Update app.py

app.py

@@ -1,12 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("nouamanetazi/hf-ar-134000")
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,34 +11,30 @@ 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})
+    # Combine history and new message into a single prompt
+    prompt = system_message + "\n\n"
+    
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            prompt += f"User: {user_msg}\n"
+        if assistant_msg:
+            prompt += f"Assistant: {assistant_msg}\n"
+    
+    prompt += f"User: {message}\nAssistant:"
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    
+    # Use text-generation instead of chat_completion
+    for token in client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +51,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()