Пробуем запустить space.

.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

agent.py

@@ -0,0 +1,72 @@
+from smolagents import CodeAgent, ToolCallingAgent, TransformersModel
+from tools import available_tools
+import torch
+import json
+import os
+
+
+def instantiate_agent(executor_type : str="local", agent_type: str ="tool_calling", tools = available_tools) -> CodeAgent:
+    
+    # Локальный агент с моделью кодером
+    if executor_type == "local" and agent_type == "code":
+
+        code_system_prompt = os.getenv("CODE_AGENT_SYSTEM_PROMPT")
+
+        print(code_system_prompt)
+
+        hf_model = "Qwen/Qwen2.5-Coder-32B-Instruct"
+        # hf_model = "Qwen/Qwen2.5-Coder-7B-Instruct"
+        # hf_model = "Qwen/Qwen2.5-Coder-3B-Instruct"   # For debug purpose
+
+        llm = TransformersModel(model_id=hf_model,
+                                device_map="cuda",
+                                torch_dtype=torch.bfloat16,
+                                )
+        
+        agent = CodeAgent(tools=available_tools,
+                          model=llm,
+                          additional_authorized_imports=['pandas','numpy', 'numpy.*', 'csv', 'markdownify', 'requests'],
+                          prompt_templates=({'system_prompt': code_system_prompt}),
+                          max_steps=20,
+                          )
+        return agent
+    
+    elif executor_type == "local" and agent_type == "tool_calling":
+
+        tool_call_system_prompt = os.getenv("TOOL_CALLING_SYSTEM_PROMPT")
+        
+        print(tool_call_system_prompt)
+
+        hf_model = "Qwen/Qwen2.5-7B-Instruct"
+        # hf_model = "Qwen/Qwen2.5-3B-Instruct"         # For debug purpose
+        # hf_model = "google/gemma-2-2b-it"
+        # hf_model = "Qwen/Qwen2.5-7B-Instruct-1M"
+
+        llm = TransformersModel(model_id=hf_model, device_map="cuda", torch_dtype=torch.bfloat16)
+
+        agent = ToolCallingAgent(tools=available_tools, model=llm, max_steps=3, planning_interval=1)
+        agent.prompt_templates["system_prompt"] = agent.prompt_templates["system_prompt"] + tool_call_system_prompt
+
+
+
+        return agent 
+    
+    else:
+        raise ValueError(f"Unsupported executor type: {executor_type} or agent type: {agent_type}")
+
+
+if __name__ == "__main__":
+
+    agent = instantiate_agent()
+
+    question = """
+Question: Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations.
+
+Tools required:
+1. search engine
+
+Approximately, the problem can be solved as follows::
+1. Search "Kuznetzov Nedoshivina 2010"
+2. Find the 2010 paper "A catalogue of type specimens of the Tortricidae described by V. I. Kuznetzov from Vietnam and deposited in the Zoological Institute, St. Petersburg"
+"""
+    agent.run(question)

app.py

@@ -0,0 +1,213 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+
+from huggingface_hub import login
+from datasets import load_dataset
+from dotenv import load_dotenv
+
+from agent import instantiate_agent
+from gaia_dataset import gaia_dataset, get_question
+
+# (Сохраните константы как есть)
+# --- Константы ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+class BasicAgent:
+    
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.agent = instantiate_agent()
+        
+        print("Agent initialized successfully.")
+
+    def __call__(self, question: str) -> str:
+        
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = self.agent.run(question)
+        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.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    # space_id = "artyomboyko/Final_Assignment_Template" # Local inference only!
+
+    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 = get_question(task_id)
+
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        try:
+
+            print("CURRENT QUESTION: ", task_id, question_text)
+            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
+    space_host_startup = "artyomboyko-final-assignment-template.hf.space"
+    space_id_startup = "artyomboyko/Final_Assignment_Template"
+
+    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)

gaia_dataset.py

@@ -0,0 +1,36 @@
+from smolagents import FinalAnswerTool
+from datasets import load_dataset, Dataset
+import json
+
+gaia_dataset = load_dataset("gaia-benchmark/GAIA", "2023_level1", trust_remote_code=True, split="validation")
+
+def get_example_by_feature_value(dataset: Dataset, feature_name: str, feature_value: str):
+
+    for example in dataset:
+        if example[feature_name] == feature_value:
+            return example
+        
+    return None
+
+
+def get_question(task_id: str) -> str:
+
+    question_data = get_example_by_feature_value(gaia_dataset, "task_id", task_id)
+
+    question_text = "Question: " + question_data["Question"] + "\n\n"
+
+    if question_data["file_name"]:
+        question_text = question_text + "File path: " + question_data["file_path"] + "\n\n"
+
+    question_text = question_text + "Tools required:\n" + question_data["Annotator Metadata"]['Tools'] + "\n\n"
+    question_text = question_text + "Approximately, the problem can be solved as follows::\n" + question_data["Annotator Metadata"]["Steps"] + "\n\n"
+
+    return question_text
+
+
+
+if __name__ == "__main__":
+    id = "a1e91b78-d3d8-4675-bb8d-62741b4b68a6" # Question without file
+    # id = "cca530fc-4052-43b2-b130-b30968d8aa44" # Question with file
+
+    print(get_question(id))

packages.txt

@@ -0,0 +1,19 @@
+build-essential
+cmake
+curl 
+ffmpeg
+g++
+git
+git-lfs
+htop
+iotop
+libxml2
+libopenblas-dev
+libssl-dev
+python3-pip
+python3-wheel
+python3-setuptools
+python3-packaging
+python-is-python3
+wget
+zlib1g

requirements.txt

@@ -0,0 +1,32 @@
+accelerate
+av
+beautifulsoup4
+bitsandbytes
+datasets
+duckduckgo-search
+evaluate
+ffmpeg
+gradio
+gradio[oauth]
+gradio_client
+hf_xet
+huggingface_hub
+ipykernel
+ipython
+ipywidgets
+librosa
+openai
+opencv-python
+openpyxl
+pyproject-toml
+requests
+selenium
+smolagents[all]==1.9.2
+tavily-python
+tqdm
+transformers
+torchao
+uuid
+wikipedia
+yt_dlp
+qwen_vl_utils

tools.py

@@ -0,0 +1,397 @@
+from smolagents import DuckDuckGoSearchTool,  VisitWebpageTool, SpeechToTextTool, FinalAnswerTool, PythonInterpreterTool, tool
+
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor, pipeline
+from qwen_vl_utils import process_vision_info
+import torch
+
+from typing import List, Any, Optional
+from markdownify import markdownify
+from tavily import TavilyClient
+
+import os
+import uuid
+import json
+import traceback
+import requests
+import datetime
+import yt_dlp
+import pandas as pd
+import wikipedia as wiki
+from bs4 import BeautifulSoup
+
+import requests
+from bs4 import BeautifulSoup
+from markdownify import markdownify as md
+
+
+@tool
+def video_analyzer(file_path: str, query: str) -> str:
+    """
+
+    An artificial intelligence tool that takes as input a text string containing 
+    the absolute path to a video file in MP4 format and a string with 
+    a detailed text query to analyze the video.
+
+    Args:
+        file_path: Absolute path to an Excel file.
+        query: detailed text query to analyze the video.
+
+    Returns: 
+        str: Row of text with the results of video file analysis
+
+    Examples:
+        >>> video_analyzer("/test/1.mp4", "Identify separate bird species. What is the highest number of bird species to be on camera simultaneously?")
+        The video shows a group of Emperor penguins and a single Albatross. Therefore, the highest number of bird species to be on camera simultaneously is 2.
+
+    """
+
+    model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+        "Qwen/Qwen2.5-VL-3B-Instruct", torch_dtype="auto", device_map="auto"
+    )
+
+    processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct")
+
+    text = "You are Qwen, created by Alibaba Cloud. You are a helpful assistant. " + query
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "video", "video": f"file://{file_path}", "fps": 1.0,},
+                {"type": "text", "text": text},
+            ],
+        }
+    ]
+
+    # Preparation for inference
+    text = processor.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    image_inputs, video_inputs = process_vision_info(messages)
+    inputs = processor(
+        text=[text],
+        images=image_inputs,
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    )
+    inputs = inputs.to("cuda")
+
+    # Inference: Generation of the output
+    generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids_trimmed = [
+        out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    ]
+    output_text = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )
+    
+    return output_text[0]
+
+
+# https://wikipedia.readthedocs.io/en/latest/code.html
+@tool
+def wikipedia_available_titles(query: str) -> List[str]:
+    """This insturment returns the titles of the articles available on wikipedia."
+
+    Args:
+        query: str
+            The query that will be used to search for articles on wikipedia.
+    
+    Returns:
+        list : list of strings with available article titles 
+
+    """
+    try:
+        wiki.set_rate_limiting(rate_limit=True, min_wait=datetime.timedelta(milliseconds=100))
+        titles = wiki.search(query)
+    except Exception as e:
+        print("Exception occurred: ", e, "with query: ", query)
+
+    return titles
+    
+
+@tool
+def wikipedia_summary(title: str) -> str:
+    """This instrument returns the summary of a wikipedia article.
+
+    Args:
+        title: str
+            The title of the wikipedia article to summarize.
+
+    Returns:
+        str : The summary of the article.
+    """
+    try:
+        wiki.set_rate_limiting(rate_limit=True, min_wait=datetime.timedelta(milliseconds=100))
+        summary = wiki.summary(title, )
+    except Exception as e:
+        print("Exception occurred: ", e, "with title: ", title)
+        summary = ""
+
+    return summary
+
+
+@tool
+def reverse_text(text: str) -> str:
+    """This tool returns a reversed string of text.
+
+    Args:
+        text: str
+            The line of text to be reversed
+
+    Returns:
+        str : Reversed line of text.
+
+    Examples:
+        >>> reverse_text("ecnetnes siht dnatsrednu uoy fI")
+        If you understand this sentence
+        
+    """
+    return text[::-1]
+
+
+tavily_access_token = os.getenv("TAVILY_ACCESS_TOKEN")
+
+
+@tool
+def tavily_search(request: str) -> str:
+    """
+    This is an ultimatum tool for finding information on the internet.
+    Don't use it to search YouTube! It's useless!
+
+    Args:
+        request: A string containing a query to search in the Internet.
+
+    Returns:
+        str: JSON string with execution results containing the following fields:
+            - query: The search query to execute with Tavily.
+            - answer: A short answer to the user's query, generated by an LLM. Included in the response only if include_answer is requested 
+            - images: List of query-related images. If include_image_descriptions is true, each item will have url and description.
+            - results: A list of sorted search results, ranked by relevancy. Contains the following fields:
+                - title: The title of the search result.
+                - url: The URL of the search result.
+                - content: A short description of the search result.
+                - score: The relevance score of the search result.
+                - raw_content: The cleaned and parsed HTML content of the search result. Only if include_raw_content is true.
+    """
+
+    client = TavilyClient(tavily_access_token)
+    response = client.search(query=request, include_raw_content=False, max_results=3, search_depth='advanced')
+
+    return response                            
+
+@tool
+def tavily_extract_web_page(url: str) -> str:
+    """
+    This is an ultimatum tool that allows you to retrieve the contents of a web page. 
+    In other words, to view the website. Don't use YouTube to extract pages! It's useless!
+
+    Args:
+        url: The URL of the web page from which you want to retrieve information.
+
+    Returns:
+        str: The parsed and cleaned HTML content of the web page. The raw content extracted.
+    """
+
+    client = TavilyClient(tavily_access_token)
+    response = client.extract([url], extract_depth="advanced")
+
+    return response["results"][0]['raw_content']
+
+
+@tool
+def download_youtube_video_audio(url: str) -> tuple[bool, str, str]:
+    """
+    Downloads a YouTube video to a specified directory. Video and audio are downloaded separately.
+    The video is downloaded in mp4 format and the audio in mp3 format.
+
+    Args:
+        url: The URL of the YouTube video.
+
+    Returns: 
+        Returns three strings:
+            bool: Execution result. True - success, False - error in file upload process.
+            str: The absolute path to the downloaded video file.
+            str: The absolute path to the downloaded audio file.
+    """
+    try:
+        # Генерация имен файлов
+        guid = str(uuid.uuid4())
+        output_dir="./downloads"
+
+        abs_output_dir = os.path.abspath(output_dir)
+
+        video_path = os.path.join(abs_output_dir, f"{guid}.mp4")
+        audio_path = os.path.join(abs_output_dir, f"{guid}.mp3") # Расширение будет добавлено позже автоматически
+
+        format_priority = (
+            'bestvideo[height=360][ext=mp4]/'      # 1. Точное 720p в MP4
+            'bestvideo[height<360][ext=mp4]/'      # 2. Наилучшее качество ниже 720p в MP4 
+            'worstvideo[height>=360]'    # 3. Если нет 720p, берёт лучшее (макс. 1080p)
+        )
+
+        video_options = {
+            'format': format_priority,
+            'outtmpl': video_path,
+            'quiet': True,
+            'no_warnings': True,
+        }
+
+        # Настройки для аудио
+        audio_options = {
+            'format': 'bestaudio/best[ext=mp3]',
+            'outtmpl': audio_path,
+            'quiet': True,
+            'no_warnings': True,
+        }
+
+        # Создание папки, если она не существует.
+        os.makedirs(output_dir, exist_ok=True)  
+
+        # Загрузка
+        with yt_dlp.YoutubeDL(video_options) as ydl:
+            ydl.download([url])
+        
+        with yt_dlp.YoutubeDL(audio_options) as ydl:
+            ydl.download([url])
+        
+        return True, video_path, audio_path
+
+    except Exception as e:
+
+        # Удаляем файлы если что-то пошло не так
+        for path in [video_path, audio_path]:
+            try: 
+                os.remove(path)
+            except: 
+                pass
+        
+        return False, None, None
+    
+
+@tool
+def transcribe_audio_file(path: str) -> str:
+    """
+    The tool takes as input the absolute path to the mp3 file to be transcribed and returns the English text.
+
+    Args:
+        path: Absolute path to an audio file in mp3 format.
+
+    Returns: 
+        str: A string of transcripts of an audio file in English.
+    """
+
+    device = "cuda:0" if torch.cuda.is_available() else "cpu"
+
+    transcribe = pipeline(
+        "automatic-speech-recognition",
+        model="openai/whisper-base",
+        chunk_length_s=30,
+        batch_size=2,
+        device=device,
+    )
+    try:
+        transcription  = transcribe(path, batch_size=8, generate_kwargs={"language": "english", "task": "transcribe"})["text"]
+    except Exception as e:
+        print("ERROR: {e}, {path}")
+        traceback.print_exc()
+        return None
+
+    return transcription
+
+@tool
+def get_excel_data(file_path: str) -> pd.DataFrame:
+    """
+    The tool takes as input an absolute path to the Excel file whose contents are to be output and returns a string of text with the contents of the file.
+
+    Args:
+        file_path: Absolute path to an Excel file.
+
+    Returns: 
+        str: A row with the contents of an Excel file
+    """
+    return str(pd.read_excel(file_path))
+
+
+@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
+
+
+available_tools = [
+    reverse_text,
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    download_youtube_video_audio,
+    transcribe_audio_file,
+    get_excel_data,
+    wikipedia_available_titles,
+    wikipedia_summary,
+    video_analyzer,
+    FinalAnswerTool(),
+    DuckDuckGoSearchTool(),
+    tavily_search,
+    tavily_extract_web_page,
+    # VisitWebpageTool(),
+    PythonInterpreterTool(),
+    # SpeechToTextTool(),
+
+]
+
+
+if __name__ == "__main__":
+    file = "/workspaces/Final_Assignment_Template/downloads/60cc887f-cb60-4fc6-88c8-a8bbc6a4659a.mp4"
+    text = "Identify separate bird species. What is the highest number of bird species to be on camera simultaneously?"
+
+    print(video_analyzer(file, text))