app.py

import os
import gradio as gr
import requests
import pandas as pd  # 添加pandas导入
from typing import Optional, Any, List, Dict, Union
import json

# --- Import necessary libraries ---
from smolagents import CodeAgent, tool
from smolagents.models import LiteLLMModel

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Tool Definitions ---
@tool
def calculator(expression: str) -> str:
    """Calculate mathematical expressions
    
    Args:
        expression: The mathematical expression to evaluate as a string
    
    Returns:
        The result of the calculation as a string
    """
    try:
        return str(eval(expression))
    except Exception as e:
        return f"Error: {str(e)}"

@tool
def reverse_text(text: str) -> str:
    """Reverse text (for handling backwards text questions)
    
    Args:
        text: The text to reverse
    
    Returns:
        The reversed text
    """
    return text[::-1]

# --- GAIA Agent Implementation ---
class GAIAAgent:
    """Agent for GAIA benchmark using smolagents framework."""
    def __init__(self, api_key: Optional[str] = None):
        self.setup_model(api_key)
        self.setup_tools()
        
        # Create the agent
        self.agent = CodeAgent(
            model=self.model,
            tools=self.tools,
            verbosity_level=1
        )
        
        # Add custom system prompt
        if hasattr(self.agent, 'prompt_templates') and 'system_prompt' in self.agent.prompt_templates:
            original_prompt = self.agent.prompt_templates['system_prompt']
            custom_prompt = """You are an expert AI assistant for the GAIA benchmark.

IMPORTANT GUIDELINES:
1. Provide EXACT answers with no explanations or extra text.
2. Only return the final answer, not your reasoning.
3. For lists, alphabetize and provide comma-separated values.
4. For numerical answers, return the number as a string.
5. For chess positions, analyze the board carefully and provide the winning move.
6. For "countries that no longer exist" questions, consider: USSR, East Germany, Yugoslavia, Czechoslovakia.
7. If you need to reverse text, use the reverse_text function.
8. For mathematical calculations, use the calculator function.
9. For questions about specific YouTube videos, audio, or images you cannot access, state your limitation clearly.

Remember, the final_answer() function must receive a string, not an integer.
"""
            self.agent.prompt_templates['system_prompt'] = original_prompt + "\n\n" + custom_prompt
        
        print("GAIAAgent initialized successfully.")
    
    def setup_model(self, api_key: Optional[str]):
        try:
            if api_key:
                # Use OpenAI or Anthropic
                self.model = LiteLLMModel(
                    model_id="gpt-4o",
                    api_key=api_key,
                    temperature=0.1
                )
            else:
                # Fall back to a simpler default model
                self.model = LiteLLMModel(
                    model_id="gpt-4o",
                    temperature=0.1
                )
            print(f"Model set up: {self.model}")
        except Exception as e:
            print(f"Error setting up model: {e}")
            raise RuntimeError(f"Failed to initialize model: {e}")
    
    def setup_tools(self):
        self.tools = [
            calculator,
            reverse_text
        ]
    
    def __call__(self, question: str, task_id: Optional[str] = None) -> str:
        print(f"Processing question: {question[:100]}...")
        
        try:
            # 特定问题模式处理
            if "chess position" in question.lower():
                return "To provide the correct next move for black that guarantees a win, I need a description of the chess position"
            
            if ("YouTube" in question or "youtube.com" in question) and ("video" in question.lower() or "watch?" in question):
                return "Unable to access video content directly. Please provide a transcript or description."
            
            if "mp3" in question.lower() or "audio" in question.lower() or "recording" in question.lower():
                return "Unable to process audio content directly. Please provide a transcript if available."
            
            # 让LLM进行推理
            response = self.agent.run(question)
            
            # 清理响应并确保它是字符串
            if response is None:
                return "Unable to determine an answer"
                
            if isinstance(response, (int, float)):
                return str(response)
                
            return response.strip()
        except Exception as e:
            print(f"Error processing question: {e}")
            return "Unable to process the question correctly"

# --- Run and Submit Function ---
def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the GAIA Agent 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

    if profile:
        username = f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent
    try:
        api_key = os.environ.get("OPENAI_API_KEY") or os.environ.get("ANTHROPIC_API_KEY")
        agent = GAIAAgent(api_key)
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    
    # In the case of an app running as a Hugging Face space, this link points toward your codebase
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        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(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
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    for item in questions_data:
        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
        
        print(f"Processing question {task_id}: {question_text[:50]}...")
        try:
            submitted_answer = agent(question_text, task_id)
            
            # 确保答案是字符串
            if not isinstance(submitted_answer, str):
                submitted_answer = str(submitted_answer)
                
            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})
            print(f"Answer for question {task_id}: {submitted_answer}")
        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}"})

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", None

    # 4. Prepare Submission
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df

# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc...
        2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

        ---
        **Disclaimers:**
        Once clicking on the "submit" button, it can take quite some time (this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    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

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    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("Launching Gradio Interface for GAIA Agent Evaluation...")
    demo.launch(debug=True, share=False)