Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-def respond(message, history, system_message, max_tokens, temperature, top_p, hf_token: gr.OAuthToken):
+def respond(message, history, system_message, max_tokens, temperature, top_p, hf_token):
     # Inicializa os 3 clientes
-    client_main = InferenceClient(token=hf_token.token, model="meta-llama/Llama-3.1-8B-Instruct")
-    client_aux1 = InferenceClient(token=hf_token.token, model="google/flan-t5-large")
-    client_aux2 = InferenceClient(token=hf_token.token, model="facebook/bart-large-cnn")
+    client_main = InferenceClient(token=hf_token, model="meta-llama/Llama-3.1-8B-Instruct")
+    client_aux1 = InferenceClient(token=hf_token, model="google/flan-t5-large")
+    client_aux2 = InferenceClient(token=hf_token, model="facebook/bart-large-cnn")
 
     # Histórico e system message
     messages = [{"role": "system", "content": system_message}]
@@ -21,12 +21,11 @@ def respond(message, history, system_message, max_tokens, temperature, top_p, hf
     # Passo 3: Aux2
     response_aux2 = client_aux2.text_generation(inputs=response_aux1, max_new_tokens=max_tokens)
 
-    # Retorna resposta final
     return response_aux2
 
 # Interface Gradio
 chatbot = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(1, 2048, 512, label="Max new tokens"),
@@ -35,10 +34,7 @@ chatbot = gr.ChatInterface(
     ],
 )
 
-
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
     chatbot.render()
 
 if __name__ == "__main__":