Update agent.py

agent.py

@@ -3,6 +3,8 @@ import os
 import operator
 import json
 import re
+import requests
+import tempfile
 from youtube_transcript_api import YouTubeTranscriptApi
 from typing import TypedDict, Annotated, Sequence, Union
 from langgraph.graph import StateGraph, END
@@ -149,13 +151,65 @@ def convert_currency(amount: float, from_currency: str, to_currency: str) -> flo
         return round(amount * rates[from_currency.upper()][to_currency.upper()], 2)
     except:
         return "Error: Currency not supported"
-
+@tool
+def process_audio_note(audio_url: str, instructions: str) -> str:
+    """
+    Extract specific information from an audio note based on user instructions. 
+    Handles various requests like recipes, meeting notes, reminders, etc.
+    
+    Args:
+        audio_url: URL of the audio file
+        instructions: Specific instructions for what to extract and how to format
+        
+    Returns:
+        Requested information formatted as specified
+    """
+    try:
+        # Download audio file
+        response = requests.get(audio_url)
+        response.raise_for_status()
+        
+        # Create temporary audio file
+        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_audio:
+            temp_audio.write(response.content)
+            temp_audio_path = temp_audio.name
+        
+        # Transcribe audio using Whisper
+        client = OpenAI()
+        with open(temp_audio_path, "rb") as audio_file:
+            transcript = client.audio.transcriptions.create(
+                model="whisper-large-v3",
+                file=audio_file,
+                response_format="text"
+            )
+        
+        # Create system prompt based on instructions
+        system_prompt = (
+            "You're an audio processing assistant. Carefully follow these instructions:\n"
+            f"{instructions}\n\n"
+            "Transcript of the audio note:\n"
+        )
+        
+        # Process transcript to extract requested information
+        response = client.chat.completions.create(
+            model="gpt-4-turbo",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": transcript}
+            ],
+            max_tokens=1000
+        )
+        
+        return response.choices[0].message.content
+        
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
 # ---------------------
 # Agent Setup
 # ---------------------
 
 # Available tools
-tools = [search_tool, wikipedia, analyze_video, describe_image, calculate, convert_date, convert_currency]
+tools = [search_tool, wikipedia, analyze_video, describe_image, calculate, convert_date, convert_currency, process_audio_note]
 tools_as_openai = [convert_to_openai_tool(t) for t in tools]
 
 # Agent State Definition