Final_Assignment_Template

Sleeping

Update app.py

92d4e7e verified 7 months ago

13.3 kB

import os
import re
import io
import gradio as gr
import requests
import pandas as pd
from smolagents import CodeAgent, DuckDuckGoSearchTool, tool, InferenceClientModel

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

PROMPT = """You are a general AI assistant.
I will ask you a question.
Report your thoughts, and finish your answer with the following 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 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 of whether the element to be put in the list is a number or a string.
"""


@tool
def search_wikipedia(query: str) -> str:
    """
    Search Wikipedia and return a summary of the topic.
    Args:
        query: The search query to look up on Wikipedia.
    """
    search_url = "https://en.wikipedia.org/w/api.php"
    search_params = {"action": "query", "list": "search", "srsearch": query, "format": "json"}
    search_data = requests.get(search_url, params=search_params).json()
    results = search_data["query"]["search"]
    if not results:
        return "No results found on Wikipedia."
    top_title = results[0]["title"]
    summary_params = {
        "action": "query", "prop": "extracts",
        "exintro": True, "explaintext": True,
        "titles": top_title, "format": "json"
    }
    summary_data = requests.get(search_url, params=summary_params).json()
    pages = summary_data["query"]["pages"]
    page = next(iter(pages.values()))
    return page.get("extract", "No content found.")[:2000]


def download_task_file(task_id: str, base_url: str):
    """Try to download the file associated with a task. Returns (filename, content) or (None, None)."""
    try:
        r = requests.get(f"{base_url}/files/{task_id}", timeout=30)
        if r.status_code == 200:
            cd = r.headers.get("content-disposition", "")
            ct = r.headers.get("content-type", "")
            fname = None
            if "filename=" in cd:
                fname = cd.split("filename=")[-1].strip('"').strip()
            elif "image" in ct:
                ext = ct.split("/")[-1].split(";")[0]
                fname = f"{task_id}.{ext}"
            elif "python" in ct:
                fname = f"{task_id}.py"
            elif "excel" in ct or "spreadsheet" in ct:
                fname = f"{task_id}.xlsx"
            elif "text" in ct:
                fname = f"{task_id}.txt"
            else:
                fname = f"{task_id}.bin"
            return fname, r.content
        return None, None
    except Exception:
        return None, None


def build_file_context(fname: str, fcontent: bytes) -> str:
    """Return context string from file content to append to prompt."""
    if fname.endswith((".py", ".txt", ".csv")):
        try:
            text = fcontent.decode("utf-8")
            return f"\n\nAssociated file ({fname}):\n```\n{text}\n```"
        except Exception:
            pass
    elif fname.endswith(".xlsx"):
        try:
            import pandas as pd
            df = pd.read_excel(io.BytesIO(fcontent))
            return f"\n\nAssociated Excel file ({fname}) contents:\n{df.to_string()}"
        except Exception as e:
            return f"\n\n[Excel file {fname} could not be parsed: {e}]"
    return f"\n\n[File {fname} is attached but cannot be read as text]"


def extract_final_answer(text: str) -> str:
    match = re.search(r"FINAL ANSWER:\s*(.+?)(?:\n|$)", str(text), re.IGNORECASE)
    if match:
        return match.group(1).strip()
    return str(text).strip()


# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        model = InferenceClientModel(
            model_id="Qwen/Qwen2.5-72B-Instruct",
            token=os.getenv("HF_TOKEN"),
        )
        self.agent = CodeAgent(model=model, tools=[DuckDuckGoSearchTool(), search_wikipedia])
        self.base_url = DEFAULT_API_URL
        print("BasicAgent initialized.")

    def __call__(self, question: str, task_id: str = "") -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")

        file_context = ""
        if task_id:
            fname, fcontent = download_task_file(task_id, self.base_url)
            if fname and fcontent:
                file_context = build_file_context(fname, fcontent)
                print(f"  [file: {fname}]")

        full_prompt = PROMPT + f"\n\nQuestion: {question}" + file_context
        try:
            result = self.agent.run(full_prompt)
            answer = extract_final_answer(result)
        except Exception as e:
            print(f"  ERROR running agent: {e}")
            answer = f"ERROR: {e}"

        print(f"Agent returning answer: {answer}")
        return answer

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"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent()
    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 ( 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 = []
    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
        try:
            submitted_answer = agent(question_text, task_id)
            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)

	import os
	import re
	import io
	import gradio as gr
	import requests
	import pandas as pd
	from smolagents import CodeAgent, DuckDuckGoSearchTool, tool, InferenceClientModel

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

	PROMPT = """You are a general AI assistant.
	I will ask you a question.
	Report your thoughts, and finish your answer with the following 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 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 of whether the element to be put in the list is a number or a string.
	"""


	@tool
	def search_wikipedia(query: str) -> str:
	"""
	Search Wikipedia and return a summary of the topic.

	Args:
	query: The search query to look up on Wikipedia.
	"""
	search_url = "https://en.wikipedia.org/w/api.php"
	search_params = {"action": "query", "list": "search", "srsearch": query, "format": "json"}
	search_data = requests.get(search_url, params=search_params).json()
	results = search_data["query"]["search"]
	if not results:
	return "No results found on Wikipedia."
	top_title = results[0]["title"]
	summary_params = {
	"action": "query", "prop": "extracts",
	"exintro": True, "explaintext": True,
	"titles": top_title, "format": "json"
	}
	summary_data = requests.get(search_url, params=summary_params).json()
	pages = summary_data["query"]["pages"]
	page = next(iter(pages.values()))
	return page.get("extract", "No content found.")[:2000]


	def download_task_file(task_id: str, base_url: str):
	"""Try to download the file associated with a task. Returns (filename, content) or (None, None)."""
	try:
	r = requests.get(f"{base_url}/files/{task_id}", timeout=30)
	if r.status_code == 200:
	cd = r.headers.get("content-disposition", "")
	ct = r.headers.get("content-type", "")
	fname = None
	if "filename=" in cd:
	fname = cd.split("filename=")[-1].strip('"').strip()
	elif "image" in ct:
	ext = ct.split("/")[-1].split(";")[0]
	fname = f"{task_id}.{ext}"
	elif "python" in ct:
	fname = f"{task_id}.py"
	elif "excel" in ct or "spreadsheet" in ct:
	fname = f"{task_id}.xlsx"
	elif "text" in ct:
	fname = f"{task_id}.txt"
	else:
	fname = f"{task_id}.bin"
	return fname, r.content
	return None, None
	except Exception:
	return None, None


	def build_file_context(fname: str, fcontent: bytes) -> str:
	"""Return context string from file content to append to prompt."""
	if fname.endswith((".py", ".txt", ".csv")):
	try:
	text = fcontent.decode("utf-8")
	return f"\n\nAssociated file ({fname}):\n```\n{text}\n```"
	except Exception:
	pass
	elif fname.endswith(".xlsx"):
	try:
	import pandas as pd
	df = pd.read_excel(io.BytesIO(fcontent))
	return f"\n\nAssociated Excel file ({fname}) contents:\n{df.to_string()}"
	except Exception as e:
	return f"\n\n[Excel file {fname} could not be parsed: {e}]"
	return f"\n\n[File {fname} is attached but cannot be read as text]"


	def extract_final_answer(text: str) -> str:
	match = re.search(r"FINAL ANSWER:\s*(.+?)(?:\n\|$)", str(text), re.IGNORECASE)
	if match:
	return match.group(1).strip()
	return str(text).strip()


	# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
	class BasicAgent:
	def __init__(self):
	model = InferenceClientModel(
	model_id="Qwen/Qwen2.5-72B-Instruct",
	token=os.getenv("HF_TOKEN"),
	)
	self.agent = CodeAgent(model=model, tools=[DuckDuckGoSearchTool(), search_wikipedia])
	self.base_url = DEFAULT_API_URL
	print("BasicAgent initialized.")

	def __call__(self, question: str, task_id: str = "") -> str:
	print(f"Agent received question (first 50 chars): {question[:50]}...")

	file_context = ""
	if task_id:
	fname, fcontent = download_task_file(task_id, self.base_url)
	if fname and fcontent:
	file_context = build_file_context(fname, fcontent)
	print(f" [file: {fname}]")

	full_prompt = PROMPT + f"\n\nQuestion: {question}" + file_context
	try:
	result = self.agent.run(full_prompt)
	answer = extract_final_answer(result)
	except Exception as e:
	print(f" ERROR running agent: {e}")
	answer = f"ERROR: {e}"

	print(f"Agent returning answer: {answer}")
	return answer

	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"

	# 1. Instantiate Agent ( modify this part to create your agent)
	try:
	agent = BasicAgent()
	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 ( 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 = []
	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
	try:
	submitted_answer = agent(question_text, task_id)
	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)