporterror <array>image convert error
422--field required

Extract text from an image

POST https://apis.aigen.online/aiscript/general-ocr/v2

Request Body

NameTypeDescription
image*StringFull-page image or multi-page PDF encoded in base64 UTF-8 format
{
"status": "200",
"request_id": "string",
"error": [
{
"object": "error",
"code": "string",
"message": "string"
}
],
"data": [
{
"bboxes": [
{
"bbox": [
[0, 0],
[50, 0],
[50, 50],
[0, 50]
],
"bbox_norm": [
[0.1, 1],
[0.2, 0.3],
[0.5, 0.5],
[0.5, 0.5]
],
"char_pos_norm": [0.01, 0.03, 0.05],
"text": "548 9",
"confidence": 0.99875
}
],
"text_page": "123 abc\n",
"page": 1,
"max_page": 5
}
]
}
import requests

api = "https://apis.aigen.online/aiscript/general-ocr/v2"
headers = {"x-aigen-key": "<key>"}
data = {"image": "<base64_string>"}

res = requests.post(api, json=data, headers=headers)
print(res.json())