tools.py

from smolagents import Tool
import wikipedia
from bs4 import BeautifulSoup
import io 
import pandas as pd
import requests 
from tabulate import tabulate
import os
import tempfile
from pathlib import Path
from PIL import Image
from io import BytesIO
from dotenv import find_dotenv, load_dotenv
from openai import OpenAI
from llama_index.readers.youtube_transcript import YoutubeTranscriptReader
from google import genai
from google.genai import types
import chess
class WikipediaSearch(Tool):
    name = "wikipedia_search"
    description = "Fetches wikipedia pages."
    inputs = {
        "query": {
            "type": "string",
            "description": "Query to be searched on wikipedia"
        }
        }
    output_type = "string"

    def forward(self, query:str)->str:
        res = wikipedia.page(query)
        bs = BeautifulSoup(res.html(), 'html.parser')
        text_only = bs.get_text()
        return text_only

class ExcelReader(Tool):
    name = 'excel_processor'
    description = "excel reading tool, processed files of .xlsx and .xls format."
    inputs = {

        "file_path": {
            "type": "string",
            "description": "path to the excel file"
        }
        }
    output_type = "string"
    
    def forward(self, file_path:str)->str:
        df = pd.read_excel(file_path)
        txt_excel = tabulate(df, headers="keys", tablefmt="github", showindex=False)
        return txt_excel
    
class FileReader(Tool):
    name = 'file_reader'
    description = "reads saved files"
    inputs = {

        "file_path": {
            "type": "string",
            "description": "path to the file"
        }
        }
    output_type = "string"
    
    def forward(self, file_path:str)->str:
        with open(file_path, "r") as file:
            content = file.read()
        return content
    
def download_files(task_id, file_name):
    url = f'https://agents-course-unit4-scoring.hf.space/files/{task_id}'
    response = requests.get(url, timeout=15)
    tmp_dir = Path(tempfile.gettempdir()) / "project_files"
    tmp_dir.mkdir(exist_ok=True)
    filepath = os.path.join(tmp_dir, file_name)
    with open(filepath, "wb") as f:
        f.write(response.content)

    return filepath

def get_images(file_format, file_path):
    if file_format in ['png', 'jpeg', 'jpg']:
        images  = [Image.open(file_path).convert("RGB")]
    else:
        images = []

    return images

class AudioTransciber(Tool):
    name = 'audio_transcriber'
    description = "transcribes audio files"
    inputs = {

        "file_path": {
            "type": "string",
            "description": "path to the file"
        }
        }
    output_type = "string"
    
    def forward(self, file_path:str)->str:
        audio = open(file_path, 'rb')
        client = OpenAI(api_key=os.getenv("OPEN_AI_KEY"))
        transcript = client.audio.transcriptions.create(model='whisper-1',
                                         file=audio)
        return transcript
    
class YouTubeTranscipt(Tool):
    name = 'youtube_transcript'
    description = "a tool that returns a transcript for a youtube video. Youtube videos come from urls containing www.youtube.com"
    inputs = {

        "url": {
            "type": "string",
            "description": "url to the youtube video, has 'www.youtube.com' in it."
        }
        }
    output_type = "string"
    
    def forward(self, url:str)->str:
        loader = YoutubeTranscriptReader()
        documents = loader.load_data(ytlinks=[url])
        transcript = documents[0].text
        return transcript
    
class YouTubeVideoUnderstanding(Tool):
    name = 'youtube_video_understanding'
    description = "a tool that processes summarizes what is happenening in a youtube video. Youtube videos come from urls containing www.youtube.com"
    inputs = {
        "url": {
            "type": "string",
            "description": "url to the youtube video, has 'www.youtube.com' in it."
        },
        "prompt": {
            "type": "string",
            "description": "user prompt about the video content"

        }
        }
    output_type = "string"
  
    def forward(self, url:str, prompt:str)->str:
        load_dotenv(find_dotenv())
        client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
        response = client.models.generate_content(
         model='models/gemini-2.0-flash',
            contents=types.Content(
                parts=[
                    types.Part(
                        file_data=types.FileData(file_uri=url)
                    ),
                    types.Part(text=prompt)
                ]
            )
        )
        return response.text
    
class VegetableFruitClassification(Tool):
    name = 'vegetable_fruit_classificaiton'
    description = "a tool that can help classify fruits and vegetables"
    inputs = {
        "prompt": {
            "type": "string",
            "description": "user prompt about fruits or vegetables"

        }
        }
    output_type = "string"
  
    def forward(self, prompt:str)->str:
        load_dotenv(find_dotenv())
        client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
        additional_context = """
        The botanical distinction between fruits and vegetables is anatomical of the plant in question. 
        For example, a tomato has seeds, which would result in reproduction.  Rhubarb is the stalk of a plant, and has no means of proliferation after consumption. 
        A tomato is a botanical fruit and rhubarb is botanically a vegetable. """
        extended_prompt = prompt + additional_context
        response = client.models.generate_content(
        model='models/gemini-2.5-flash-preview-05-20',
            contents=types.Content(
                parts=[
                    types.Part(text=extended_prompt)
                ]
            )
        )
        return response.text
    
class ChessSolver(Tool):
    name = "chess_analysis_tool"
    description = "analyzes the chess board to determine the best next move."
    inputs = {
        "image_path": {
            "type": "string",
            "description": "path to the image showing a chess board."
        },
        "current_player":{
            "type": "string",
            "description": "player whose turn it is. Acceptable inputs are 'black' or 'white'"
        },
        }
    output_type = "string"
        
    def forward(self, image_path:str, current_player:str)->str:
        fen = chess.fen_notation(image_path, current_player)
        best_move = chess.chess_analysis(fen)
        return best_move