Update agent.py

agent.py

@@ -3,6 +3,7 @@ import os
 import operator
 import json
 import re
+from youtube_transcript_api import YouTubeTranscriptApi
 from typing import TypedDict, Annotated, Sequence, Union
 from langgraph.graph import StateGraph, END
 from langchain_community.tools import DuckDuckGoSearchResults
@@ -30,68 +31,49 @@ wikipedia = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=3))
 
 #video analysis
 @tool
-def analyze_video(video_url: str, question: str) -> str:
+def analyze_youtube_video(youtube_link: str, question: str) -> str:
     """
-    Analyze a video to answer a specific question about its content.
-    Supports YouTube videos. Provide both the video URL and the question.
+    Analyze a YouTube video to answer a specific question about its content.
+    Returns the answer to the question based on the video's transcript.
     
-    Example: 
-    analyze_video(
-        "https://www.youtube.com/watch?v=1htKBjuUWec", 
-        "What does Teal'c say in response to the question 'Isn't that hot?'"
-    )
+    Args:
+        youtube_link: URL of the YouTube video
+        question: Specific question about the video content
+        
+    Returns:
+        Answer to the question or error message
     """
+    # Extract video ID from various YouTube URL formats
+    def extract_video_id(url):
+        regex = r"(?:youtube\.com\/(?:[^\/]+\/.+\/|(?:v|e(?:mbed)?)\/|.*[?&]v=)|youtu\.be\/)([^\"&?\/\s]{11})"
+        match = re.search(regex, url)
+        return match.group(1) if match else None
+    
     try:
-        # Create a temporary directory for processing
-        with tempfile.TemporaryDirectory() as tmp_dir:
-            # Download audio from YouTube
-            ydl_opts = {
-                'format': 'bestaudio/best',
-                'outtmpl': os.path.join(tmp_dir, 'audio.%(ext)s'),
-                'postprocessors': [{
-                    'key': 'FFmpegExtractAudio',
-                    'preferredcodec': 'mp3',
-                    'preferredquality': '192',
-                }],
-                'quiet': True,
-            }
-            
-            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-                ydl.download([video_url])
-                audio_file = os.path.join(tmp_dir, 'audio.mp3')
-                
-                # If the file wasn't created with .mp3 extension, find it
-                if not os.path.exists(audio_file):
-                    for f in os.listdir(tmp_dir):
-                        if f.startswith('audio.'):
-                            audio_file = os.path.join(tmp_dir, f)
-                            break
-            
-            # Transcribe audio using OpenAI Whisper
-            client = OpenAI()
-            with open(audio_file, 'rb') as f:
-                transcript = client.audio.transcriptions.create(
-                    model="whisper-large-v3",
-                    file=f,
-                    response_format="text"
-                )
-            
-            # Use GPT to answer the question based on transcript
-            response = client.chat.completions.create(
-                model="gpt-4-turbo",
-                messages=[
-                    {"role": "system", "content": "Answer the question based on the video transcript below. Be precise and quote directly when possible."},
-                    {"role": "user", "content": f"Question: {question}\n\nTranscript:\n{transcript}"}
-                ],
-                max_tokens=300
-            )
-            
-            return response.choices[0].message.content
-            
+        # Get video ID
+        video_id = extract_video_id(youtube_link)
+        if not video_id:
+            return "Error: Invalid YouTube URL format"
+        
+        # Get transcript
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        transcript_text = " ".join([entry['text'] for entry in transcript])
+        
+        # Use OpenAI to answer the question based on transcript
+        client = OpenAI()
+        response = client.chat.completions.create(
+            model="gpt-4-turbo",
+            messages=[
+                {"role": "system", "content": "Answer the user's question based EXCLUSIVELY on the video transcript below. Be precise and quote directly when possible."},
+                {"role": "user", "content": f"Question: {question}\n\nTranscript:\n{transcript_text}"}
+            ],
+            max_tokens=300
+        )
+        
+        return response.choices[0].message.content
+        
     except Exception as e:
-        return f"Error analyzing video: {str(e)}"
-
-
+        return f"Error: {str(e)}"
 
 # Image Description Tool (using GPT-4 Vision)
 @tool