Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+from flask import Flask, request
 import os
 import time
 from collections import defaultdict
@@ -7,33 +8,48 @@ from collections import defaultdict
 token = os.environ["TOKEN"]
 model = os.environ["MODEL"]
 
-# Request tracking for rate limiting
+# Create Flask app
+app = Flask(__name__)
+
+# Rate-limiting configuration
+RATE_LIMIT_WINDOW = 60  # Time window in seconds
+RATE_LIMIT_REQUESTS = 5  # Max requests per user per window
+
+# Dictionary to store request logs
 request_log = defaultdict(list)
 
-def rate_limited_wrapper(*args, **kwargs):
-    user_identifier = "user_ip_placeholder"  # Replace with logic to retrieve user's IP or unique ID
+# Function to apply rate limiting
+def rate_limiter():
+    user_ip = request.remote_addr  # Retrieve the user's IP address
     current_time = time.time()
 
-    # Remove requests older than 60 seconds from the log
-    request_log[user_identifier] = [t for t in request_log[user_identifier] if current_time - t < 60]
-
-    # Check the number of requests in the last minute
-    if len(request_log[user_identifier]) >= 5:  # Example: Limit to 5 requests per minute
-        return "Rate limit exceeded. Please try again later."
+    # Clean up old requests outside the rate limit window
+    request_log[user_ip] = [
+        timestamp for timestamp in request_log[user_ip]
+        if current_time - timestamp < RATE_LIMIT_WINDOW
+    ]
 
-    # Add the current request to the log
-    request_log[user_identifier].append(current_time)
+    # Check if the user exceeded the allowed requests
+    if len(request_log[user_ip]) >= RATE_LIMIT_REQUESTS:
+        return "❌ Rate limit exceeded. Please wait and try again later."
 
-    # Forward request to the loaded model
-    return demo(*args, **kwargs)
+    # Log the current request timestamp
+    request_log[user_ip].append(current_time)
+    return None  # Indicate no rate limit violation
 
-# Load the model from Hugging Face Spaces
+# Load the Gradio model from Hugging Face Spaces
 demo = gr.load(model, src="spaces", token=token)
 
-# Launch the interface with the rate-limited wrapper
-demo.launch(
-    show_api=False,
-    show_error=False,
-    quiet=True,
-    debug=False
-)
+# Route to serve the Gradio interface with rate limiting
+@app.route("/", methods=["GET", "POST"])
+def gradio_interface():
+    # Apply rate limiting
+    rate_limit_message = rate_limiter()
+    if rate_limit_message:
+        return rate_limit_message  # Return rate limit error if exceeded
+
+    # Launch Gradio app
+    return demo.launch(prevent_thread_lock=True)
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)  # Run the Flask app