SKU Detection Predict API

X-API-Key: your-api-key-here

{
  "success": true,
  "detections": [
    {
      "sku": "JORDINA_APPLE_500ML",
      "sku_conf": 0.94,
      "yolo_conf": 0.89,
      "bbox": [120, 45, 280, 320]
    },
    {
      "sku": "JORDINA_ORANGE_500ML",
      "sku_conf": 0.91,
      "yolo_conf": 0.87,
      "bbox": [300, 50, 460, 315]
    }
  ],
  "analysis": {
    "total": 2,
    "counts": {
      "JORDINA_APPLE_500ML": 1,
      "JORDINA_ORANGE_500ML": 1
    },
    "sos": {
      "JORDINA_APPLE_500ML": 50.0,
      "JORDINA_ORANGE_500ML": 50.0
    },
    "osa": {
      "JORDINA_APPLE_500ML": 1,
      "JORDINA_ORANGE_500ML": 1
    }
  },
  "annotated_image_base64": "/9j/4AAQSkZJRg..."
}

{
  "success": false,
  "error": "Failed to load model for category 'SNACKS' and brand 'UNKNOWN': Models directory not found"
}

{
  "gpu_status": "online",
  "gpu_endpoint": "https://...",
  "response_time_ms": 124.5
}

# Base64 encode your image
IMAGE_BASE64=$(base64 -i shelf_photo.jpg | tr -d '\n')

# Make the API request
curl -X POST 'https://api.iralpha.core88.ai/api/v1/predict' \
  -H 'Content-Type: application/json' \
  -H 'X-API-Key: your-api-key-here' \
  -d "{
    \"image\": \"$IMAGE_BASE64\",
    \"category\": \"DRINKS\",
    \"brand\": \"JORDINA\",
    \"sku_conf\": 0.5,
    \"det_conf\": 0.25,
    \"show_unknown\": false,
    \"return_annotated\": true
  }"

import requests
import base64

API_URL = "https://api.iralpha.core88.ai/api/v1/predict"
API_KEY = "your-api-key-here"

# Read and encode the shelf image
with open("shelf_photo.jpg", "rb") as f:
    image_base64 = base64.b64encode(f.read()).decode("utf-8")

# Prepare request
headers = {
    "Content-Type": "application/json",
    "X-API-Key": API_KEY,
}

payload = {
    "image": image_base64,
    "category": "DRINKS",
    "brand": "JORDINA",
    "sku_conf": 0.5,
    "det_conf": 0.25,
    "show_unknown": False,
    "return_annotated": True,
}

# Send request
response = requests.post(API_URL, json=payload, headers=headers, timeout=60)
result = response.json()

if result["success"]:
    # Print detected SKUs
    print(f"Detected {result['analysis']['total']} products:")
    for det in result["detections"]:
        print(f"  {det['sku']}  conf={det['sku_conf']:.0%}  box={det['bbox']}")

    # Print share-of-shelf
    print("\nShare of Shelf:")
    for sku, pct in result["analysis"]["sos"].items():
        if pct > 0:
            print(f"  {sku}: {pct}%")

    # Save annotated image (optional)
    if "annotated_image_base64" in result:
        img_bytes = base64.b64decode(result["annotated_image_base64"])
        with open("annotated_shelf.jpg", "wb") as f:
            f.write(img_bytes)
        print("\nAnnotated image saved to annotated_shelf.jpg")

    # Check monthly usage from response headers
    print(f"\nQuota: {response.headers.get('X-RateLimit-Used')}"
          f" / {response.headers.get('X-RateLimit-Limit')} used this month")
else:
    print(f"Error: {result['error']}")

const API_URL = "https://api.iralpha.core88.ai/api/v1/predict";
const API_KEY = "your-api-key-here";

async function classifyShelf(imageFile) {
  // Convert file to base64
  const base64 = await new Promise((resolve, reject) => {
    const reader = new FileReader();
    reader.onload = () => resolve(reader.result.split(",")[1]);
    reader.onerror = reject;
    reader.readAsDataURL(imageFile);
  });

  const response = await fetch(API_URL, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "X-API-Key": API_KEY,
    },
    body: JSON.stringify({
      image: base64,
      category: "DRINKS",
      brand: "JORDINA",
      sku_conf: 0.5,
      det_conf: 0.25,
      show_unknown: false,
      return_annotated: true,
    }),
  });

  const result = await response.json();

  if (!result.success) {
    throw new Error(result.error);
  }

  // Log detected products
  console.log(`Detected ${result.analysis.total} products`);
  result.detections.forEach((det) => {
    console.log(`  ${det.sku} — ${(det.sku_conf * 100).toFixed(0)}%`);
  });

  // Display annotated image
  if (result.annotated_image_base64) {
    const img = document.createElement("img");
    img.src = `data:image/jpeg;base64,${result.annotated_image_base64}`;
    document.body.appendChild(img);
  }

  // Check monthly quota from response headers
  console.log(
    `Quota: ${response.headers.get("X-RateLimit-Used")}` +
    ` / ${response.headers.get("X-RateLimit-Limit")} used`
  );

  return result;
}

// Usage with a file input
document.getElementById("imageInput").addEventListener("change", async (e) => {
  const result = await classifyShelf(e.target.files[0]);
  console.log("Analysis:", result.analysis);
});