OCR Recognition

Short description: Use the OCR API to recognize text in an image and return structured text output.

---

Overview

• Method: POST
• Path: /task/gi/ocr
• Content-Type: multipart/form-data

Authentication

• Header: Authorization: Bearer <token>

---

Request Example

Form Parameters

Parameter	Type	Required	Description
image	file	Yes	The source image file to be processed by OCR

---

curl Example

curl -X POST "https://api.gpt.ge/task/gi/ocr" \
  -H "Authorization: Bearer sk-xxxx" \
  -F "image=@/path/to/image.png"

JavaScript (fetch) Example

const formData = new FormData();
formData.append('image', fileInput.files[0]);

fetch('https://api.gpt.ge/task/gi/ocr', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxx'
  },
  body: formData
}).then(r => r.json()).then(console.log);

Python (requests) Example

import requests

url = 'https://api.gpt.ge/task/gi/ocr'
headers = {
    'Authorization': 'Bearer sk-xxxx'
}
files = {
    'image': open('image.png', 'rb')
}

response = requests.post(url, headers=headers, files=files)
print(response.json())

---

Response Example (200)

{
  "text": "I am morphogen API intelligent assistant, small vv\nDo you need my help?"
}

Note: This endpoint requires multipart/form-data upload of the image file. The response contains a single text field with the recognized text.