Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import requests
-import json
 import os
+import json
 
 # API and environment variables
 API_KEY = os.getenv('API_KEY')
@@ -19,7 +19,7 @@ BASE_SYSTEM_MESSAGE = "I carefully provide accurate, factual, thoughtful, nuance
 def call_nvidia_api(history, system_message, max_tokens, temperature, top_p):
     """Calls the NVIDIA API to generate a response."""
     messages = [{"role": "system", "content": system_message}]
-    messages.extend([{"role": "user", "content": h[0]} for h in history])
+    messages.extend([{"role": "user", "content": msg} for msg, _ in history])
 
     payload = {
         "messages": messages,
@@ -28,7 +28,6 @@ def call_nvidia_api(history, system_message, max_tokens, temperature, top_p):
         "max_tokens": max_tokens,
         "stream": False
     }
-    print(f"Payload enviado: {json.dumps(payload, indent=2)}")
     session = requests.Session()
     response = session.post(INVOKE_URL, headers=headers, json=payload)
     while response.status_code == 202:
@@ -37,28 +36,25 @@ def call_nvidia_api(history, system_message, max_tokens, temperature, top_p):
         response = session.get(fetch_url, headers=headers)
         response.raise_for_status()
     response_body = response.json()
-    print(f"Payload recebido: {json.dumps(response_body, indent=2)}")
     if response_body.get("choices"):
         assistant_message = response_body["choices"][0]["message"]["content"]
         return assistant_message
     else:
-        return "Desculpe, ocorreu um erro ao gerar a resposta."
+        return "Sorry, there was an error generating the response."
 
 def chatbot_submit(message, chat_history, system_message, max_tokens_val, temperature_val, top_p_val):
     """Submits the user message to the chatbot and updates the chat history."""
-    print("Updating chatbot...")
-
-    # Adiciona a mensagem do usuário ao histórico para exibição
-    chat_history.append([message, ""])
+    chat_history.append([message, ""])  # Add user message to history
 
-    # Chama a API da NVIDIA para gerar uma resposta
+    # Call NVIDIA API to generate a response
     assistant_message = call_nvidia_api(chat_history, system_message, max_tokens_val, temperature_val, top_p_val)
 
-    # Atualiza o histórico com a resposta do assistente
+    # Update history with assistant's response
     chat_history[-1][1] = assistant_message
 
     return assistant_message, chat_history
 
+# Gradio interface setup
 chat_history_state = gr.State([])
 system_msg = gr.Textbox(BASE_SYSTEM_MESSAGE, label="System Message", placeholder="System prompt.", lines=5)
 max_tokens = gr.Slider(20, 1024, label="Max Tokens", step=20, value=1024)