Update app.py

app.py

@@ -8,9 +8,15 @@ from smolagents import DuckDuckGoSearchTool, VisitWebpageTool
 import time  # Added: For sleep functionality
 from functools import lru_cache  # Added: For caching search results
 
+pip install youtube-transcript-api
 
+from youtube_transcript_api import YouTubeTranscriptApi
+import re
+
+# TOOLS
 search_tool = DuckDuckGoSearchTool()
 visit_webpage = VisitWebpageTool()
+youtube_tool = YouTubeVideoTool()
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -92,7 +98,58 @@ class BasicAgent:
     
     def _get_fallback_answer(self, question):
         return f"Based on the information available, I cannot provide a specific answer to your question about {question.split()[0:3]}..."
+from youtube_transcript_api import YouTubeTranscriptApi
+import re
+
+class YouTubeVideoTool:
+    def __init__(self):
+        self.name = "youtube_video_tool"
+        
+    def __call__(self, query):
+        """
+        Extract information from a YouTube video.
         
+        Args:
+            query: Either a YouTube URL or video ID
+        
+        Returns:
+            String with the transcript of the video
+        """
+        try:
+            # Extract video ID from URL if needed
+            video_id = self._extract_video_id(query)
+            if not video_id:
+                return "Could not extract a valid YouTube video ID"
+                
+            # Get the transcript
+            transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
+            
+            # Combine the transcript text
+            transcript_text = " ".join([item['text'] for item in transcript_list])
+            
+            return f"Transcript from YouTube video {video_id}:\n{transcript_text}"
+        except Exception as e:
+            return f"Error processing YouTube video: {str(e)}"
+    
+    def _extract_video_id(self, url_or_id):
+        """Extract YouTube video ID from various URL formats or return the ID if already provided."""
+        # Handle direct video ID
+        if len(url_or_id) == 11 and re.match(r'^[A-Za-z0-9_-]{11}$', url_or_id):
+            return url_or_id
+            
+        # Common YouTube URL patterns
+        patterns = [
+            r'(?:youtube\.com\/watch\?v=|youtu\.be\/|youtube\.com\/embed\/|youtube\.com\/v\/)([A-Za-z0-9_-]{11})',
+            r'youtube\.com\/watch\?.*v=([A-Za-z0-9_-]{11})',
+            r'youtube\.com\/shorts\/([A-Za-z0-9_-]{11})'
+        ]
+        
+        for pattern in patterns:
+            match = re.search(pattern, url_or_id)
+            if match:
+                return match.group(1)
+                
+        return None        
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -115,7 +172,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent(model='Qwen/Qwen2.5-Coder-32B-Instruct', tools=[search_tool, visit_webpage])
+        agent = BasicAgent(model= LiteLLMModel('gemini/gemini-2.0-flash-exp'), tools=[search_tool, visit_webpage, youtube_tool])
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None