OCR

A paddleocr-based ocr service has been deployed in the AI Pod.

Documentation

The API of the ocr service can be accessed via .

bash

curl -X 'POST' \
    'https://ocr-ai.13gxg.heiyu.space/ocr' \
    -H 'accept: application/json' \
    -H 'Content-Type: multipart/form-data' \
    -F 'file=@ocr-4.png;type=image/png' \
    -F 'request={"max_size":1920,"overlap":100,"memory_limit_mb":1024,"det":true,"rec":true,"cls":true}'

Deploying as a Standalone

Save the following content to a docker-compose.yml file

yml

services:
  ocr:
    image: registry.lazycat.cloud/x/lzc-aipod-ocr:d81102a
    ports:
      - 3000:3000
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/health"]
      interval: 10s
      timeout: 30s
      retries: 100
      start_period: 1s

Run docker-compose up -d to start in the current directory
After startup, access http://127.0.0.1:3000/docs