Update main.py

main.py

@@ -1,6 +1,5 @@
 from flask import Flask, request, jsonify
 from huggingface_hub import InferenceClient
-import time
 
 # Initialize Flask app
 app = Flask(__name__)
@@ -48,22 +47,11 @@ def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, r
     )
 
     output = ""
-    complete = False
-
-    # Use a loop to ensure response is fully received
-    while not complete:
-        for token in response:
-            if hasattr(token, 'token') and hasattr(token.token, 'text'):
-                output += token.token.text
-            else:
-                print(f"Unexpected token structure: {token}", flush=True)
-
-            # Check if the response seems complete
-            if token.token.text.endswith('</s>'):
-                complete = True
-                break
-        # Introduce a delay to handle streaming responses more smoothly
-        time.sleep(0.1)
+    for token in response:
+        if hasattr(token, 'token') and hasattr(token.token, 'text'):
+            output += token.token.text
+        else:
+            print(f"Unexpected token structure: {token}", flush=True)
 
     # Print AI response
     print(f"\nSema AI: {output}\n", flush=True)
@@ -95,4 +83,4 @@ def generate_text():
         return jsonify({"error": str(e)}), 500
 
 if __name__ == "__main__":
-    app.run(debug=True, port=5000)
+    app.run(debug=True, port=5000)