gaia_tools.py

import os
import requests
import wikipedia
import pandas as pd
from smolagents import PythonInterpreterTool, tool
from youtube_transcript_api import YouTubeTranscriptApi

@tool
def ReverseTextTool(text: str) -> str:
    """
    Reverses a text string character by character.
    Args:
        text (str): The text to reverse
    Returns:
        str: The reversed text
    """
    return text[::-1]

@tool
def RunPythonFileTool(file_path: str) -> str:
    """
    Executes a Python script loaded from the specified path using the PythonInterpreterTool.
    Args:
        file_path (str): The full path to the python (.py) file containing the Python code.
    Returns:
        str: The output produced by the code execution, or an error message if it fails.
    """
    try:
        with open(file_path, "r") as f:
            code = f.read()
        interpreter = PythonInterpreterTool()
        result = interpreter.run({"code": code})
        return result.get("output", "No output returned.")
    except Exception as e:
        return f"Execution failed: {e}"

@tool
def download_server(url: str, save_path: str) -> str:
    """
    Downloads a file from a URL and saves it to the given path.
    Args:
        url (str): The URL from which to download the file.
        save_path (str): The local file path where the downloaded file will be saved.
    Returns:
        str: A message indicating the result of the download operation.
    """
    try:
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        with open(save_path, "wb") as f:
            f.write(response.content)
        return f"File downloaded to {save_path}"
    except Exception as e:
        return f"Failed to download: {e}"

@tool
def WikipediaSearchTool(query: str) -> str:
    """
    Performs a search on Wikipedia and returns a summary of the result.
    Args:
        query: The search term.
    Returns:
        A string containing the summary of the search result or an error message.
    """
    try:
        summary = wikipedia.summary(query, sentences=3)
        return summary
    except wikipedia.exceptions.PageError:
        return f"Error: No Wikipedia page found for '{query}'."
    except wikipedia.exceptions.DisambiguationError as e:
        return f"Error: Multiple results found for '{query}'. Try a more specific query. Options: {e.options}"
    except Exception as e:
        return f"An unexpected error occurred: {e}"

@tool
def YouTubeVideoAnalysisTool(video_id: str, keyword: str) -> str:
    """
    Fetches the transcript of a YouTube video by its ID and performs a keyword search.
    Args:
        video_id: The ID of the YouTube video.
        keyword: The keyword to search for in the transcript.
    Returns:
        A string indicating if the keyword was found and providing a snippet, or an error message.
    """
    try:
        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
        full_transcript = " ".join([d['text'] for d in transcript_list])
        
        if keyword.lower() in full_transcript.lower():
            index = full_transcript.lower().find(keyword.lower())
            start = max(0, index - 50)
            end = min(len(full_transcript), index + len(keyword) + 50)
            snippet = full_transcript[start:end]
            return f"Keyword '{keyword}' found in the video. Snippet: '...{snippet}...'."
        else:
            return f"Keyword '{keyword}' not found in the video transcript."
    except Exception as e:
        return f"An error occurred while fetching the YouTube transcript: {e}"

@tool
def ExcelFileParserTool(file_path: str, query: str = "get_headers") -> str:
    """
    Reads and queries data from an Excel file at a given path.
    
    Args:
        file_path (str): The path to the Excel file (.xlsx, .xls).
        query (str): The type of query to perform. Defaults to 'get_headers'.
                   Other options include 'find_value:column_name:value_to_find'.
    
    Returns:
        str: A string with the result of the query or an error message.
    """
    try:
        df = pd.read_excel(file_path)
        
        if query == "get_headers":
            return f"Headers found: {', '.join(df.columns.tolist())}"
        
        elif query.startswith("find_value:"):
            parts = query.split(":")
            if len(parts) != 3:
                return "Error: Invalid query format. Use 'find_value:column_name:value_to_find'."
            
            column_name = parts[1]
            value_to_find = parts[2]
            
            if column_name not in df.columns:
                return f"Error: Column '{column_name}' not found."
            
            found_rows = df[df[column_name].astype(str).str.contains(value_to_find, case=False, na=False)]
            
            if not found_rows.empty:
                return f"Value '{value_to_find}' found in column '{column_name}'. Found in the following rows:\n{found_rows.to_string()}"
            else:
                return f"Value '{value_to_find}' not found in column '{column_name}'."
        
        else:
            return "Error: Unknown query type. Supported queries: 'get_headers', 'find_value:column_name:value_to_find'."
            
    except FileNotFoundError:
        return f"Error: File not found at '{file_path}'."
    except Exception as e:
        return f"An unexpected error occurred: {e}"