Update app.py

app.py

@@ -1,12 +1,25 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from dotenv import find_dotenv, load_dotenv
+from langchain.chat_models import init_chat_model
+from langchain.schema import HumanMessage, SystemMessage
+from langgraph.prebuilt import create_react_agent
+from langsmith import traceable
 
-"""
-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")
+# Load environment variables
+load_dotenv(find_dotenv())
+
+# Initialize OpenAI model
+openai_model = init_chat_model(
+    model="gpt-4.1-nano-2025-04-14",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+# Create the agent (you can add tools here later if needed)
+chat_agent = create_react_agent(openai_model, tools=[])
 
 
+@traceable
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,8 +28,44 @@ def respond(
     temperature,
     top_p,
 ):
-    # Simple modification: always respond with "haha"
-    yield "haha"
+    """
+    Main chat function that processes user input and returns AI response
+    """
+    try:
+        # Convert history to LangChain message format
+        messages = [SystemMessage(content=system_message)]
+        
+        # Add conversation history
+        for user_msg, assistant_msg in history:
+            if user_msg:
+                messages.append(HumanMessage(content=user_msg))
+            if assistant_msg:
+                messages.append(SystemMessage(content=assistant_msg))
+        
+        # Add current user message
+        messages.append(HumanMessage(content=message))
+        
+        # Prepare input for the agent
+        input_data = {"messages": messages}
+        
+        # Stream the response
+        response_text = ""
+        for chunk in chat_agent.stream(input_data, stream_mode="values"):
+            if "messages" in chunk and chunk["messages"]:
+                latest_message = chunk["messages"][-1]
+                if hasattr(latest_message, 'content'):
+                    # Extract content from the message
+                    current_content = latest_message.content
+                    if current_content and len(current_content) > len(response_text):
+                        response_text = current_content
+                        yield response_text
+        
+        # Ensure we return something even if streaming doesn't work
+        if not response_text:
+            yield "I'm sorry, I couldn't process your message. Please check your OpenAI API key."
+            
+    except Exception as e:
+        yield f"Error: {str(e)}. Please make sure your OpenAI API key is set correctly."
 
 
 """
@@ -25,7 +74,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful AI assistant. Be friendly, informative, and concise in your responses.", 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(