Update app.py

app.py

@@ -1,70 +1,31 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    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
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+# Elige uno de estos modelos top (enero 2026, basados en leaderboards):
+# - Qwen/Qwen2.5-14B-Instruct → Súper inteligente, líder actual en modelos open pequeños/medianos, excelente en español.
+# - microsoft/Phi-3-mini-4k-instruct → Más ligero y rápido si quieres respuestas instantáneas.
+# - meta-llama/Llama-3.2-3B-Instruct → Bueno y rápido.
+
+client = InferenceClient(model="Qwen/Qwen2.5-14B-Instruct")  # Cambia aquí si quieres otro
+
+def chat(message, history):
+    messages = []
+    for user, assistant in history:
+        if user:
+            messages.append({"role": "user", "content": user})
+        if assistant:
+            messages.append({"role": "assistant", "content": assistant})
     messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message 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
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+    
+    response = client.chat_completion(
+        messages=messages,
+        max_tokens=1024,
+        temperature=0.7,
+    )
+    return response.choices[0].message.content
+
+gr.ChatInterface(
+    fn=chat,
+    title="Mi Chatbot con Qwen2.5 (Gratis y Potente)",
+    description="Chatbot usando Hugging Face Inference API free"
+).launch()