Update app.py

app.py

@@ -1,54 +1,70 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain.chat_models import init_chat_model
+from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 
-"""
-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")
+# gradio_app.py
+from dotenv import load_dotenv # <--- Añade esta línea
+import os # <--- Añade esta línea
 
+# Carga las variables de entorno desde el archivo .env (y estas dos líneas)
+load_dotenv()
+os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# ... el resto de tus importaciones y tu código ...
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+model = init_chat_model("gemini-2.0-flash", model_provider="google_genai")
+# ... tu código existente ...
 
-    messages.append({"role": "user", "content": message})
+model = init_chat_model("gemini-2.0-flash", model_provider="google_genai")
+
+
+def respond(
+    user_input: str,
+    dialog_history: list[dict],
+    system_message: str,
+    max_new_tokens: int,
+    temperature: float,
+    top_p: float,
+) -> str:
+    """
+    Respond to user input using the model.
+    """
+    # Set the model parameters
+    model.temperature = temperature
+    model.max_output_tokens = max_new_tokens
+    model.top_p = top_p
 
-    response = ""
+    history_langchain_format = []
+    # Add the dialog history to the history
+    for msg in dialog_history:
+        if msg['role'] == "user":
+            history_langchain_format.append(
+                HumanMessage(content=msg['content']))
+        elif msg['role'] == "assistant":
+            history_langchain_format.append(AIMessage(content=msg['content']))
 
-    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
+    # Combine the system message, history, and user input into a single list
+    model_input = [SystemMessage(content=system_message)] + \
+        history_langchain_format + [HumanMessage(content=user_input)]
 
-        response += token
-        yield response
+    response = model.invoke(model_input)
+    return response.content
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
+    type="messages",
+    # save_history=True,
     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.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,
@@ -61,4 +77,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()