Update app.py

app.py

@@ -4,129 +4,147 @@ import requests
 import pandas as pd
 from smolagents import ToolCallingAgent, tool
 from duckduckgo_search import DDGS
+import math
+import openai
 
-
-# Define a DuckDuckGo tool
+# --- Tools ---
 @tool
 def duck_search(query: str) -> str:
-    """Searches the web using DuckDuckGo for the given query and returns the top results."""
-    with DDGS() as ddgs:
-        results = ddgs.text(query, max_results=3)
-        return "\n".join([r["body"] for r in results])
+    """
+    Searches the web using DuckDuckGo and returns a short summary.
+
+    Args:
+        query: The search query string.
+
+    Returns:
+        A string summarizing the top search results.
+    """
+    try:
+        with DDGS() as ddgs:
+            results = ddgs.text(query, max_results=3)
+            summaries = [f"{r['title']}: {r['body']}" for r in results]
+            return "\n\n".join(summaries) if summaries else "No results found."
+    except Exception as e:
+        return f"Search error: {e}"
+
+@tool
+def calculator(expression: str) -> str:
+    """
+    Evaluates basic math expressions using math module.
+
+    Args:
+        expression: A math expression as a string.
 
+    Returns:
+        The result or an error message.
+    """
+    try:
+        result = eval(expression, {"__builtins__": {}}, math.__dict__)
+        return str(result)
+    except Exception as e:
+        return f"Calculation error: {e}"
 
-# Custom Agent class
-class GAIAAgent:
+# --- Agent Wrapper ---
+class WebSearchAgent:
     def __init__(self):
         self.agent = ToolCallingAgent(
             name="GAIAWebToolAgent",
             description="An agent using DuckDuckGo and calculator tools.",
             tools=[duck_search, calculator],
-            model="gpt-3.5-turbo"
+            model="gpt-3.5-turbo",  # You can use gpt-4o if you have access
+            step_limit=5,
+            system_prompt=(
+                "You're a helpful reasoning agent. Use the provided tools "
+                "to help answer the user's questions accurately."
+            ),
         )
+        print("✅ Agent initialized.")
 
     def __call__(self, question: str) -> str:
         print(f"🔍 Question: {question}")
         try:
-            return self.agent.run(
-                question,
-                step_limit=5,
-                system_prompt=(
-                    "You are a helpful reasoning agent. You can answer questions using search and calculation tools. "
-                    "Be concise and accurate. Think step by step when needed. Use DuckDuckGo for recent or factual queries."
-                )
-            )
+            return self.agent.run(question)
         except Exception as e:
             print(f"❌ Agent error: {e}")
             return f"Error: {e}"
 
-
-# Evaluation and submission code (Hugging Face GAIA integration)
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# --- Evaluation & Submission ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
     if profile:
         username = profile.username
-        print(f"User: {username}")
+        print(f"👤 User: {username}")
     else:
         return "Please login to Hugging Face.", None
 
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    questions_url = f"{DEFAULT_API_URL}/questions"
+    submit_url = f"{DEFAULT_API_URL}/submit"
+
     try:
-        agent = GAIAAgent()
+        agent = WebSearchAgent()
     except Exception as e:
         return f"Agent initialization error: {e}", None
 
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
-        questions_data = response.json()
+        questions = response.json()
+        if not questions:
+            return "No questions received.", None
     except Exception as e:
-        return f"Error fetching questions: {e}", None
+        return f"Failed to fetch questions: {e}", None
 
-    answers_payload = []
     results_log = []
+    answers_payload = []
 
-    for item in questions_data:
+    for item in questions:
         task_id = item.get("task_id")
         question = item.get("question")
         if not task_id or not question:
             continue
         try:
             answer = agent(question)
-            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
             results_log.append({"Task ID": task_id, "Question": question, "Submitted Answer": answer})
+            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
         except Exception as e:
-            results_log.append({"Task ID": task_id, "Question": question, "Submitted Answer": f"Error: {e}"})
+            error_msg = f"Agent error: {e}"
+            results_log.append({"Task ID": task_id, "Question": question, "Submitted Answer": error_msg})
 
     if not answers_payload:
-        return "No answers generated.", pd.DataFrame(results_log)
-
-    submission_data = {
-        "username": username,
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
+        return "No answers were generated.", pd.DataFrame(results_log)
 
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response = requests.post(submit_url, json={
+            "username": username.strip(),
+            "agent_code": agent_code,
+            "answers": answers_payload
+        }, timeout=60)
         response.raise_for_status()
-        result_data = response.json()
-        final_status = (
+        result = response.json()
+        status = (
             f"✅ Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Score: {result_data.get('score')}% "
-            f"({result_data.get('correct_count')}/{result_data.get('total_attempted')})\n"
-            f"Message: {result_data.get('message', '')}"
+            f"User: {result.get('username')}\n"
+            f"Score: {result.get('score', 'N/A')}% "
+            f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')} correct)\n"
+            f"Message: {result.get('message', 'No message')}"
         )
-        return final_status, pd.DataFrame(results_log)
+        return status, pd.DataFrame(results_log)
     except Exception as e:
-        return f"Submission error: {e}", pd.DataFrame(results_log)
+        return f"❌ Submission failed: {e}", pd.DataFrame(results_log)
 
-
-# Gradio UI
+# --- UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("## 🌍 GAIA Agent with Web Search & Calculator Tools")
-    gr.Markdown(
-        "1. Log in with your Hugging Face account.\n"
-        "2. Click the button to evaluate the agent on GAIA questions.\n"
-        "3. Results and score will appear below."
-    )
-
+    gr.Markdown("# 🤖 GAIA Agent with Web Search & Calculator")
     gr.LoginButton()
-    run_button = gr.Button("🔁 Run & Submit to GAIA")
-    status_output = gr.Textbox(label="Status", lines=5)
-    results_table = gr.DataFrame(label="Results")
-
-    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+    run_btn = gr.Button("Run Evaluation & Submit All Answers")
+    status_box = gr.Textbox(label="Status", lines=5)
+    result_table = gr.DataFrame(label="Agent Answers")
 
+    run_btn.click(fn=run_and_submit_all, outputs=[status_box, result_table])
 
 if __name__ == "__main__":
-    print("🚀 Launching app...")
-    demo.launch()
+    demo.launch(debug=True, share=False)