app.py

import os
import gradio as gr
import pandas as pd
import requests
import subprocess
import json
import csv
import openpyxl
import whisper
from typing import Optional
from bs4 import BeautifulSoup
from duckduckgo_search import DDGS
from smolagents import CodeAgent, tool

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Basic Agent Definition ---
# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
class ClaudeServerModel:
    def __init__(self, api_key: str, model_id: str = "claude-3-opus-20240229", temperature: float = 0.0):
        self.api_key = api_key
        self.model_id = model_id
        self.temperature = temperature

    def complete(self, prompt: str) -> str:
        headers = {
            "x-api-key": self.api_key,
            "anthropic-version": "2023-06-01",
            "content-type": "application/json"
        }
        body = {
            "model": self.model_id,
            "max_tokens": 1024,
            "temperature": self.temperature,
            "messages": [
                {"role": "user", "content": prompt}
            ]
        }
        response = requests.post("https://api.anthropic.com/v1/messages", headers=headers, json=body)
        response.raise_for_status()
        return response.json()["content"][0]["text"].strip()

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

def download_file(file_name: str) -> None:
    if not os.path.exists(file_name):
        url = f"{DEFAULT_API_URL}/files/{file_name.split('.')[0]}"
        r = requests.get(url)
        with open(file_name, "wb") as f:
            f.write(r.content)

@tool
def open_file_as_text(file_name: str, filetype: Optional[str] = "txt") -> str:
    """
    Opens and reads a file of the given type (txt, json, csv, xlsx, mp3).
    Returns its content as readable text or transcription for audio files.
    """
    download_file(file_name)
    try:
        if filetype == "txt":
            with open(file_name, "r", encoding="utf-8") as f:
                return f.read()
        elif filetype == "json":
            with open(file_name, "r", encoding="utf-8") as f:
                data = json.load(f)
            return json.dumps(data, indent=2)
        elif filetype == "csv":
            with open(file_name, "r", encoding="utf-8") as f:
                reader = csv.reader(f)
                rows = list(reader)
            return "\n".join([", ".join(row) for row in rows])
        elif filetype == "xlsx":
            wb = openpyxl.load_workbook(file_name, data_only=True)
            sheet = wb.active
            content = []
            for row in sheet.iter_rows(values_only=True):
                content.append(", ".join(str(cell) if cell is not None else "" for cell in row))
            return "\n".join(content)
        elif filetype == "mp3":
            w = whisper.load_model("base")
            res = w.transcribe(file_name)
            return res["text"]
        else:
            return f"Unsupported filetype '{filetype}'."
    except Exception as e:
        return f"Error opening file '{file_name}': {str(e)}"

@tool
def web_search(query: str) -> str:
    """
    Performs a web search using DuckDuckGo and returns the top results.

    Args:
        query: Search query string.

    Returns:
        Top search results formatted as title, snippet, and URL.
    """
    try:
        with DDGS() as ddgs:
            results = ddgs.text(query, max_results=3)
            if not results:
                return "No results found."
            return "\n\n".join([f"Title: {r['title']}\nSnippet: {r['body']}\nURL: {r['href']}" for r in results])
    except Exception as e:
        return f"Error during search: {str(e)}"

@tool
def read_wikipedia_page(url: str) -> str:
    """
    Reads and extracts clean text content from a Wikipedia page.

    Args:
        url: Full URL to the Wikipedia page.

    Returns:
        Sectioned and readable content from the page, including paragraphs, lists, and tables.
    """
    headers = {"User-Agent": "Mozilla/5.0"}
    resp = requests.get(url, headers=headers, timeout=10)
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "html.parser")
    content_div = soup.find('div', id='mw-content-text')
    parts = []
    for elem in content_div.find_all(['h2', 'h3', 'p', 'ul', 'ol', 'table']):
        if elem.name in ['h2', 'h3']:
            parts.append("\n\n" + elem.get_text(strip=True) + "\n")
        elif elem.name in ['p', 'ul', 'ol']:
            parts.append(elem.get_text(strip=True))
        elif elem.name == 'table':
            parts.append(parse_wikipedia_table(elem))
    return "\n".join(parts)

@tool
def smart_paginate_around_query(full_text: str, query: str) -> list:
    """
    Splits full text into focused windows surrounding the query keyword.

    Args:
        full_text: The large text content to paginate.
        query: Keyword or phrase to center each window on.

    Returns:
        List of substrings centered around the query within the original text.
    """
    before_chars = 1000
    after_chars = 3000
    q = query.lower()
    text_lower = full_text.lower()
    pages = []
    start = 0
    while True:
        idx = text_lower.find(q, start)
        if idx == -1:
            break
        s = max(0, idx - before_chars)
        e = min(len(full_text), idx + len(q) + after_chars)
        pages.append(full_text[s:e])
        start = e
    return pages

@tool
def reverse_sentence(text: str) -> str:
    """
    Reverses the input text string.

    Args:
        text: A string to reverse.

    Returns:
        Reversed string.
    """
    return text[::-1]

@tool
def run_python_code(file_name: str) -> str:
    """
    Executes a Python script and returns the output.

    Args:
        file_name: Name of the Python file to execute.

    Returns:
        Printed standard output or error message from the script.
    """
    download_file(file_name)
    try:
        result = subprocess.run(["python", file_name], capture_output=True, text=True, timeout=10)
        if result.returncode != 0:
            return f"Error: {result.stderr.strip()}"
        return result.stdout.strip()
    except Exception as e:
        return f"Execution failed: {e}"

# Agent Setup
tools = [
    open_file_as_text,
    web_search,
    read_wikipedia_page,
    smart_paginate_around_query,
    reverse_sentence,
    run_python_code
]

model = ClaudeServerModel(
    api_key=os.getenv("CLAUDE_API_KEY"),
    model_id="claude-3-opus-20240229"
)

agent = CodeAgent(
    model=model,
    tools=tools,
    additional_authorized_imports=["pandas", "numpy", "datetime", "json", "re", "math", "os", "requests", "csv", "urllib"]
)

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

    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"

    # Instantiate Agent ( modify this part to create your agent)
    try:
        agent = CodeAgent(
            model=model,
            tools=tools,
            additional_authorized_imports=["pandas", "numpy", "datetime", "json", "re", "math", "os", "requests", "csv",
                                           "urllib"]
        )
    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 (useful 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 = []
    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")
        file_name = item.get("file_name")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            full_prompt = f"""You are a highly precise answering agent designed to meet the GAIA benchmark's exact-match standards.

When presented with a question:
- Use tools appropriately and deliberately. Do not make assumptions or guess answers.
- Use `web_search` to find external sources only if necessary. If the results include short snippets, you MUST follow the link and read the full content using `read_wikipedia_page`.
- You have access to `read_wikipedia_page` ONLY — no other external browsing is allowed.
- When reading long text, ALWAYS use `smart_paginate_around_query` to extract focused context. Use 1-3 general keywords (not full questions) as the query.
- If the task involves reversing words, letters, or phrases, use the `reverse_sentence` tool. Never reverse text manually.
- For any file-based task (e.g., .mp3, .csv, .json, .xlsx), use the `file_name` provided in the metadata — not a name mentioned in the question text.
- Format lists with a single space after each comma.
- If asked for a number, return digits only — no commas, currency signs, or symbols (e.g., %, $, etc.).
- If asked for a string, do not include articles (e.g., "the", "a") or abbreviations unless required. Spell out numbers in digit form unless stated otherwise.
- If asked for a comma-separated list, apply the correct formatting per element type (string or number).
Once you have the exact answer:
- Immediately call `final_answer("your_answer")` and stop execution.
- Never retry, rerun, or generate multiple answers.
- Do not include reasoning, steps, thoughts, or commentary — just the final value.
Example:
If asked: "What is the capital of France?"
Your answer logic should follow:
```py
print("Paris")
```<end_code>
Based on the above guidelines, answer the following question:
--begin of question--
{question_text}
--end of question--
If the questions mentions the need to use a file, use the following `file_name` value as the `file_name` parameter in any function calls:
file_name: {file_name}"""
            submitted_answer = agent.run(full_prompt)
            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)