Update app.py

app.py

@@ -3,21 +3,51 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+#from tavily import TavilyClient
+from langchain_tavily import TavilySearch
+from langgraph.prebuilt import create_react_agent
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+def _set_if_undefined(var: str):
+    if not os.environ.get(var):
+        os.environ[var] = userdata.get(var)
+
+_set_if_undefined("TAVILY_API_KEY")
+_set_if_undefined("HUGGINGFACEHUB_API_TOKEN")        
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+        
+        # Generate the chat interface, including the tools
+        llm = HuggingFaceEndpoint(
+            repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+            huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
+        )
+
+        # Initialize Tavily Search Tool
+        tavily_search_tool = TavilySearch(
+            max_results=5,
+            topic="general",
+        )
+        
+        agent = create_react_agent(llm, [tavily_search_tool])
+
+#        chat = ChatHuggingFace(llm=llm, verbose=True)
+#        tools = [search_web_tool]
+#        chat_with_tools = chat.bind_tools(tools)
+        
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        answer = agent.invoke({"messages": [{"role": "user", "content": question}]})
+        print(f"Agent returning answer: {answer}")
+        return answer
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -150,6 +180,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 #        return status_message, results_df
 
 
+
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")