Update app.py

app.py

@@ -1,22 +1,24 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import google.generativeai as genai
+import os
+from dotenv import load_dotenv
 
-"""
-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")
+# Cargar variables de entorno
+load_dotenv()
 
+# Configurar la API de Google Gemini
+genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-
+    
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -25,40 +27,32 @@ def respond(
 
     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,
-    ):
-        token = message.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
-"""
+    # Configurar el modelo de Gemini
+    model_name = "gemini-1.5-pro"  # Ajusta el modelo según sea necesario
+    generation_config = {
+        "temperature": temperature,
+        "top_p": top_p,
+        "max_output_tokens": max_tokens,
+        "response_mime_type": "text/plain",
+    }
+    model = genai.GenerativeModel(model_name=model_name, generation_config=generation_config)
+    chat_session = model.start_chat(
+        history=messages
+    )
+    response = chat_session.send_message(message)
+    return response.text
+
+
+# Crear la interfaz de Gradio
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful assistant.", 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)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()