test

.env

@@ -0,0 +1,5 @@
+CLOUDINARY_CLOUD_NAME="doon4qkgm"
+CLOUDINARY_API_KEY=735892612685739
+CLOUDINARY_API_SECRET=49jRAR4VWshrRAC25UaBTjmws9U
+MONGODB_URI=mongodb+srv://zuhasohail2003:[email protected]/?retryWrites=true&w=majority&appName=ImageSearchFYP
+PORT=5000

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["gunicorn", "-b", "0.0.0.0:7860", "main:app"]

main.py

@@ -0,0 +1,51 @@
+import os
+import tempfile
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+from services.db import save_image_data, find_similar_images
+from services.cloudinary import upload_to_cloudinary
+from services.feature_extraction import extract_features
+
+app = Flask(__name__)
+CORS(app, resources={r"/api/*": {"origins": "*"}},supports_credentials=True)  # Allow all origins
+
+
+
+
+@app.route("/api/search", methods=["POST"])
+def search_image():
+    file = request.files["file"]
+    
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp:
+        file.save(temp.name)
+        temp_path = temp.name
+        
+    query_features = extract_features(temp_path)
+    similar_images = find_similar_images(query_features)
+    os.remove(temp_path)
+    
+    return jsonify({
+        "similar_images": [
+            {"url": img[0], "score": round(img[1], 4)} for img in similar_images
+        ]
+    })
+
+@app.route("/api/upload", methods=["POST"])
+def upload_image():
+    file = request.files["file"]
+    
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp:
+        file.save(temp.name)
+        temp_path = temp.name
+    
+    cloud_url = upload_to_cloudinary(temp_path)
+    features = extract_features(temp_path)
+    save_image_data({"image_url": cloud_url, "features": features})
+    
+    os.remove(temp_path)
+    return jsonify({"message": "Image uploaded", "url": cloud_url})
+
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 5000))
+    app.run(host="0.0.0.0", port=port)

requirements.txt

@@ -0,0 +1,21 @@
+blinker==1.9.0
+certifi==2025.1.31
+click==8.1.8
+cloudinary==1.43.0
+colorama==0.4.6
+dnspython==2.7.0
+faiss-cpu==1.10.0
+Flask==3.1.0
+flask-cors==5.0.1
+gunicorn==23.0.0
+Jinja2==3.1.6
+MarkupSafe==2.1.5
+numpy==2.0.2
+pillow==11.0.0
+pymongo==4.11.3
+python-dotenv==1.0.1
+torch==2.6.0
+torchvision==0.21.0
+tqdm==4.67.1
+urllib3==2.3.0
+Werkzeug==3.1.3

services/cloudinary.py

@@ -0,0 +1,15 @@
+import cloudinary
+import cloudinary.uploader
+from config import config
+from config.config import CLOUDINARY_CLOUD_NAME, CLOUDINARY_API_KEY, CLOUDINARY_API_SECRET
+
+print("🚀 Cloudinary setup successful", CLOUDINARY_CLOUD_NAME)
+cloudinary.config(
+    cloud_name=CLOUDINARY_CLOUD_NAME,
+    api_key=CLOUDINARY_API_KEY,
+    api_secret=CLOUDINARY_API_SECRET
+)
+
+def upload_to_cloudinary(image_path):
+    response = cloudinary.uploader.upload(image_path)
+    return response["secure_url"]

services/db.py

@@ -0,0 +1,30 @@
+
+from pymongo import MongoClient
+from config.config import MONGODB_URI
+import numpy as np
+
+
+client = MongoClient(MONGODB_URI)
+db = client["image_search"]
+collection = db["images"]
+
+def save_image_data(image_data):
+    collection.insert_one(image_data)
+
+def get_all_images():
+    return list(collection.find({}, {"_id": 0}))
+
+def cosine_similarity(vec1, vec2):
+    """Computes cosine similarity between two vectors."""
+    return np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))
+
+def find_similar_images(query_vector, top_n=5):
+    """Finds top N similar images based on cosine similarity."""
+    images = get_all_images()
+    
+    similarities = [
+        (image["image_url"], cosine_similarity(query_vector, image["features"]))
+        for image in images
+    ]
+
+    return sorted(similarities, key=lambda x: x[1], reverse=True)[:top_n]

services/feature_extraction.py

@@ -0,0 +1,30 @@
+
+import torch
+import torchvision.models as models
+import torchvision.transforms as transforms
+from PIL import Image
+
+# Load Pretrained ResNet-50 Model
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = models.resnet50(pretrained=True).to(device)
+model.eval()
+
+# Remove the last fully connected layer
+model = torch.nn.Sequential(*(list(model.children())[:-1]))
+
+# Define Preprocessing Transform
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+
+def extract_features(image_path):
+    """Extracts ResNet feature vector from an image."""
+    image = Image.open(image_path).convert("RGB")
+    image = transform(image).unsqueeze(0).to(device)
+
+    with torch.no_grad():
+        features = model(image).squeeze()
+    
+    return features.cpu().numpy().flatten().tolist()  # Convert tensor to list