Update tools.py

tools.py

@@ -3,6 +3,11 @@ from langchain_community.tools.tavily_search import TavilySearchResults
 from youtube_transcript_api import YouTubeTranscriptApi
 from langchain_community.document_loaders import WikipediaLoader
 import pandas as pd
+import whisper
+import os
+import tempfile
+
+whisper_model = whisper.load_model("base")
 
 @tool
 def add(a: int, b: int) -> int:
@@ -54,6 +59,9 @@ def divide(a: int, b: int) -> int:
 def read_excel_summary(file_path: str) -> str:
     """
     Reads an Excel file and returns basic summary statistics, column names, and row count.
+
+    Args:
+        file_path: The path to the Excel file
     """
     try:
         df = pd.read_excel(file_path, engine="openpyxl")
@@ -94,6 +102,21 @@ def wiki_search(query: str) -> str:
         ])
     return {"wiki_results": formatted_search_docs}
 
+@tool
+def transcribe_audio(file_path: str) -> str:
+    """
+    Transcribes an audio file (MP3, WAV, etc.) to text using Whisper.
+    Returns the transcribed text.
+
+    Args:
+        file_path: the path to the audio file
+    """
+    try:
+        result = whisper_model.transcribe(file_path)
+        return result["text"]
+    except Exception as e:
+        return f"Error during transcription: {str(e)}"
+
 @tool
 def arvix_search(query: str) -> str:
     """Search Arxiv for a query and return maximum 3 result.
@@ -113,6 +136,9 @@ def fetch_youtube_transcript(video_url: str) -> str:
     """
     Fetch transcript of a YouTube video by URL.
     Returns plain text if transcript is available.
+
+    Args:
+        video_url: The YouTube url link to the video
     """
     import re
     video_id_match = re.search(r"(?:v=|youtu\.be/)([\w-]+)", video_url)