import json import csv import openpyxl import whisper import os import requests from smolagents.tools import tool DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" def _download_file(file_name: str) -> None: if not os.path.exists(file_name): url = f"{DEFAULT_API_URL}/files/{file_name.split('.')[-2]}" r = requests.get(url) with open(file_name, "wb") as f: f.write(r.content) @tool def read_file_as_text(file_name: str) -> str: """ Opens a file and returns its content as readable text. Supports 'txt', 'json', 'csv', 'xlsx', and 'mp3' (for mp3, it transcribes speech to text). Args: file_name (str): The path or name of the file. Returns: str: The content of the file as text, or transcribed speech if 'mp3'. """ _download_file(file_name) file_type = file_name.split(".")[-1] try: if file_type in {"txt", "py"}: with open(file_name, "r", encoding="utf-8") as f: return f.read() elif file_type == "json": with open(file_name, "r", encoding="utf-8") as f: data = json.load(f) return json.dumps(data, indent=2) elif file_type == "csv": with open(file_name, "r", encoding="utf-8") as f: reader = csv.reader(f) rows = list(reader) return "\n".join([", ".join(row) for row in rows]) elif file_type == "xlsx": wb = openpyxl.load_workbook(file_name, data_only=True) sheet = wb.active content = [] for row in sheet.iter_rows(values_only=True): content.append(", ".join(str(cell) if cell is not None else "" for cell in row)) return "\n".join(content) elif file_type == "mp3": w = whisper.load_model("base") res = w.transcribe(file_name) return res["text"] else: return f"File type '{file_type}' not supported." except FileNotFoundError: return f"File '{file_name}' not found." except Exception as e: return f"Error opening file '{file_name}': {str(e)}"