Update app.py

app.py

@@ -6,7 +6,6 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 client = InferenceClient("BSC-LT/ALIA-40b")
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,31 +14,27 @@ 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]})
+    prompt = f"{system_message}\n"
 
-    messages.append({"role": "user", "content": message})
+    for user_input, bot_response in history:
+        prompt += f"User: {user_input}\nAssistant: {bot_response}\n"
+    
+    prompt += f"User: {message}\nAssistant:"
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    for message in client.text_generation(
+        prompt=prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        response += message
         yield response
 
 
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """