gaia_sample_tasks.py

"""
GAIA Sample Tasks for Testing the AI Agent

This file contains sample tasks from the GAIA benchmark categories
to test the agent's capabilities across different skills.
"""

# Sample GAIA tasks for testing the agent
GAIA_SAMPLE_TASKS = [
    # Reasoning tasks
    {
        "category": "reasoning",
        "difficulty": "easy",
        "task": "If a train travels at 60 miles per hour, how far will it travel in 2.5 hours?"
    },
    {
        "category": "reasoning",
        "difficulty": "medium",
        "task": "A store is having a 30% off sale. If an item originally costs $85, what is the sale price? Additionally, if there's a 8% sales tax, what is the final price?"
    },
    {
        "category": "reasoning",
        "difficulty": "hard",
        "task": "In a class of 30 students, 40% are boys. If 3 more girls join the class, what percentage of the class will be boys?"
    },
    
    # Web search and information retrieval tasks
    {
        "category": "web_search",
        "difficulty": "easy",
        "task": "What is the capital of Japan and what is its population?"
    },
    {
        "category": "web_search",
        "difficulty": "medium",
        "task": "Who won the Nobel Prize in Physics in 2023? What was their contribution?"
    },
    {
        "category": "web_search",
        "difficulty": "hard",
        "task": "Compare and contrast the climate policies of the United States and the European Union. What are the key differences in their approaches to reducing carbon emissions?"
    },
    
    # Multimodal understanding tasks (would require image input in a real scenario)
    {
        "category": "multimodal",
        "difficulty": "easy",
        "task": "Analyze this image URL and describe what you see: https://upload.wikimedia.org/wikipedia/commons/thumb/e/ec/Mona_Lisa%2C_by_Leonardo_da_Vinci%2C_from_C2RMF_retouched.jpg/800px-Mona_Lisa%2C_by_Leonardo_da_Vinci%2C_from_C2RMF_retouched.jpg"
    },
    {
        "category": "multimodal",
        "difficulty": "medium",
        "task": "Look at this chart image and explain the trend: https://upload.wikimedia.org/wikipedia/commons/thumb/5/51/Global-surface-temperature.svg/1200px-Global-surface-temperature.svg.png"
    },
    
    # Tool usage tasks
    {
        "category": "tool_usage",
        "difficulty": "easy",
        "task": "Write a Python function to calculate the factorial of a number, then use it to find the factorial of 5."
    },
    {
        "category": "tool_usage",
        "difficulty": "medium",
        "task": "Create a Python script that fetches the current weather for New York City using a weather API and displays the temperature, humidity, and weather conditions."
    },
    {
        "category": "tool_usage",
        "difficulty": "hard",
        "task": "Write a Python script that analyzes a text file containing a list of numbers (one per line), calculates the mean, median, mode, and standard deviation, and creates a histogram visualization of the data."
    },
    
    # Combined skills tasks
    {
        "category": "combined",
        "difficulty": "medium",
        "task": "Research the top 3 electric vehicle manufacturers by market share. Create a Python script to visualize their market shares in a pie chart."
    },
    {
        "category": "combined",
        "difficulty": "hard",
        "task": "Find information about global coffee production by country for the last year. Write a Python script to create a bar chart showing the top 5 coffee-producing countries and their production volumes."
    }
]

# Function to get tasks by category
def get_tasks_by_category(category):
    return [task for task in GAIA_SAMPLE_TASKS if task["category"] == category]

# Function to get tasks by difficulty
def get_tasks_by_difficulty(difficulty):
    return [task for task in GAIA_SAMPLE_TASKS if task["difficulty"] == difficulty]

# Function to get all task queries as a list
def get_all_task_queries():
    return [task["task"] for task in GAIA_SAMPLE_TASKS]

# Function to get a subset of tasks for quick testing
def get_quick_test_tasks():
    # One task from each category and difficulty level
    quick_test_tasks = [
        GAIA_SAMPLE_TASKS[0],  # reasoning, easy
        GAIA_SAMPLE_TASKS[3],  # web_search, easy
        GAIA_SAMPLE_TASKS[6],  # multimodal, easy
        GAIA_SAMPLE_TASKS[9],  # tool_usage, medium
        GAIA_SAMPLE_TASKS[11]  # combined, medium
    ]
    return [task["task"] for task in quick_test_tasks]