Organize and format YouTube video transcripts using LangChain

transcript_formatter.py

from langchain_community.document_loaders import YoutubeLoader
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI

model = ChatOpenAI()
parser = StrOutputParser()

url = input("Enter the YouTube video URL: ")

loader = YoutubeLoader.from_youtube_url(url, add_video_info=False)
documents = loader.load()
transcript = documents[0].page_content

template = PromptTemplate(
    template="""Organize and format the following text properly:\n```\n{transcript}\n```\nDon't omit anything.""",
    input_variables=["transcript"],
    validate_template=True,
)

chain = template | model | parser

output = chain.invoke({"transcript": transcript})

with open("transcript.txt", "w") as file:
    file.write(output)

print("The transcript has been written to transcript.txt.")