Implement basic agent and tools to solve GAIA questions

.env.example

@@ -0,0 +1,15 @@
+# example of file for storing private and user specific environment variables, like keys or system paths
+# rename it to ".env" (excluded from version control by default)
+
+# example, uncomment and adapt for your needs!
+# MY_VAR="/home/user/my/system/path"
+
+# OPENWEATHERMAP_API_KEY=YOUR_OPENWEATHERMAP_API_KEY
+# OPENAI_API_KEY=YOUR_OPENAI_API_KEY
+# FUSE_PUBLIC_KEY=YOUR_FUSE_PUBLIC_KEY
+# LANGFUSE_SECRET_KEY=YOUR_LANGFUSE_SECRET_KEY
+# OTEL_EXPORTER_OTLP_ENDPOINT=https://cloud.langfuse.com/api/public/otel
+# LANGFUSE_HOST=https://cloud.langfuse.com
+# HUGGINGFACE_API_KEY=YOUR_HUGGINGFACE_API_KEY
+# ANTHROPIC_API_KEY=YOUR_ANTHROPIC_API_KEY
+# GROQ_API_KEY=YOUR_GROQ_API_KEY

.gitignore

@@ -0,0 +1,174 @@
+# 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

README.md

@@ -12,4 +12,4 @@ hf_oauth: true
 hf_oauth_expiration_minutes: 480
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

agent.py

@@ -0,0 +1,65 @@
+from typing import Annotated, Optional, TypedDict
+
+from dotenv import find_dotenv, load_dotenv
+from langchain.chat_models import init_chat_model
+from langchain_core.messages import AnyMessage, HumanMessage
+from langgraph.graph.message import add_messages
+from langgraph.prebuilt import create_react_agent
+
+from tools import (add, ask_about_image, divide, get_current_time_and_date,
+                   get_sum, get_weather_info, get_youtube_transcript,
+                   get_youtube_video_info, inspect_file_as_text, multiply,
+                   reverse_text, subtract, visit_website, web_search,
+                   wiki_search)
+
+
+class AgentState(TypedDict):
+    input_file: Optional[str]  # Contains file path
+    messages: Annotated[list[AnyMessage], add_messages]
+
+
+class BasicAgent:
+    def __init__(self):
+        load_dotenv(find_dotenv())
+        model = init_chat_model("groq:meta-llama/llama-4-scout-17b-16e-instruct")
+        system_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."
+            "Give it all you can: I know for a fact that you have access to all the relevant tools to solve it and find "
+            "the correct answer (the answer does exist). Failure or 'I cannot answer' or 'None found' will not be "
+            "tolerated, success will be rewarded. Run verification steps if that's needed, you must make sure you find "
+            "the correct answer! "
+        )
+        tools = [
+            get_weather_info,
+            add,
+            get_sum,
+            subtract,
+            multiply,
+            divide,
+            get_current_time_and_date,
+            wiki_search,
+            web_search,
+            visit_website,
+            inspect_file_as_text,
+            ask_about_image,
+            reverse_text,
+            get_youtube_video_info,
+            get_youtube_transcript,
+        ]
+
+        self.agent = create_react_agent(model=model, tools=tools, prompt=system_prompt)
+        print("BasicAgent initialized.")
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        messages = [HumanMessage(content=question)]
+        response = self.agent.invoke({"messages": messages})
+        response_string = response["messages"][-1].content
+        print(f"Agent's response: {response_string}")
+        return response_string

app.py

@@ -1,34 +1,89 @@
+# import inspect
+import json
 import os
+from pathlib import Path
+from typing import Dict
+from zipfile import ZipFile
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+
+from agent import BasicAgent
 
 # (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:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return 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.
-    """
+with open("prompt.json", mode="r") as f:
+    prompt_template = json.load(f)
+
+
+def post_process_answer(answer: str) -> str:
+    """Post-process the answer to extract the final answer."""
+    if "FINAL ANSWER:" in answer:
+        answer = answer.split("FINAL ANSWER:")[-1].strip()
+    return answer
+
+
+def solve_question(question: Dict[str, str]) -> Dict[str, str]:
+    """Solve the question using the BasicAgent."""
+    agent = BasicAgent()
+    question_text = question.get("question")
+    task_id = question.get("task_id")
+    if not question_text:
+        raise ValueError("Question text is empty.")
+    augmented_question = prompt_template["user_prompt"] + question_text
+    if question.get("file_name"):
+        file_url = DEFAULT_API_URL + "/files"
+        response = requests.get(f"{file_url}/{question['file_name']}", timeout=15)
+        file_path = Path("files") / question["file_name"]
+        # Create files directory if it doesn't exist
+        file_path.parent.mkdir(parents=True, exist_ok=True)
+        with open(file_path, "wb") as f:
+            f.write(response.content)
+        if file_path.suffix == "zip":
+            # If the file is a zip, we need to extract the files and give the LLM the list of files
+            file_paths = []
+            with ZipFile(file_path, "r") as zip_ref:
+                for file_info in zip_ref.infolist():
+                    # Read file content
+                    file_data = zip_ref.read(file_info.filename)
+                    extracted_file_path = file_path / file_info.filename
+                    with open(extracted_file_path, "wb") as extracted_file:
+                        extracted_file.write(file_data)
+                    file_paths.append(str(extracted_file_path))
+            augmented_question += prompt_template["use_files_prompt"] + str(file_paths)
+        else:
+            augmented_question += prompt_template["use_file_prompt"] + str(file_path)
+    try:
+        agent_response = agent(augmented_question)
+        submitted_answer = post_process_answer(agent_response)
+        return {
+            "Task ID": task_id,
+            "Question": augmented_question,
+            "Submitted Answer": submitted_answer,
+            "Full Answer": agent_response,
+        }
+    except Exception as e:
+        print(f"Error running agent on task {task_id}: {e}")
+        return {
+            "Task ID": task_id,
+            "Question": augmented_question,
+            "Submitted Answer": f"AGENT ERROR: {e}",
+            "Full 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
+    # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,62 +93,89 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     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)
+    # In the case of an app running as a hugging Face space, this link points
+    # toward your codebase ( useful for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Fetch Questions
+    # 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("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
+        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
+    # Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+
+    results_file_path = Path("files/results_log.jsonl")
+    results_file_path.parent.mkdir(parents=True, exist_ok=True)
+    solved_task_ids = []
+    if results_file_path.exists():
+        print(f"Results file already exists: {results_file_path}")
+        with open(results_file_path, "r") as results_file:
+            for line in results_file:
+                result = json.loads(line)
+                results_log.append(result)
+                solved_task_ids.append(result["Task ID"])
+    filtered_questions_data = [
+        question
+        for question in questions_data
+        if question["task_id"] not in solved_task_ids
+    ]
+    if solved_task_ids:
+        print(
+            f"Found {len(solved_task_ids)} solved questions. "
+            f"Running agent on remaining {len(filtered_questions_data)} questions."
+        )
+    else:
+        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}"})
+        result = solve_question(item)
+        results_log.append(result)
+    with open(results_file_path, "w") as results_file:
+        for result in results_log:
+            results_file.write(json.dumps(result) + "\n")
+    for result in results_log:
+        answers_payload.append(
+            {
+                "task_id": result["Task ID"],
+                "submitted_answer": result["Submitted Answer"],
+            }
+        )
 
     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)
+        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}'..."
+    # 4. Prepare Submission
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
+    status_update = (
+        f"Agent finished. Submitting {len(answers_payload)} "
+        f"answers for user '{username}'..."
+    )
     print(status_update)
 
     # 5. Submit
@@ -106,7 +188,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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"({result_data.get('correct_count', '?')}/"
+            f"{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
@@ -154,7 +237,7 @@ with gr.Blocks() as demo:
         ---
         **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.
+        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 separate action or even to answer the questions in async.
         """
     )
 
@@ -162,20 +245,19 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    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
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +265,20 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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")
+        print(
+            f"   Repo Tree URL: https://huggingface.co/spaces/"
+            f"{space_id_startup}/tree/main"
+        )
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        print(
+            "ℹ️  SPACE_ID environment variable not found (running locally?). "
+            "Repo URL cannot be determined."
+        )
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)

prompt.json

@@ -0,0 +1,5 @@
+{
+  "user_prompt": "Here is the task:\n",
+  "use_files_prompt": "\n\nTo solve the task above, you will have to use the appropriate tools to extract the relevant information from these attached files:\n",
+  "use_file_prompt": "\n\nTo solve the task above, you will have to use the appropriate tools to extract the relevant information from the attached file:\n"
+}

requirements.txt

@@ -1,2 +1,24 @@
-gradio
-requests
+beautifulsoup4==4.13.4
+datasets==3.5.1
+duckduckgo-search==8.0.1
+gradio==5.29.0
+huggingface-hub==0.30.2
+langchain==0.3.25
+langchain-community==0.3.23
+langchain-core==0.3.58
+langchain_groq==0.3.2
+langchain-huggingface==0.1.2
+langchain-openai==0.3.16
+langgraph==0.4.1
+numpy==2.2.5
+openai-whisper==20240930
+openpyxl==3.1.5
+pandas==2.2.3
+pyrootutils~=1.0.4
+python-dotenv~=1.1.0
+requests==2.32.3
+tabulate==0.9.0
+unstructured[pdf,docx,pptx]==0.17.2
+wikipedia~=1.4.0
+youtube-transcript-api==1.0.3
+yt-dlp==2025.4.30

tools.py

@@ -0,0 +1,359 @@
+import base64
+import os
+from datetime import datetime
+
+import pandas as pd
+import requests
+import whisper
+import wikipedia
+from dotenv import find_dotenv, load_dotenv
+from langchain.chat_models import init_chat_model
+from langchain_community.document_loaders import (
+    UnstructuredPDFLoader, UnstructuredPowerPointLoader,
+    UnstructuredWordDocumentLoader, WebBaseLoader)
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.tools import tool
+from youtube_transcript_api import YouTubeTranscriptApi
+from yt_dlp import YoutubeDL
+
+
+@tool
+def get_weather_info(location: str) -> str:
+    """Fetches dummy weather information for a given location.
+
+    Usage:
+    ```
+    # Initialize the tool
+    weather_info_tool = Tool(
+        name="get_weather_info",
+        func=get_weather_info,
+        description="Fetches weather information for a given location.")
+    ```
+    """
+    load_dotenv(find_dotenv())
+    api_key = os.getenv("OPENWEATHERMAP_API_KEY")
+    url = (
+        f"https://api.openweathermap.org/data/2.5/"
+        f"weather?q={location}&appid={api_key}&units=metric"
+    )
+
+    res = requests.get(url, timeout=15)
+    data = res.json()
+    humidity = data["main"]["humidity"]
+    pressure = data["main"]["pressure"]
+    wind = data["wind"]["speed"]
+    description = data["weather"][0]["description"]
+    temp = data["main"]["temp"]
+    min_temp = data["main"]["temp_min"]
+    max_temp = data["main"]["temp_max"]
+    return (
+        f"Weather in {location}: {description}, "
+        f"Temperature: {temp}°C, Min: {min_temp}°C, Max: {max_temp}°C, "
+        f"Humidity: {humidity}%, Pressure: {pressure} hPa, "
+        f"Wind Speed: {wind} m/s"
+    )
+
+
+@tool
+def add(a: int, b: int) -> int:
+    """Adds two numbers together.
+
+    Args:
+        a (int): The first number.
+        b (int): The second number.
+    """
+    return a + b
+
+
+@tool
+def get_sum(list_of_numbers: list[int]) -> int:
+    """Sums a list of numbers.
+
+    Args:
+        list_of_numbers (list[int]): The list of numbers to sum.
+    """
+    return sum(list_of_numbers)
+
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtracts the second number from the first.
+
+    Args:
+        a (int): The first number.
+        b (int): The second number.
+    """
+    return a - b
+
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiplies two numbers together.
+
+    Args:
+        a (int): The first number.
+        b (int): The second number.
+    """
+    return a * b
+
+
+@tool
+def divide(a: int, b: int) -> float:
+    """Divides the first number by the second.
+
+    Args:
+        a (int): The first number.
+        b (int): The second number.
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+
+@tool
+def get_current_time_and_date() -> str:
+    """Returns the current time and date in ISO format."""
+    return datetime.now().isoformat()
+
+
+@tool
+def reverse_text(text: str) -> str:
+    """Reverses the given text.
+
+    Args:
+        text (str): The text to reverse.
+    """
+    return text[::-1]
+
+
+@tool
+def wiki_search(query: str) -> str:
+    """Searches Wikipedia for a given query and returns the summary.
+
+    Args:
+        query (str): The search query.
+    """
+    search_results = wikipedia.search(query)
+    if not search_results:
+        return "No results found."
+    page_title = search_results[0]
+    summary = wikipedia.summary(page_title)
+    # Alternatively wikipedia.page(page_title).content[:max_length]
+    return f"Title: {page_title}\n\nSummary: {summary}"
+
+
+@tool
+def web_search(query: str) -> str:
+    """Searches the web for a given query and returns the first result.
+
+    Args:
+        query (str): The search query.
+    """
+    search_tool = DuckDuckGoSearchRun()
+    results = search_tool.invoke(query)
+    if results:
+        return results
+    else:
+        return "No results found."
+
+
+@tool
+def visit_website(url: str) -> str:
+    """Visits a website and returns the content.
+
+    Args:
+        url (str): The URL of the website to visit.
+    """
+    loader = WebBaseLoader(url)
+    documents = loader.load()
+    if documents:
+        return documents[0].page_content
+    else:
+        return "No content found."
+
+
+@tool
+def get_youtube_transcript(video_url: str, return_timestamps: bool = False) -> str:
+    """Fetches the transcript of a YouTube video.
+
+    Args:
+        video_url (str): The URL of the YouTube video.
+        return_timestamps (bool): If True, returns timestamps with the transcript. Otherwise, returns only the text.
+    """
+    try:
+        video_id = video_url.split("v=")[-1]
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        if return_timestamps:
+            sentences = []
+            for t in transcript:
+                start = t["start"]
+                end = start + t["duration"]
+                sentences.append(f"{start:.2f} - {end:.2f}: {t['text']}")
+            return "\n".join(sentences)
+        else:
+            return "\n".join([t["text"] for t in transcript])
+    except Exception as e:
+        return f"Error fetching transcript: {e}"
+
+
+@tool
+def get_youtube_video_info(video_url: str) -> str:
+    """Fetches information about a YouTube video.
+
+    Args:
+        video_url (str): The URL of the YouTube video.
+    """
+    try:
+        ydl_opts = {
+            "quiet": True,
+            "skip_download": True,
+        }
+        with YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(video_url, download=False)
+        video_info = {
+            "Title": info.get("title"),
+            "Description": info.get("description"),
+            "Uploader": info.get("uploader"),
+            "Upload date": info.get("upload_date"),
+            "Duration": info.get("duration"),
+            "View count": info.get("view_count"),
+            "Like count": info.get("like_count"),
+        }
+        video_info_filtered = {k: v for k, v in video_info.items() if v is not None}
+        video_info_str = "\n".join(
+            [f"{k}: {v}" for k, v in video_info_filtered.items()]
+        )
+        return video_info_str
+    except Exception as e:
+        return f"Error fetching video info: {e}"
+
+
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+
+@tool
+def ask_about_image(image_path: str, question: str) -> str:
+    """Performs vision-based question answering on an image.
+
+    Args:
+        image_path (str): The path to the image file.
+        question (str): Your question about the image, as a natural language sentence. Provide as much context as possible.
+    """
+    load_dotenv(find_dotenv())
+    llm = init_chat_model("groq:meta-llama/llama-4-scout-17b-16e-instruct")
+    prompt = ChatPromptTemplate(
+        [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": "Please write a concise caption for the image that helps answer the following question: {question}",
+                    },
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": "data:image/jpeg;base64,{base64_image}",
+                        },
+                    },
+                ],
+            }
+        ]
+    )
+    chain = prompt | llm
+    response = chain.invoke(
+        {"question": question, "base64_image": encode_image(image_path)}
+    )
+    return response.text()
+
+
+def transcribe_audio(audio_path: str) -> str:
+    """Transcribes audio to text.
+
+    Args:
+        audio_path (str): The path to the audio file.
+    """
+    model = whisper.load_model("base")
+    result = model.transcribe(audio_path)
+    text = result.text
+    return text
+
+
+def get_table_description(table: pd.DataFrame) -> str:
+    """Generates a description of the table. If applicable, calculates sum and mean of numeric
+    columns.
+
+    Args:
+        table (pd.DataFrame): The table to describe.
+    """
+    if table.empty:
+        return "The table is empty."
+    description = []
+    total_sum = 0
+    for column in table.select_dtypes(include=[int, float]).columns:
+        column_sum = table[column].sum()
+        column_mean = table[column].mean()
+        description.append(
+            f"Column '{column}': Sum = {column_sum}, Mean = {column_mean:.2f}"
+        )
+        total_sum += column_sum
+    if total_sum:
+        description.append(f"Total Sum of all numeric columns: {total_sum}")
+    if description:
+        description = "\n".join(description)
+    else:
+        description = "No numeric columns to summarize."
+    # Add the number of rows and columns
+    description += f"\n\nTable has {table.shape[0]} rows and {table.shape[1]} columns."
+    df_as_markdown = table.to_markdown()
+    description += f"\n\nTable:\n{df_as_markdown}"
+    return description
+
+
+@tool
+def inspect_file_as_text(file_path: str) -> str:
+    """This tool reads a file as markdown text. It handles [".csv", ".xlsx", ".pptx", ".wav",
+    ".mp3", ".m4a", ".flac", ".pdf", ".docx"], and all other types of text files. IT DOES NOT
+    HANDLE IMAGES.
+
+    Args:
+        file_path (str): The path to the file you want to read as text. If it is an image, use `vision_qa` tool.
+    """
+    try:
+        suffix = os.path.splitext(file_path)[-1]
+        if suffix in [".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff"]:
+            raise Exception(
+                "Cannot use inspect_file_as_text tool with images: use `vision_qa` tool instead!"
+            )
+        if suffix in [".csv", ".tsv", ".xlsx"]:
+            if suffix == ".csv":
+                df = pd.read_csv(file_path)
+            elif suffix == ".tsv":
+                df = pd.read_csv(file_path, sep="\t")
+            elif suffix == ".xlsx":
+                df = pd.read_excel(file_path)
+            else:
+                raise Exception(f"Unsupported file type: {suffix}")
+            table_description = get_table_description(df)
+            return table_description
+        elif suffix == ".pptx":
+            doc = UnstructuredPowerPointLoader(file_path)
+            return doc.load()[0].page_content
+        elif suffix == ".pdf":
+            doc = UnstructuredPDFLoader(file_path)
+            return doc.load()[0].page_content
+        elif suffix == ".docx":
+            doc = UnstructuredWordDocumentLoader(file_path)
+            return doc.load()[0].page_content
+        elif suffix in [".wav", ".mp3", ".m4a", ".flac"]:
+            return transcribe_audio(file_path)
+        else:
+            # All other text files
+            with open(file_path, "r", encoding="utf-8") as file:
+                content = file.read()
+            return content
+    except Exception as e:
+        return f"Error file: {e}"