Update space

app.py

@@ -7,6 +7,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 client = InferenceClient("emeses/lab2_model")
 
 
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,34 +16,32 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+    # Format conversation history into a text prompt
+    prompt = f"{system_message}\n\n"
+    
+    for user_msg, assistant_msg in history:
+        prompt += f"User: {user_msg}\n"
+        if assistant_msg:
+            prompt += f"Assistant: {assistant_msg}\n"
+    
+    prompt += f"User: {message}\nAssistant:"
 
     response = ""
-
     try:
-        for chunk in client.chat_completion(
-            messages,
-            max_tokens=max_tokens,
-            stream=True,
+        # Use text_generation instead of chat_completion
+        for chunk in client.text_generation(
+            prompt,
+            max_new_tokens=max_tokens,
             temperature=temperature,
             top_p=top_p,
+            stream=True
         ):
-            # The API returns the text directly in streaming mode
             if chunk:
                 response += chunk
                 yield response
     except Exception as e:
         yield f"Error: {str(e)}"
 
-
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """