Update app.py

app.py

@@ -4,7 +4,7 @@ from huggingface_hub import InferenceClient
 
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,  
     system_message,
     max_tokens,
     temperature,
@@ -12,40 +12,44 @@ def respond(
     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
+    Função de resposta usando Hugging Face Inference API.
     """
+    # Use o token diretamente se estiver testando localmente
     client = InferenceClient(token=hf_token.token, model="apple/FastVLM-7B")
 
+
     messages = [{"role": "system", "content": system_message}]
-    messages.extend(history)
+
+
+    if history:
+        for h in history:
+   
+            if isinstance(h, tuple) and len(h) == 2:
+                user_msg, bot_msg = h
+                messages.append({"role": "user", "content": user_msg})
+                messages.append({"role": "assistant", "content": bot_msg})
+
     messages.append({"role": "user", "content": message})
 
     response = ""
 
     try:
-        for message in client.chat_completion(
+        for message_chunk in client.chat_completion(
             messages,
             max_tokens=max_tokens,
             stream=True,
             temperature=temperature,
             top_p=top_p,
         ):
-            choices = message.choices
-            token = ""
-            if len(choices) and choices[0].delta.content:
-                token = choices[0].delta.content
-
-            response += token
-            yield response
+            if hasattr(message_chunk, "choices") and message_chunk.choices:
+                delta = message_chunk.choices[0].delta
+                if delta and hasattr(delta, "content"):
+                    response += delta.content
+                    yield response
     except Exception as e:
         yield f"Erro durante a execução: {str(e)}"
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs:
-https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -53,13 +57,7 @@ chatbot = gr.ChatInterface(
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
@@ -68,6 +66,6 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()
+