Update app.py

app.py

@@ -4,40 +4,28 @@ from huggingface_hub import InferenceClient
 """
 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("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("susanazhou/our.modelo_final")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Función para generar respuesta usando text_generation
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Arma el prompt incluyendo sistema, historial y nuevo mensaje
+    prompt = system_message + "\n"
+    for user_input, assistant_response in history:
+        prompt += f"Usuario: {user_input}\nAsistente: {assistant_response}\n"
+    prompt += f"Usuario: {message}\nAsistente:"
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Llama a la API de Hugging Face para generar texto
+    response = client.text_generation(
+        prompt=prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    # Extrae solo la parte generada (quita el prompt original)
+    generated_text = response.generated_text[len(prompt):]
+    return generated_text
 
 
 
@@ -87,16 +75,15 @@ with gr.Blocks() as demo:
 
     with gr.Tab("Chatbot LeIA GO"):
         gr.ChatInterface(
-            respond,
+            fn=respond,
             additional_inputs=[
-                gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+                gr.Textbox(value="Eres una asistente lingüística especializada en español regional.", 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)"),
             ],
         )
 
+# Lanza la app
 if __name__ == "__main__":
     demo.launch()
-
-