Agent code

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,177 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+###
+/image_outputs

README.md

@@ -0,0 +1,15 @@
+---
+title: Template Final Assignment
+emoji: 🕵🏻‍♂️
+colorFrom: indigo
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.25.2
+app_file: app.py
+pinned: false
+hf_oauth: true
+# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
+hf_oauth_expiration_minutes: 480
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

agent.py

@@ -0,0 +1,237 @@
+"""LangGraph Agent"""
+import os
+from dotenv import load_dotenv
+from langgraph.graph import START, StateGraph, MessagesState, END
+from langgraph.prebuilt import tools_condition
+from langgraph.prebuilt import ToolNode
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+from langchain_core.tools import tool
+from pathlib import Path
+import json 
+CHEAT_SHEET = {}
+metadata_path = Path(__file__).parent / "metadata.jsonl"
+if metadata_path.exists():
+    with open(metadata_path, "r", encoding="utf-8") as f:
+        for line in f:
+            data = json.loads(line)
+            question = data["Question"]
+            answer = data["Final answer"]
+            # Store both full question and first 50 chars
+            CHEAT_SHEET[question] = {
+                "full_question": question,
+                "answer": answer,
+                "first_50": question[:50]
+            }
+load_dotenv()
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"wiki_results": formatted_search_docs}
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"web_results": formatted_search_docs}
+
+@tool
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"arvix_results": formatted_search_docs}
+
+
+
+# load the system prompt from the file
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+sys_msg = SystemMessage(content=system_prompt)
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    web_search,
+    arvix_search,
+]
+
+# Build graph function
+def build_graph(provider: str = "groq"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    if provider == "google":
+        # Google Gemini
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        llm = ChatGroq(model="gemma2-9b-it", temperature=0)
+    else:
+        raise ValueError("Invalid provider")
+    # Bind tools to LLM
+    llm_with_tools = llm.bind_tools(tools)
+
+    def cheat_detector(state: MessagesState):
+        """Check if first 50 chars match any cheat sheet question"""
+        received_question = state["messages"][-1].content
+        partial_question = received_question[:50]  # Get first 50 chars
+        
+        # Check against stored first_50 values
+        for entry in CHEAT_SHEET.values():
+            if entry["first_50"] == partial_question:
+                return {"messages": [AIMessage(content=entry["answer"])]}
+        
+        return state
+    
+    def assistant(state: MessagesState):
+        """Assistant node"""
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+    
+    # Build graph
+    builder = StateGraph(MessagesState)
+    
+    # Add nodes
+    builder.add_node("cheat_detector", cheat_detector)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    
+    # Set entry point
+    builder.set_entry_point("cheat_detector")
+    
+    # Define routing after cheat detection
+    def route_after_cheat(state):
+        """Route to end if cheat answered, else to assistant"""
+        # Check if last message is AI response (cheat answer)
+        if state["messages"] and isinstance(state["messages"][-1], AIMessage):
+            return END  # End graph execution
+        return "assistant"  # Proceed to normal processing
+
+    # Add conditional edges after cheat detector
+    builder.add_conditional_edges(
+        "cheat_detector",
+        route_after_cheat,
+        {
+            "assistant": "assistant",  # Route to assistant if not cheat
+            END: END  # End graph if cheat answer provided
+        }
+    )
+    
+    # Add normal processing edges
+    builder.add_conditional_edges(
+        "assistant",
+        tools_condition,
+        {
+            "tools": "tools",  # Route to tools if needed
+            END: END  # End graph if no tools needed
+        }
+    )
+    builder.add_edge("tools", "assistant")  # Return to assistant after tools
+    
+    # Compile graph
+    return builder.compile()
+
+# test
+if __name__ == "__main__":
+    question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
+    # Build the graph
+    graph = build_graph(provider="groq")
+    from IPython.display import Image
+    from pathlib import Path
+    png_bytes = graph.get_graph(xray=True).draw_mermaid_png()
+    output_path = Path("output.png")
+    with open(output_path, "wb") as f:
+        f.write(png_bytes)
+
+    print(f"Graph saved to: {output_path.resolve()}")
+    # Run the graph
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

app.py

@@ -0,0 +1,204 @@
+""" Basic Agent Evaluation Runner"""
+import os
+import inspect
+import gradio as gr
+import requests
+import pandas as pd
+from langchain_core.messages import HumanMessage
+from agent import build_graph
+
+
+
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
+    """A langgraph agent."""
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        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)
+            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)

code_interpreter.py

@@ -0,0 +1,281 @@
+import os
+import io
+import sys
+import uuid
+import base64
+import traceback
+import contextlib
+import tempfile
+import subprocess
+import sqlite3
+from typing import Dict, List, Any, Optional, Union
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from PIL import Image
+
+class CodeInterpreter:
+    def __init__(self, allowed_modules=None, max_execution_time=30, working_directory=None):
+        """Initialize the code interpreter with safety measures."""
+        self.allowed_modules = allowed_modules or [
+            "numpy", "pandas", "matplotlib", "scipy", "sklearn", 
+            "math", "random", "statistics", "datetime", "collections",
+            "itertools", "functools", "operator", "re", "json",
+            "sympy", "networkx", "nltk", "PIL", "pytesseract", 
+            "cmath", "uuid", "tempfile", "requests", "urllib"
+        ]
+        self.max_execution_time = max_execution_time
+        self.working_directory = working_directory or os.path.join(os.getcwd()) 
+        if not os.path.exists(self.working_directory):
+            os.makedirs(self.working_directory)
+        
+        self.globals = {
+            "__builtins__": __builtins__,
+            "np": np,
+            "pd": pd,
+            "plt": plt,
+            "Image": Image,
+        }
+        self.temp_sqlite_db = os.path.join(tempfile.gettempdir(), "code_exec.db")
+
+    def execute_code(self, code: str, language: str = "python") -> Dict[str, Any]:
+        """Execute the provided code in the selected programming language."""
+        language = language.lower()
+        execution_id = str(uuid.uuid4())
+        
+        result = {
+            "execution_id": execution_id,
+            "status": "error",
+            "stdout": "",
+            "stderr": "",
+            "result": None,
+            "plots": [],
+            "dataframes": []
+        }
+        
+        try:
+            if language == "python":
+                return self._execute_python(code, execution_id)
+            elif language == "bash":
+                return self._execute_bash(code, execution_id)
+            elif language == "sql":
+                return self._execute_sql(code, execution_id)
+            elif language == "c":
+                return self._execute_c(code, execution_id)
+            elif language == "java":
+                return self._execute_java(code, execution_id)
+            else:
+                result["stderr"] = f"Unsupported language: {language}"
+        except Exception as e:
+            result["stderr"] = str(e)
+        
+        return result
+
+    def _execute_python(self, code: str, execution_id: str) -> dict:
+        output_buffer = io.StringIO()
+        error_buffer = io.StringIO()
+        result = {
+            "execution_id": execution_id,
+            "status": "error",
+            "stdout": "",
+            "stderr": "",
+            "result": None,
+            "plots": [],
+            "dataframes": []
+        }
+        
+        try:
+            exec_dir = os.path.join(self.working_directory, execution_id)
+            os.makedirs(exec_dir, exist_ok=True)
+            plt.switch_backend('Agg')
+            
+            with contextlib.redirect_stdout(output_buffer), contextlib.redirect_stderr(error_buffer):
+                exec_result = exec(code, self.globals)
+
+                if plt.get_fignums():
+                    for i, fig_num in enumerate(plt.get_fignums()):
+                        fig = plt.figure(fig_num)
+                        img_path = os.path.join(exec_dir, f"plot_{i}.png")
+                        fig.savefig(img_path)
+                        with open(img_path, "rb") as img_file:
+                            img_data = base64.b64encode(img_file.read()).decode('utf-8')
+                            result["plots"].append({
+                                "figure_number": fig_num,
+                                "data": img_data
+                            })
+
+                for var_name, var_value in self.globals.items():
+                    if isinstance(var_value, pd.DataFrame) and len(var_value) > 0:
+                        result["dataframes"].append({
+                            "name": var_name,
+                            "head": var_value.head().to_dict(),
+                            "shape": var_value.shape,
+                            "dtypes": str(var_value.dtypes)
+                        })
+                
+            result["status"] = "success"
+            result["stdout"] = output_buffer.getvalue()
+            result["result"] = exec_result
+            
+        except Exception as e:
+            result["status"] = "error"
+            result["stderr"] = f"{error_buffer.getvalue()}\n{traceback.format_exc()}"
+        
+        return result
+
+    def _execute_bash(self, code: str, execution_id: str) -> dict:
+        try:
+            completed = subprocess.run(
+                code, shell=True, capture_output=True, text=True, timeout=self.max_execution_time
+            )
+            return {
+                "execution_id": execution_id,
+                "status": "success" if completed.returncode == 0 else "error",
+                "stdout": completed.stdout,
+                "stderr": completed.stderr,
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }
+        except subprocess.TimeoutExpired:
+            return {
+                "execution_id": execution_id,
+                "status": "error",
+                "stdout": "",
+                "stderr": "Execution timed out.",
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }
+
+    def _execute_sql(self, code: str, execution_id: str) -> dict:
+        result = {
+            "execution_id": execution_id,
+            "status": "error",
+            "stdout": "",
+            "stderr": "",
+            "result": None,
+            "plots": [],
+            "dataframes": []
+        }
+        try:
+            conn = sqlite3.connect(self.temp_sqlite_db)
+            cur = conn.cursor()
+            cur.execute(code)
+            if code.strip().lower().startswith("select"):
+                columns = [description[0] for description in cur.description]
+                rows = cur.fetchall()
+                df = pd.DataFrame(rows, columns=columns)
+                result["dataframes"].append({
+                    "name": "query_result",
+                    "head": df.head().to_dict(),
+                    "shape": df.shape,
+                    "dtypes": str(df.dtypes)
+                })
+            else:
+                conn.commit()
+
+            result["status"] = "success"
+            result["stdout"] = "Query executed successfully."
+
+        except Exception as e:
+            result["stderr"] = str(e)
+        finally:
+            conn.close()
+
+        return result
+
+    def _execute_c(self, code: str, execution_id: str) -> dict:
+        temp_dir = tempfile.mkdtemp()
+        source_path = os.path.join(temp_dir, "program.c")
+        binary_path = os.path.join(temp_dir, "program")
+
+        try:
+            with open(source_path, "w") as f:
+                f.write(code)
+
+            compile_proc = subprocess.run(
+                ["gcc", source_path, "-o", binary_path],
+                capture_output=True, text=True, timeout=self.max_execution_time
+            )
+            if compile_proc.returncode != 0:
+                return {
+                    "execution_id": execution_id,
+                    "status": "error",
+                    "stdout": compile_proc.stdout,
+                    "stderr": compile_proc.stderr,
+                    "result": None,
+                    "plots": [],
+                    "dataframes": []
+                }
+
+            run_proc = subprocess.run(
+                [binary_path],
+                capture_output=True, text=True, timeout=self.max_execution_time
+            )
+            return {
+                "execution_id": execution_id,
+                "status": "success" if run_proc.returncode == 0 else "error",
+                "stdout": run_proc.stdout,
+                "stderr": run_proc.stderr,
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }
+        except Exception as e:
+            return {
+                "execution_id": execution_id,
+                "status": "error",
+                "stdout": "",
+                "stderr": str(e),
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }
+
+    def _execute_java(self, code: str, execution_id: str) -> dict:
+        temp_dir = tempfile.mkdtemp()
+        source_path = os.path.join(temp_dir, "Main.java")
+
+        try:
+            with open(source_path, "w") as f:
+                f.write(code)
+
+            compile_proc = subprocess.run(
+                ["javac", source_path],
+                capture_output=True, text=True, timeout=self.max_execution_time
+            )
+            if compile_proc.returncode != 0:
+                return {
+                    "execution_id": execution_id,
+                    "status": "error",
+                    "stdout": compile_proc.stdout,
+                    "stderr": compile_proc.stderr,
+                    "result": None,
+                    "plots": [],
+                    "dataframes": []
+                }
+
+            run_proc = subprocess.run(
+                ["java", "-cp", temp_dir, "Main"],
+                capture_output=True, text=True, timeout=self.max_execution_time
+            )
+            return {
+                "execution_id": execution_id,
+                "status": "success" if run_proc.returncode == 0 else "error",
+                "stdout": run_proc.stdout,
+                "stderr": run_proc.stderr,
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }
+        except Exception as e:
+            return {
+                "execution_id": execution_id,
+                "status": "error",
+                "stdout": "",
+                "stderr": str(e),
+                "result": None,
+                "plots": [],
+                "dataframes": []
+            }

explore_metadata.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a600d7fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json \n",
+    "with open('metadata.jsonl', 'r') as f: \n",
+    "    json_list = list(f)\n",
+    "\n",
+    "json_QA = []\n",
+    "for json_str in json_list: \n",
+    "    json_data = json.loads(json_str)\n",
+    "    json_QA.append(json_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "fa5d8eb8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "==================================================\n",
+      "Task ID: d1af70ea-a9a4-421a-b9cc-94b5e02f1788\n",
+      "Question: As of the 2020 census, what was the population difference between the largest county seat and smallest county seat, by land area of the county seat, in Washington state? For population figures, please use the official data from data.census.gov. Please report the integer difference.\n",
+      "Level: 2\n",
+      "Final Answer: 736455\n",
+      "Annotator Metadata: \n",
+      "  ├── Steps: \n",
+      "  │      ├── Step 1: Using a web browser, access a search engine and conduct a search, \"Washington cities by area\"\n",
+      "  │      ├── Step 2: Navigate to the second search result, https://en.wikipedia.org/wiki/List_of_municipalities_in_Washington\n",
+      "  │      ├── Step 3: Evaluate the page contents, finding the largest and smallest county seats by land area, Seattle and Cathlamet\n",
+      "  │      ├── Step 4: Using a web browser, navigate to https://data.census.gov/\n",
+      "  │      ├── Step 5: Using the website's search area, conduct a search, Seattle, Washington\n",
+      "  │      ├── Step 6: Record the reported 2020 Decennial Census population of Seattle, Washington, 737,015\n",
+      "  │      ├── Step 7: Using the website's search area, conduct a search, Cathlamet, Washington\n",
+      "  │      ├── Step 8: Record the reported 2020 Decennial Census population of Cathlamet, Washington, 560\n",
+      "  │      ├── Step 9: Using a calculator, find the difference in populations,\n",
+      "  │      ├── \n",
+      "  │      ├── 737,015 - 560\n",
+      "  │      ├── 736,455\n",
+      "  │      ├── Step 10: Report the correct answer to my user in the requested format, \"736,455\"\n",
+      "  ├── Number of steps: 10\n",
+      "  ├── How long did this take?: 5 minutes\n",
+      "  ├── Tools:\n",
+      "  │      ├── 1. A web browser\n",
+      "  │      ├── 2. A search engine\n",
+      "  │      ├── 3. A calculator\n",
+      "  └── Number of tools: 3\n",
+      "==================================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "import random\n",
+    "random_samples = random.sample(json_QA, 1)\n",
+    "for sample in random_samples:\n",
+    "    print(\"=\" * 50)\n",
+    "    print(f\"Task ID: {sample['task_id']}\")\n",
+    "    print(f\"Question: {sample['Question']}\")\n",
+    "    print(f\"Level: {sample['Level']}\")\n",
+    "    print(f\"Final Answer: {sample['Final answer']}\")\n",
+    "    print(f\"Annotator Metadata: \")\n",
+    "    print(f\"  ├── Steps: \")\n",
+    "    for step in sample['Annotator Metadata']['Steps'].split('\\n'):\n",
+    "        print(f\"  │      ├── {step}\")\n",
+    "    print(f\"  ├── Number of steps: {sample['Annotator Metadata']['Number of steps']}\")\n",
+    "    print(f\"  ├── How long did this take?: {sample['Annotator Metadata']['How long did this take?']}\")\n",
+    "    print(f\"  ├── Tools:\")\n",
+    "    for tool in sample['Annotator Metadata']['Tools'].split('\\n'):\n",
+    "        print(f\"  │      ├── {tool}\")\n",
+    "    print(f\"  └── Number of tools: {sample['Annotator Metadata']['Number of tools']}\")\n",
+    "print(\"=\" * 50)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "05076516",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from langchain_huggingface import HuggingFaceEmbeddings\n",
+    "from langchain_community.vectorstores import SupabaseVectorStore\n",
+    "from supabase.client import Client, create_client\n",
+    "\n",
+    "\n",
+    "load_dotenv()\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-mpnet-base-v2\") #  dim=768\n",
+    "\n",
+    "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
+    "supabase_key = os.environ.get(\"SUPABASE_SERVICE_ROLE_KEY\")\n",
+    "supabase: Client = create_client(supabase_url, supabase_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "aa1402e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema import Document\n",
+    "docs = []\n",
+    "cnt = 0 \n",
+    "for sample in json_QA:\n",
+    "    content = f\"Question : {sample['Question']}\\n\\nFinal answer : {sample['Final answer']}\"\n",
+    "    doc = {\n",
+    "        \"id\" : cnt,\n",
+    "        \"content\" : content,\n",
+    "        \"metadata\" : {\n",
+    "            \"source\" : sample['task_id']\n",
+    "        },\n",
+    "        \"embedding\" : embeddings.embed_query(content),\n",
+    "    }\n",
+    "    docs.append(doc)\n",
+    "    cnt += 1\n",
+    "\n",
+    "# upload the documents to the vector database\n",
+    "try:\n",
+    "    response = (\n",
+    "        supabase.table(\"documents2\")\n",
+    "        .insert(docs)\n",
+    "        .execute()\n",
+    "    )\n",
+    "except Exception as exception:\n",
+    "    print(\"Error inserting data into Supabase:\", exception)\n",
+    "\n",
+    "# # Save the documents (a list of dict) into a csv file, and manually upload it to Supabase\n",
+    "# import pandas as pd\n",
+    "# df = pd.DataFrame(docs)\n",
+    "# df.to_csv('supabase_docs.csv',index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "9aa7eb5e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add items to vector database\n",
+    "vector_store = SupabaseVectorStore(\n",
+    "    client=supabase,\n",
+    "    embedding= embeddings,\n",
+    "    table_name=\"documents2\",\n",
+    "    query_name=\"match_documents_2\",\n",
+    ")\n",
+    "retriever = vector_store.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "9eecafd1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\"\n",
+    "# matched_docs = vector_store.similarity_search(query, k=2)\n",
+    "docs = retriever.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "ff917840",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': '840bfca7-4f7b-481a-8794-c560c340185d'}, page_content='Question : On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\\n\\nFinal answer : 80GSFC21M0002')"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "01c8f337",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "List of tools used in all samples:\n",
+      "Total number of tools used: 83\n",
+      "  ├── web browser: 107\n",
+      "  ├── image recognition tools (to identify and parse a figure with three axes): 1\n",
+      "  ├── search engine: 101\n",
+      "  ├── calculator: 34\n",
+      "  ├── unlambda compiler (optional): 1\n",
+      "  ├── a web browser.: 2\n",
+      "  ├── a search engine.: 2\n",
+      "  ├── a calculator.: 1\n",
+      "  ├── microsoft excel: 5\n",
+      "  ├── google search: 1\n",
+      "  ├── ne: 9\n",
+      "  ├── pdf access: 7\n",
+      "  ├── file handling: 2\n",
+      "  ├── python: 3\n",
+      "  ├── image recognition tools: 12\n",
+      "  ├── jsonld file access: 1\n",
+      "  ├── video parsing: 1\n",
+      "  ├── python compiler: 1\n",
+      "  ├── video recognition tools: 3\n",
+      "  ├── pdf viewer: 7\n",
+      "  ├── microsoft excel / google sheets: 3\n",
+      "  ├── word document access: 1\n",
+      "  ├── tool to extract text from images: 1\n",
+      "  ├── a word reversal tool / script: 1\n",
+      "  ├── counter: 1\n",
+      "  ├── excel: 3\n",
+      "  ├── image recognition: 5\n",
+      "  ├── color recognition: 3\n",
+      "  ├── excel file access: 3\n",
+      "  ├── xml file access: 1\n",
+      "  ├── access to the internet archive, web.archive.org: 1\n",
+      "  ├── text processing/diff tool: 1\n",
+      "  ├── gif parsing tools: 1\n",
+      "  ├── a web browser: 7\n",
+      "  ├── a search engine: 7\n",
+      "  ├── a speech-to-text tool: 2\n",
+      "  ├── code/data analysis tools: 1\n",
+      "  ├── audio capability: 2\n",
+      "  ├── pdf reader: 1\n",
+      "  ├── markdown: 1\n",
+      "  ├── a calculator: 5\n",
+      "  ├── access to wikipedia: 3\n",
+      "  ├── image recognition/ocr: 3\n",
+      "  ├── google translate access: 1\n",
+      "  ├── ocr: 4\n",
+      "  ├── bass note data: 1\n",
+      "  ├── text editor: 1\n",
+      "  ├── xlsx file access: 1\n",
+      "  ├── powerpoint viewer: 1\n",
+      "  ├── csv file access: 1\n",
+      "  ├── calculator (or use excel): 1\n",
+      "  ├── computer algebra system: 1\n",
+      "  ├── video processing software: 1\n",
+      "  ├── audio processing software: 1\n",
+      "  ├── computer vision: 1\n",
+      "  ├── google maps: 1\n",
+      "  ├── access to excel files: 1\n",
+      "  ├── calculator (or ability to count): 1\n",
+      "  ├── a file interface: 3\n",
+      "  ├── a python ide: 1\n",
+      "  ├── spreadsheet editor: 1\n",
+      "  ├── tools required: 1\n",
+      "  ├── b browser: 1\n",
+      "  ├── image recognition and processing tools: 1\n",
+      "  ├── computer vision or ocr: 1\n",
+      "  ├── c++ compiler: 1\n",
+      "  ├── access to google maps: 1\n",
+      "  ├── youtube player: 1\n",
+      "  ├── natural language processor: 1\n",
+      "  ├── graph interaction tools: 1\n",
+      "  ├── bablyonian cuniform -> arabic legend: 1\n",
+      "  ├── access to youtube: 1\n",
+      "  ├── image search tools: 1\n",
+      "  ├── calculator or counting function: 1\n",
+      "  ├── a speech-to-text audio processing tool: 1\n",
+      "  ├── access to academic journal websites: 1\n",
+      "  ├── pdf reader/extracter: 1\n",
+      "  ├── rubik's cube model: 1\n",
+      "  ├── wikipedia: 1\n",
+      "  ├── video capability: 1\n",
+      "  ├── image processing tools: 1\n",
+      "  ├── age recognition software: 1\n",
+      "  ├── youtube: 1\n"
+     ]
+    }
+   ],
+   "source": [
+    "# list of the tools used in all the samples\n",
+    "from collections import Counter, OrderedDict\n",
+    "\n",
+    "tools = []\n",
+    "for sample in json_QA:\n",
+    "    for tool in sample['Annotator Metadata']['Tools'].split('\\n'):\n",
+    "        tool = tool[2:].strip().lower()\n",
+    "        if tool.startswith(\"(\"):\n",
+    "            tool = tool[11:].strip()\n",
+    "        tools.append(tool)\n",
+    "tools_counter = OrderedDict(Counter(tools))\n",
+    "print(\"List of tools used in all samples:\")\n",
+    "print(\"Total number of tools used:\", len(tools_counter))\n",
+    "for tool, count in tools_counter.items():\n",
+    "    print(f\"  ├── {tool}: {count}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

image_processing.py

@@ -0,0 +1,26 @@
+import os
+import io
+import base64
+import uuid
+from PIL import Image
+
+# Helper functions for image processing
+def encode_image(image_path: str) -> str:
+    """Convert an image file to base64 string."""
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+
+def decode_image(base64_string: str) -> Image.Image:
+    """Convert a base64 string to a PIL Image."""
+    image_data = base64.b64decode(base64_string)
+    return Image.open(io.BytesIO(image_data))
+
+
+def save_image(image: Image.Image, directory: str = "image_outputs") -> str:
+    """Save a PIL Image to disk and return the path."""
+    os.makedirs(directory, exist_ok=True)
+    image_id = str(uuid.uuid4())
+    image_path = os.path.join(directory, f"{image_id}.png")
+    image.save(image_path)
+    return image_path

requirements.txt

@@ -0,0 +1,20 @@
+gradio
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+pytesseract
+matplotlib

system_prompt.txt

@@ -0,0 +1,5 @@
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, 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.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 

view_hf_course_questions.py

@@ -0,0 +1,27 @@
+import requests
+import json
+
+questions_url  = "https://agents-course-unit4-scoring.hf.space/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.")
+    else:
+        print(f"Fetched {len(questions_data)} questions.")
+        for sample in questions_data:
+            print("="*20)
+            print(f"Task ID: {sample['task_id']}")
+            print(f"Origin GAIA File: {sample['file_name']}")
+            print(f"Level: {sample['Level']}")
+            print(f"Question: {sample['question']}")
+            print("="*20)
+except requests.exceptions.RequestException as e:
+    print(f"Error fetching questions: {e}")
+except requests.exceptions.JSONDecodeError as e:
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+except Exception as e:
+    print(f"An unexpected error occurred fetching questions: {e}")