Update app.py

app.py

@@ -1,13 +1,9 @@
 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
+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
 """
-
-# Replace the default model with your custom model
 client = InferenceClient("Mayank-22/Mayank-AI")
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -16,39 +12,27 @@ def respond(
     temperature,
     top_p,
 ):
-    try:
-        # Format conversation for text generation
-        formatted_prompt = f"{system_message}\n\n"
-        
-        for val in history:
-            if val[0]:
-                formatted_prompt += f"User: {val[0]}\n"
-            if val[1]:
-                formatted_prompt += f"Assistant: {val[1]}\n"
-        
-        formatted_prompt += f"User: {message}\nAssistant:"
-        
-        response = ""
-        
-        for token in client.text_generation(
-            formatted_prompt,
-            max_new_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
-            stream=True,
-            stop_sequences=["User:", "\nUser:"],
-        ):
-            if token:
-                response += token
-                yield response
-                
-    except Exception as e:
-        yield f"Error: {str(e)}. Please try again or contact support."
-
+    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})
+    response = ""
+    for message in client.chat_completion(
+        messages,
+        max_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=[
@@ -64,6 +48,5 @@ demo = gr.ChatInterface(
         ),
     ],
 )
-
-if __name__ == "__main__":
+if name == "main":
     demo.launch()