fresh start

Requirements.txt

@@ -0,0 +1,9 @@
+gradio
+requests
+openpyxl
+langchain_google_genai
+langchain
+langgraph
+pytube
+google
+google-genai

app.py

@@ -0,0 +1,405 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+import asyncio
+from langchain_google_genai.chat_models import ChatGoogleGenerativeAI
+from typing import IO, Dict
+from io import BytesIO
+from langchain_core.messages import HumanMessage, SystemMessage
+from langgraph.graph import MessagesState
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import tools_condition
+from langgraph.prebuilt import ToolNode
+import base64
+from google.ai.generativelanguage_v1beta.types import Tool as GenAITool
+from google import genai
+from google.genai import types
+import os
+
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+GEMINI_API_KEY = os.getenv("Gemini_API_key")
+SERPER_API_KEY = os.getenv("SERPER_API_KEY")
+
+# --- Basic Agent Definition ---
+# Agent capabilities required: Search the web, listen to audio recordings, watch YouTube videos (process the footage, not the transcript), work with Excel spreadsheets
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+def get_file(task_id: str) -> IO:
+    '''
+    Downloads the file associated with the given task_id, if one exists and is mapped.
+    If the question mentions an attachment, use this function.
+    Args:
+        task_id: Id of the question.
+    Returns:
+        The file associated with the question.
+    '''
+    file_request = requests.get(url=f'https://agents-course-unit4-scoring.hf.space/files/{task_id}')
+    file_request.raise_for_status()
+
+    return BytesIO(file_request.content)
+
+def analyse_excel(task_id: str) -> Dict[str, float]:
+    '''
+    Analyzes the Excel file associated with the given task_id and returns the sum of each numeric column.
+    Args:
+        task_id: Id of the question.
+    Returns:
+        A dictionary with the sum of each numeric column.
+    '''
+    excel_file = get_file(task_id)
+    df = pd.read_excel(excel_file, sheet_name=0)
+    
+    return df.select_dtypes(include='number').sum().to_dict()
+
+def add_numbers(a: float, b: float) -> float:
+    '''
+    Adds two numbers together.
+    Args:
+        a: First number.
+        b: Second number.
+    Returns:
+        The sum of the two numbers.
+    '''
+    return a + b
+
+def transcribe_audio(task_id: str) -> HumanMessage:
+    '''
+    Opens an audio file and returns its content as a string.
+    Args:
+        file: The audio file to be opened.
+    Returns:
+        The content of the audio file as a string.
+    '''
+    audio_file = get_file(task_id)
+    if audio_file is None:
+        raise ValueError("No audio file found for the given task_id.")
+    # Encode the audio file to base64
+    audio_file.seek(0)  # Ensure the file pointer is at the beginning
+    encoded_audio = base64.b64encode(audio_file.read()).decode("utf-8")
+
+    return HumanMessage(
+        content=[
+            {"type": "text", "text": "Transcribe the audio."},
+            {
+                "type": "media",
+                "data": encoded_audio,  # Use base64 string directly
+                "mime_type": "audio/mpeg",
+            },
+        ]
+    )
+
+def python_code(task_id: str) -> str:
+    '''
+    Returns the Python code associated with the given task_id.
+    Args:
+        task_id: Id of the question.
+    Returns:
+        The Python code associated with the question.
+    '''
+    code_request = requests.get(url=f'https://agents-course-unit4-scoring.hf.space/files/{task_id}')
+    code_request.raise_for_status()
+    
+    return code_request.text
+
+def open_image(task_id: str) -> str:
+    '''
+    Opens an image file associated with the given task_id.
+    Args:
+        task_id: Id of the question.
+    Returns:
+        The base64 encoded string of the image file.
+    '''
+    image_file = get_file(task_id)
+    if image_file is None:
+        raise ValueError("No image file found for the given task_id.")
+    
+    return base64.b64encode(image_file.read()).decode("utf-8")
+
+def open_youtube_video(url: str, query:str) -> str:
+    '''
+    Answers a question about a video from the given URL.
+    Args:
+        url: The URL of the video file.
+        query: The question to be answered about the video.
+    Returns:
+        Answer to the question about the video.
+    '''
+    
+    client = genai.Client(api_key=GOOGLE_API_KEY)
+
+    response = client.models.generate_content(
+    model='models/gemini-2.0-flash',
+    contents=types.Content(
+        parts=[
+            types.Part(
+                file_data=types.FileData(file_uri=url)
+            ),
+            types.Part(text=f'''{query} YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated 
+                       list of numbers and/or strings.''')
+            ]
+            )
+            )
+    
+    return response.text
+
+def google_search(query: str) -> str:
+    '''
+    Performs a Google search for the given query.
+    Args:
+        query: The search query.
+    Returns:
+        The search results as a string.
+    '''
+    llm = ChatGoogleGenerativeAI(
+            model="gemini-2.5-flash-preview-05-20",
+            max_tokens=8192,
+            temperature=0
+            )
+    response = llm.invoke(query,
+        tools=[GenAITool(google_search={})]
+    )
+
+    return response.content
+
+
+class BasicAgent:
+    def __init__(self):
+        self.llm = ChatGoogleGenerativeAI(
+            model="gemini-2.5-flash-preview-05-20",
+            max_tokens=8192,
+            temperature=0
+            )
+        self.tools = [get_file, analyse_excel, add_numbers, transcribe_audio, python_code, open_image, open_youtube_video
+         , google_search
+         ]
+        
+        self.agent = self.llm.bind_tools(self.tools)
+
+        self.sys_msg = SystemMessage('''You are a general AI assistant. I will ask you a question. Only provide YOUR FINAL ANSWER and nothing else. 
+        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.
+        You have access to multiple tools and should use as many as you need to answer the question.
+        If you are asked to analyze an Excel file, use the 'analyse_excel' tool. 
+        If you are asked to download a file, use the 'get_file' tool. 
+        If you are asked to add two numbers, use the 'add_numbers' tool. If you need to add more than two numbers, use the 'add_numbers' 
+        tool multiple times.
+        If you are asked to transcribe an audio file, use the 'transcribe_audio' tool.
+        If you are asked to run a Python code, use the 'python_code' tool.
+        If you are asked to open an image, use the 'open_image' tool.
+        If you were given a link with www.youtube.com, use the 'open_youtube_video' tool.
+        If the question requires a web search because your internal knowledge doesn't have the information, use the 'google_search' tool.
+                        ''')
+
+        # Graph
+        self.builder = StateGraph(MessagesState)
+
+        # Define nodes: these do the work
+        self.builder.add_node("assistant", self.assistant)
+        self.builder.add_node("tools", ToolNode(self.tools))
+
+        # Define edges: these determine how the control flow moves
+        self.builder.add_edge(START, "assistant")
+        self.builder.add_conditional_edges(
+            "assistant",
+            # If the latest message (result) from assistant is a tool call -> tools_condition routes to tools
+            # If the latest message (result) from assistant is a not a tool call -> tools_condition routes to END
+            tools_condition,
+        )
+        self.builder.add_edge("tools", "assistant")
+        self.react_graph = self.builder.compile()
+        
+        print("BasicAgent initialized.")
+    
+    def assistant(self, state: MessagesState):
+        return {"messages": [self.agent.invoke([self.sys_msg] + state["messages"])]}
+    
+    async def __call__(self, question: str, task_id: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = "This is a default answer."
+
+        await asyncio.sleep(60)
+        messages = self.react_graph.invoke({"messages": f'Task id: {task_id}\n {question}'})
+        return messages["messages"][-1].content if messages["messages"] else fixed_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 = asyncio.run(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)

my-final-assignment

@@ -0,0 +1 @@
+Subproject commit 7a69f377adc049319143e7e01a89e6004c1fa4db

utilities.py

@@ -0,0 +1,17 @@
+from smolagents import tool
+from typing import IO
+
+@tool
+def get_file(task_id: str) -> IO:
+    '''
+    Downloads the file associated with the given task_id, if one exists and is mapped.
+    If the question mentions an attachment, use this function.
+    Args:
+        task_id: Id of the question.
+    Returns:
+        The file associated with the question.
+    '''
+    file_request = requests.get(url=f'https://agents-course-unit4-scoring.hf.space/files/{task_id}')
+    file_request.raise_for_status()
+
+    return file_request