Blame for app.py

import os
import gradio as gr
import requests
import inspect
import tempfile
import pandas as pd
from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool, InferenceClientModel, tool,OpenAIServerModel
import re
from huggingface_hub import InferenceClient
import base64

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

#--- tools ---

@tool
def analyze_image_tool(image_path: str, question: str) -> str:
    """
    Analyzes an image and answers a question about its contents. 
    Use this tool AFTER you downloaded an image file (.png, .jpg, .jpeg) using download_task_file.
    
    Args:
        image_path: The local path to the image file you want to analyze.
        question: The specific question about what to look for in the image.
    """
    try:
        client = InferenceClient(model="Qwen/Qwen2-VL-7B-Instruct") 
        
        with open(image_path, "rb") as image_file:
            encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
            
        image_url = f"data:image/jpeg;base64,{encoded_string}"
        
        messages = [
            {
                "role": "user",
                "content": [
                    {"type": "image_url", "image_url": {"url": image_url}},
                    {"type": "text", "text": question},
                ],
            }
        ]
        
        print(f"Sending image {image_path} to Vision model for analysis...")
        response = client.chat_completion(messages=messages, max_tokens=500)
        return response.choices[0].message.content
    except Exception as e:
        return f"Error analyzing image: {str(e)}"

@tool
def download_task_file(task_id: str) -> str:
    """
    Downloads the file associated with a specific task_id and returns the local file path.
    Use this tool EVERY TIME the question mentions an attached file or asks to analyze data from a file.
    
    Args:
        task_id: The ID of the task to fetch the file for.
    """
    url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
    print(f"Downloading file for task: {task_id}")
    
    try:
        response = requests.get(url, timeout=20)
        if response.status_code == 200:
            filename = f"file_{task_id}" 
            cd = response.headers.get('content-disposition')
            if cd and 'filename=' in cd:
                matches = re.findall('filename="?([^"]+)"?', cd)
                if matches:
                    filename = matches[0]
                    
            temp_dir = tempfile.gettempdir()
            filepath = os.path.join(temp_dir, filename)  
            
            with open(filepath, 'wb') as f:
                f.write(response.content)
            
            return f"File downloaded successfully! The file is located at: {filepath}. You can now write python code to open and read this file."
        else:
            return f"Failed to download file. HTTP Status: {response.status_code}. The file might not exist for this task."
    except Exception as e:
        return f"An error occurred while downloading: {e}"

@tool
def transcribe_audio_tool(audio_path: str) -> str:
    """
    Transcribes an audio or video file (mp3, mp4, wav) to text.
    Use this tool AFTER downloading a media file using download_task_file if the question requires knowing what is spoken in the file.
    
    Args:
        audio_path: The local path to the audio/video file.
    """
    try:
        api_key = os.getenv("GROQ_API_KEY")
        if not api_key:
            return "Error: GROQ_API_KEY not found in environment."
            
        headers = {"Authorization": f"Bearer {api_key}"}
        url = "https://api.groq.com/openai/v1/audio/transcriptions"
        
        print(f"Transcribing audio file {audio_path}...")
        with open(audio_path, "rb") as f:
            files = {"file": (os.path.basename(audio_path), f)}
            data = {"model": "whisper-large-v3"}
            response = requests.post(url, headers=headers, files=files, data=data)
            
        response.raise_for_status()
        return response.json().get("text", "No text could be extracted.")
    except Exception as e:
        return f"Error transcribing audio: {str(e)}"

@tool
def read_webpage_clean_tool(url: str) -> str:
    """
    Reads a webpage and extracts clean Markdown text. 
    Use this tool when VisitWebpageTool fails or when you need to read articles, documentation, or bypass JavaScript rendering.
    
    Args:
        url: The full URL of the webpage to read.
    """
    try:
        print(f"Fetching clean text from: {url}")
        jina_url = f"https://r.jina.ai/{url}"
        response = requests.get(jina_url, timeout=20)
        response.raise_for_status()
        # Restrict length to prevent context window overflow
        return response.text[:8000] 
    except Exception as e:
        return f"Error reading webpage with clean tool: {str(e)}" 
search_tool = DuckDuckGoSearchTool()
visit_webpage_tool = VisitWebpageTool()

#--- agent ---

model = OpenAIServerModel(
    model_id="llama-3.3-70b-versatile",
    api_base="https://api.groq.com/openai/v1",
    api_key=os.getenv("GROQ_API_KEY")
)
manager_system_prompt="""
You are an advanced AI assistant designed to solve complex, multi-step tasks from the GAIA benchmark.
You MUST strictly adhere to the ReAct (Reason, Act, Observe) framework for EVERY step you take.

Your process must look like this:
1. **Thought:** Carefully analyze the current state. What information do you have? What is missing? Plan your next exact move step-by-step.
2. **Action:** Execute your plan by calling the appropriate tool or writing Python code. 
3. **Observation:** Review the output of your tool or code. (If code fails, your next Thought must be how to fix it).

Repeat this loop until you are 100% confident you have the final answer.

NEVER guess facts or make up data. If you are asked about factual information (like Wikipedia), you MUST use the search_tool or visit_webpage_tool to verify it before answering.

**Specific Guidelines for Tools and Code:**
1. **Information Gathering:** If the prompt mentions a file, use `download_task_file` FIRST to retrieve the local file path. 
2. **Analysis via Code:** Write Python code to open, read, and analyze downloaded files (using pandas, json, PyPDF2, etc.). ALWAYS use `print()` in your code to output intermediate data, statistics, or rows so you can see the results in your next step.
3. **Vision/Images:** If the task involves an image, pass the local image path and your specific question to `analyze_image_tool`.
4. **Audio/Video:** If the task involves a spoken media file, use `transcribe_audio_tool` to get the transcript.
5. **Web Scraping:** Use `read_webpage_clean_tool` to fetch clean text from URLs if standard web browsing fails.
6. **Self-Correction:** Do not guess the final answer. If your Python code throws an error, read the traceback carefully, fix the code, and try again.

VERY IMPORTANT!: FINISH YOUR ANSWER STRICTLY WITH THE FOLLOING TEMPLATE: FINAL ANSWER: [YOUR FINAL ANSWER].
YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
If you are asked for a number, don't use a comma to write your number neither use units such as $ or percent sign unless specified otherwise.
If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
If you are asked for a comma separated list, apply the above rules depending on whether the element to be put in the list is a number or a string."""

def create_new_agent():
    return CodeAgent(
        tools=[
            search_tool, 
            download_task_file, 
            visit_webpage_tool, 
            analyze_image_tool, 
            transcribe_audio_tool, 
            read_webpage_clean_tool
        ],
        model=model,
        instructions=manager_system_prompt,  
        max_steps=10,
        additional_authorized_imports=["pandas", "openpyxl", "PyPDF2", "json", "csv", "re", "math", "datetime"] 
    )

#--- run ---

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the manager_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"


    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
    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 your Agent
    results_log = []
    answers_payload = []
    questions_data = questions_data[:2]
    print(f"Running agent on {len(questions_data)} questions...")
    for item in questions_data:
        try:
            agent = create_new_agent()
        except Exception as e:
            print(f"Error instantiating agent: {e}")
            return f"Error initializing agent: {e}", None
        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)
            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})
        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.", pd.DataFrame(results_log)

    # 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("# Basic 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. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

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

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    # Removed max_rows=10 from DataFrame constructor
    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 Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)