LLM plugin for pulling content from Youtube videos
Project description
llm-youtube
LLM plugin for extracting content from YouTube videos.
This plugin is inspired by Simon Willison's llm-hacker-news and his excellent llm tool.
Installation
llm install llm-youtube
Usage
Passing the video ID
example:
llm -f yt:zv72WMmVkPw 'Please summarize this video'
Passing the Video URL
example:
llm -f yt:https://www.youtube.com/watch\?v\=zv72WMmVkPw 'Please summarize this video'
We can also use a system prompt to improve the result
example:
llm -f yt:sCr_gb8rdEI --system "You are an expert at analyzing YouTube videos. Extract the key points only, ignore filler content." "What is this video about?"
Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
cd llm-youtube
python -m venv venv
source venv/bin/activate
Now install the dependencies:
pip install -e .
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llm_youtube-0.1.tar.gz.
File metadata
- Download URL: llm_youtube-0.1.tar.gz
- Upload date:
- Size: 6.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c8c4c7ef585bee252572b9d2979fd2fd6a61dc46d869696a457defc9ebd08ee6
|
|
| MD5 |
35de054ed2a4f07bb0cc9b9fc8d6d6a2
|
|
| BLAKE2b-256 |
2394c52b16ae296fcdf4ee161c5eda8b2e9af65b5c4ebe0b5c3ae36b5607a3c1
|
File details
Details for the file llm_youtube-0.1-py3-none-any.whl.
File metadata
- Download URL: llm_youtube-0.1-py3-none-any.whl
- Upload date:
- Size: 6.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
63faf6250352744a5f6c4565b9991571c1be6a74afb6a5fe6811de0cb3144107
|
|
| MD5 |
7f6442746df4a2595c3efc0f1c70bfd5
|
|
| BLAKE2b-256 |
cced43affd32b6dd5ea1fd8f730b5a8c4e1714551c6b512cb2657c584a66a0d0
|