Create app.py

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+
+# Pegando o token da Hugging Face do ambiente
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+# Inicializando o cliente de inferência
+client = InferenceClient(
+    provider="sambanova",
+    api_key=HF_TOKEN,
+)
+
+def chatbot_response(user_input):
+    messages = [{"role": "user", "content": user_input}]
+    
+    try:
+        completion = client.chat.completions.create(
+            model="meta-llama/Llama-3.3-70B-Instruct", 
+            messages=messages, 
+            max_tokens=500,
+        )
+        return completion.choices[0].message['content']
+    except Exception as e:
+        return f"Erro ao gerar resposta: {str(e)}"
+
+# Criando interface Gradio
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🤖 Llama-70B Chatbot - SambaNova")
+    
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Digite sua mensagem aqui...")
+    btn = gr.Button("Enviar")
+    
+    def respond(message, chat_history):
+        response = chatbot_response(message)
+        chat_history.append((message, response))
+        return "", chat_history
+    
+    btn.click(respond, [msg, chatbot], [msg, chatbot])
+
+# Rodando a aplicação
+if __name__ == "__main__":
+    demo.launch()