Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
     message,
     history: list[dict[str, str]],
@@ -11,38 +10,33 @@ def respond(
     top_p,
     hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+    client = InferenceClient(
+        token=hf_token.token,
+        model="DeepHat/DeepHat-V1-7B"  # <-- Modelo correto
+    )
 
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
+    for msg in client.chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = msg.choices
         token = ""
-        if len(choices) and choices[0].delta.content:
+        if len(choices) and choices[0].delta and choices[0].delta.content:
             token = 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
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -65,6 +59,5 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()