Update app.py

app.py

@@ -116,23 +116,22 @@ def retrieve_context(query, max_results=6, max_chars=600):
         return []
 
 def format_conversation(history, system_prompt, tokenizer):
+    if history is None:
+        history = []
+        
     if hasattr(tokenizer, "chat_template") and tokenizer.chat_template:
-        if len(history) > 0:
-            messages = [{"role": "system", "content": system_prompt.strip()}] + history
-        else:
-            messages = [{"role": "system", "content": system_prompt.strip()}]
+        messages = [{"role": "system", "content": system_prompt.strip()}] + history
         return tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
     else:
         # Fallback for base LMs without chat template
         prompt = system_prompt.strip() + "\n"
-        if len(history) > 0:
-            for msg in history:
-                if msg['role'] == 'user':
-                    prompt += "User: " + msg['content'].strip() + "\n"
-                elif msg['role'] == 'assistant':
-                    prompt += "Assistant: " + msg['content'].strip() + "\n"
-            if not prompt.strip().endswith("Assistant:"):
-                prompt += "Assistant: "
+        for msg in history:
+            if msg['role'] == 'user':
+                prompt += "User: " + msg['content'].strip() + "\n"
+            elif msg['role'] == 'assistant':
+                prompt += "Assistant: " + msg['content'].strip() + "\n"
+        if not prompt.strip().endswith("Assistant:"):
+            prompt += "Assistant: "
         return prompt
 
 def chat_response(user_msg, chat_history, system_prompt,
@@ -177,15 +176,7 @@ def chat_response(user_msg, chat_history, system_prompt,
             enriched = system_prompt
 
         pipe = load_pipeline(model_name)
-
-        # TODO:
-        debug += "\nLOAD MODEL:\n" + model_name
         prompt = format_conversation(history, enriched, pipe["tokenizer"])
-
-
-        # TODO:
-        debug += "\nPROMPT:\n" + prompt
-
         prompt_debug = f"\n\n--- Prompt Preview ---\n```\n{prompt}\n```"
         streamer = TextIterStreamer(pipe["tokenizer"],
                                         skip_prompt=True,
@@ -218,9 +209,6 @@ def chat_response(user_msg, chat_history, system_prompt,
                 break
             text = chunk
 
-            # TODO:
-            debug += "\nRESPONSE:\n" + text
-
             # Detect start of thinking
             if not in_thought and '<think>' in text:
                 in_thought = True