Tool

Load YouTube Video Transcripts

LlamaIndex reader that fetches YouTube video transcripts into documents.

Works with youtube

79
Spark score
out of 100
Updated 2 days ago
Version 0.14.23
Models

Add to Favorites

Why it matters

Ingest and process transcripts from YouTube videos to extract valuable textual information for further analysis or summarization.

Outcomes

What it gets done

01

Fetch transcripts from YouTube video URLs.

02

Support multiple YouTube URL formats.

03

Extract text data for integration with LlamaIndex.

04

Enable programmatic URL validation.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/li-reader-readers-youtube-transcript | bash

Overview

Youtube Transcript Loader

The YouTube Transcript Loader fetches video transcripts via the youtube_transcript_api package, given a list of YouTube links, and includes a helper to check whether a URL is a supported YouTube format. Use it when you need YouTube video transcripts loaded into LlamaIndex. It supports three specific YouTube URL formats: watch, embed, and youtu.be links.

What it does

The YouTube Transcript Loader fetches the text transcript of YouTube videos using the youtube_transcript_api Python package. You pass an array of YouTube links to load_data, and it returns each video's transcript as a document.

When to use - and when NOT to

Use it when you need YouTube video transcripts pulled into LlamaIndex documents. It supports three URL formats -- youtube.com/watch?v={video_id}, youtube.com/embed?v={video_id} (each with or without www.), and youtu.be/{video_id} (never with www.) -- so it is not usable with other video-hosting URLs or unsupported YouTube link formats.

Inputs and outputs

Install with:

pip install llama-hub-youtube-transcript

pip install llama-index-readers-youtube-transcript

You will also need youtube_transcript_api: pip install youtube_transcript_api.

Load transcripts by passing a list of YouTube links:

from llama_index.readers.youtube_transcript import YoutubeTranscriptReader

loader = YoutubeTranscriptReader()
documents = loader.load_data(
    ytlinks=["https://www.youtube.com/watch?v=i3OYlaoj-BM"]
)

To check whether a URL is a supported YouTube link before passing it in, use the is_youtube_video utility:

from llama_index.readers.youtube_transcript.utils import is_youtube_video

is_youtube_video("https://youtube.com/watch?v=j83jrh2")  # => True
is_youtube_video("https://vimeo.com/272134160")  # => False

Who it's for

Developers building LlamaIndex pipelines that need YouTube video transcripts loaded as documents.

Source README

Youtube Transcript Loader

pip install llama-hub-youtube-transcript

pip install llama-index-readers-youtube-transcript

This loader fetches the text transcript of Youtube videos using the youtube_transcript_api Python package.

Usage

To use this loader, you will need to first pip install youtube_transcript_api.

Then, simply pass an array of YouTube links into load_data:

from llama_index.readers.youtube_transcript import YoutubeTranscriptReader

loader = YoutubeTranscriptReader()
documents = loader.load_data(
    ytlinks=["https://www.youtube.com/watch?v=i3OYlaoj-BM"]
)

Supported URL formats: + youtube.com/watch?v={video_id} (with or without 'www.') + youtube.com/embed?v={video_id} (with or without 'www.') + youtu.be/{video_id} (never includes www subdomain)

To programmatically check if a URL is supported:

from llama_index.readers.youtube_transcript.utils import is_youtube_video

is_youtube_video("https://youtube.com/watch?v=j83jrh2")  # => True
is_youtube_video("https://vimeo.com/272134160")  # => False

This loader is designed to be used as a way to load data into LlamaIndex.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.