English | 中文

Online OCR recognition API service based on Baidu PP-OCRv6 model.

• Supports Bearer Token authentication
• Supports Docker containerized deployment
• Supports common image formats: jpg/jpeg/png/bmp/webp
• Image size limit: 10MB
• Returns JSON format recognition results

Create a compose.yaml file:

services:
  zocr:
    image: helloz/zocr
    container_name: zocr
    ports:
      - "5080:5080"
    environment:
      - ZOCR_TOKEN=your_token_here
    restart: always

Optional environment variables:

• ZOCR_WORKERS: Number of uvicorn worker processes, default 1
• ZOCR_MODEL_VERSION: OCR model version (tiny/small), default small
• ZOCR_MAX_FILE_SIZE: Maximum file size (bytes), default 10485760

Start the service:

# Start the service
docker compose up -d

Environment requirements: Python >= 3.11

# Install dependencies
pip install -r requirements.txt

# Start the service (development mode)
bash run.sh dev

Configure via environment variables. If ZOCR_TOKEN is empty, authentication is skipped:

POST /api/ocr/upload
Content-Type: multipart/form-data
Authorization: Bearer <token>

Request Parameters:

• file: Image file

GET /api/ocr/fetch?url=<image_url>
Authorization: Bearer <token>

Request Parameters:

• url: Image URL address

{
    "code": 200,
    "msg": "success",
    "data": {
        "texts": ["Recognized text 1", "Recognized text 2"],
        "scores": [0.99, 0.95],
        "boxes": [[[0,0], [100,0], [100,30], [0,30]], ...],
        "full_text": "Recognized text 1\nRecognized text 2"
    }
}

GET /api/health

# Using curl (upload file)
curl -X POST http://localhost:5080/api/ocr/upload \
  -H "Authorization: Bearer your_token" \
  -F "file=@test.jpg"

# Using curl (via URL)
curl "http://localhost:5080/api/ocr/fetch?url=https://example.com/image.jpg" \
  -H "Authorization: Bearer your_token"

• X: @xiaozblog