added more workers

Dockerfile

@@ -25,4 +25,4 @@ RUN chown -R user:user /app
 # Switch to the new user
 USER user
 
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "4"]

test.py

@@ -103,16 +103,20 @@ test_texts = [
     "For my number, follow the clues hidden in Da Vinci's most famous painting."
 
 ]
+import time
 
 url = "https://vidhitmakvana1-contact-sharing-recognizer-api.hf.space/detect_contact"
 
 async def process_text(session, text):
     payload = {"text": text}
     headers = {"Content-Type": "application/json"}
-    
+
+    start_time = time.time()
     async with session.post(url, data=json.dumps(payload), headers=headers) as response:
         if response.status == 200:
             result = await response.json()
+            end_time = time.time()
+            result['response_time'] = end_time - start_time
             return result
         else:
             print(f"Error for text: {text}")
@@ -124,23 +128,30 @@ async def main():
     async with aiohttp.ClientSession() as session:
         tasks = [process_text(session, text) for text in test_texts]
         results = await tqdm.gather(*tasks)
-    
+
     correct_predictions = 0
     total_predictions = len(results)
-    
+    total_response_time = 0
+
     for text, result in zip(test_texts, results):
         if result:
             print(f"Text: {result['text']}")
             print(f"Contact Probability: {result['contact_probability']:.4f}")
             print(f"Is Contact Info: {result['is_contact_info']}")
+            print(f"Response Time: {result['response_time']:.4f} seconds")
             print("---")
-            
+        
             # Assuming all texts in test_texts are actually contact information
             if result['is_contact_info']:
                 correct_predictions += 1
-    
+        
+            total_response_time += result['response_time']
+
     accuracy = correct_predictions / total_predictions
+    average_response_time = total_response_time / total_predictions
     print(f"Accuracy: {accuracy:.2f}")
+    print(f"Average Response Time: {average_response_time:.4f} seconds")
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    while True:
+        asyncio.run(main())