Quickstart

import requests

# Make prediction request
with open('your_image.jpg', 'rb') as f:
    response = requests.post(
        'http://localhost:8000/predict/detectron2/mask_rcnn_R_50_FPN_3x',
        files={'file': f}
    )

# Parse results
detections = response.json()
print(f"Found {len(detections)} objects")

for det in detections:
    print(f"  - {det['class_name']}: {det['confidence']:.2f}")

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

const response = await fetch(
  'http://localhost:8000/predict/detectron2/mask_rcnn_R_50_FPN_3x',
  {
    method: 'POST',
    body: formData
  }
);

const detections = await response.json();
console.log(`Found ${detections.length} objects`);

from mozo import ModelManager
import cv2

manager = ModelManager()
model = manager.get_model('easyocr', 'english-light')

image = cv2.imread('document.jpg')
results = model.predict(image)

for item in results.detections:
    print(f"Text: {item.text}")
    print(f"Confidence: {item.confidence:.2%}")

from mozo import ModelManager
import cv2

manager = ModelManager()
model = manager.get_model('depth_anything', 'small')

image = cv2.imread('scene.jpg')
depth_map = model.predict(image)

# depth_map is a PIL Image
depth_map.save('depth_output.png')
depth_map.show()

from mozo import ModelManager
import cv2

manager = ModelManager()
model = manager.get_model('qwen2.5_vl', '7b-instruct')

image = cv2.imread('image.jpg')
result = model.predict(
    image,
    prompt="What objects are visible in this image?"
)

print(result['text'])