first version

agent.py

@@ -1,8 +1,127 @@
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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
+import os
+from dotenv import load_dotenv
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    PythonInterpreterTool,
+    VisitWebpageTool,
+    LiteLLMModel,
+)
+from tools import (
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    get_wikipedia_summary
+)
+# Load environment variables
+load_dotenv()
+
+
+def create_gaia_agent():
+    """
+    Create a GAIA question-answering agent using Gemini API and smolagents tools
+    """
+
+    # Initialize the Gemini model
+    model = LiteLLMModel(
+        model_id="gemini/gemini-2.0-flash",
+        api_key=os.getenv("GEMINI_API_KEY")
+    )
+
+    # Initialize tools for the agent
+    tools = [
+        DuckDuckGoSearchTool(),
+        PythonInterpreterTool(),
+        VisitWebpageTool(),
+        get_wikipedia_summary,
+        multiply,
+        add,
+        subtract,
+        divide,
+        modulus
+    ]
+
+    # Create the agent with iterative decision-making capabilities
+    agent = CodeAgent(
+        tools=tools,
+        model=model
+    )
+
+    return agent
+
+
+def answer_gaia_question(agent: CodeAgent, question: str):
+    """
+    Answer a GAIA question using the agent
+
+    Args:
+        question (str): The GAIA question to answer
+
+    Returns:
+        str: The agent's answer
+    """
+
+    # Enhanced prompt for GAIA questions
+    enhanced_prompt = f"""
+    You are an expert AI assistant designed to answer complex GAIA (General AI Assistant) questions.
+    These questions often require:
+    - Multi-step reasoning
+    - Web searches for current information
+    - Mathematical calculations
+    - Data analysis
+    - Combining information from multiple sources
+
+    Question: {question}
+
+    Please approach this systematically:
+    1. Break down the question into components
+    2. Identify what information you need
+    3. Use appropriate tools to gather information
+    4. Perform any necessary calculations
+    5. Synthesize your findings into a clear answer
+
+    Make sure to:
+    - Use web search when you need current or specific information
+    - Use Python for any calculations or data processing
+    - Visit specific webpages if you need detailed information from particular sources
+    - Think step by step and show your reasoning
+
+    Provide a final, clear answer at the end.
+    """
+
+    try:
+        # Run the agent
+        result = agent.run(enhanced_prompt)
+        return result
+
+    except Exception as e:
+        return f"Error occurred while processing the question: {str(e)}"
+
+
+
+
+# Example usage for specific GAIA questions
+def example_usage():
+    """
+    Example of how to use the agent with specific GAIA questions
+    """
+
+    # Example GAIA questions (you can replace with actual ones)
+    example_questions = [
+        "What is the current population of Tokyo and how does it compare to New York City?",
+    ]
+
+    print("Running example GAIA questions:")
+    print("=" * 40)
+
+    for i, question in enumerate(example_questions, 1):
+        print(f"\nExample {i}: {question}")
+        answer = answer_gaia_question(question)
+        print(f"Answer: {answer}")
+        print("-" * 40)
+
+
+if __name__ == "__main__":
+    example_usage()

app.py

@@ -1,24 +1,27 @@
 import os
+import time
+
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
-from agent import BasicAgent
+from agent import create_gaia_agent, answer_gaia_question
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -30,7 +33,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = create_gaia_agent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -45,16 +48,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -64,18 +67,22 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
+        print("item:", item)  # Debugging: print each item
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = answer_gaia_question(agent, question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            # timeout to avoid getting rate limited by the API
+            wait_time = 60  # seconds
+            time.sleep(wait_time)
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -162,10 +169,10 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -173,14 +180,14 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)

tools.py

@@ -0,0 +1,82 @@
+from smolagents import tool
+import wikipedia
+
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+
+
+@tool
+def get_wikipedia_summary(query: str, sentences: int = 2) -> str:
+    """
+    Get a summary from Wikipedia for a given query.
+
+    Args:
+        query: The search term.
+        sentences: Number of sentences for the summary.
+
+    Returns:
+        The summary as a string.
+    """
+    try:
+        summary = wikipedia.summary(query, sentences=sentences)
+        return summary
+    except Exception as e:
+        return f"Error retrieving Wikipedia summary: {e}"
+
+
+
+