Update agent.py

agent.py

@@ -30,6 +30,9 @@ from langchain_core.documents import Document
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 
+from youtube_transcript_api import YouTubeTranscriptApi
+from youtube_transcript_api._errors import TranscriptsDisabled, VideoUnavailable
+import re
 
 
 load_dotenv()
@@ -128,6 +131,46 @@ def arvix_search(query: str) -> str:
     return {"arvix_results": formatted_search_docs}
 
 
+@tool
+def get_youtube_transcript(url: str) -> str:
+    """
+    Fetch transcript text from a YouTube video.
+    
+    Args:
+        url (str): Full YouTube video URL.
+    
+    Returns:
+        str: Transcript text as a single string.
+    
+    Raises:
+        ValueError: If no transcript is available or URL is invalid.
+    """
+    try:
+        # Extract video ID
+        video_id = extract_video_id(url)
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+
+        # Combine all transcript text
+        full_text = " ".join([entry['text'] for entry in transcript])
+        return full_text
+
+    except (TranscriptsDisabled, VideoUnavailable) as e:
+        raise ValueError(f"Transcript not available: {e}")
+    except Exception as e:
+        raise ValueError(f"Failed to fetch transcript: {e}")
+
+@tool
+def extract_video_id(url: str) -> str:
+    """
+    Extract the video ID from a YouTube URL.
+    """
+    match = re.search(r"(?:v=|youtu\.be/)([A-Za-z0-9_-]{11})", url)
+    if not match:
+        raise ValueError("Invalid YouTube URL")
+    return match.group(1)
+
+
+
 
 # -----------------------------
 # Load configuration from YAML
@@ -165,6 +208,9 @@ tool_map = {
     "wiki_search": wiki_search,
     "web_search": web_search,
     "arvix_search": arvix_search,
+    "get_youtube_transcript": get_youtube_transcript,
+    "extract_video_id": extract_video_id,
+    
 }
 
 tools = [tool_map[name] for name in enabled_tool_names]