utils.py

import re
from youtube_transcript_api import YouTubeTranscriptApi
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma

def extract_video_id(url: str) -> str:
    video_id_match = re.search(r'(?:v=|\/)([0-9A-Za-z_-]{11}).*', url)
    if video_id_match:
        return video_id_match.group(1)
    raise ValueError("Invalid YouTube URL")

def create_vector_store(text: str) -> Chroma:
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=500,
        chunk_overlap=100
    )
    texts = text_splitter.split_text(text)
    embeddings = OpenAIEmbeddings()
    return Chroma.from_texts(texts, embeddings)

def get_transcript(video_id: str) -> str:
    transcript = YouTubeTranscriptApi.get_transcript(video_id)
    return " ".join([entry["text"] for entry in transcript])