Update app.py

app.py

@@ -45,29 +45,31 @@ Your job:
 # Chat function (generator for streaming)
 # ----------------------------
 def generate_response(message, history):
-
     yield "🤖 Thinking..."
     time.sleep(0.5)
 
     prompt = f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n"
 
-    for user, assistant in history:
-        prompt += f"<|im_start|>user\n{user}<|im_end|>\n"
-        prompt += f"<|im_start|>assistant\n{assistant}<|im_end|>\n"
+    # Safe history handling
+    for h in history:
+        if len(h) >= 2:
+            user, assistant = h[0], h[1]
+            prompt += f"<|im_start|>user\n{user}<|im_end|>\n"
+            prompt += f"<|im_start|>assistant\n{assistant}<|im_end|>\n"
 
     prompt += f"<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n"
 
-    # Streaming tokens
     output = ""
-    for token in llm(prompt,
-                     max_tokens=2048,  # Increased limit
-                     temperature=0.2,
-                     top_p=0.9,
-                     repeat_penalty=1.1,
-                     stream=True):
+    for token in llm(
+        prompt,
+        max_tokens=2048,  # increase for longer responses
+        temperature=0.2,
+        top_p=0.9,
+        repeat_penalty=1.1,
+        stream=True
+    ):
         output += token["choices"][0]["text"]
         yield output
-
 # ----------------------------
 # Gradio UI
 # ----------------------------