Skip to content

YouTubeGPT β€’ AI Chat with 100+ videos ft. YouTuber Marques Brownlee (@ MKBHD) βš‘οΈπŸ”΄πŸ€–πŸ’¬

Notifications You must be signed in to change notification settings

vdutts7/youtube-gpt

Repository files navigation


Logo Logo Logo

YouTubeGPT ft. Marques Brownlee (@MKBHD)

AI Chatbot with 100+ videos from tech/gadget YouTuber Marques Brownlee @MKBHD

Table of Contents

    πŸ“ About
    πŸ’» How to build
    πŸš€ Next steps
    πŸ”§ Tools used
    πŸ‘€ Contact



πŸ“ About

Chat with 100+ YouTube videos from any creator in less than 10 minutes. This project combines basic Python scripting, vector embeddings, OpenAI, Pinecone, and Langchain into a modern chat interface, allowing you to quickly reference any content your favorite YouTuber covers. Type in natural language and get returned detailed answers: (1) in the style / tone of your YouTuber, and (2) with the top 2-3 specific videos referenced hyperlinked.

Example used in this repo is tech content creator Marques Brownlee, also known as MKBHD

πŸ’» How to build

Note: macOS version, adjust accordingly for Windows / Linux

Initial setup

Clone and install dependencies:

git clone https://github.com/vdutts7/yt-ai-chat
cd yt-ai-chat
npm i

Copy .env.example and rename to .env in root directory. Fill out API keys:

ASSEMBLY_AI_API_TOKEN=""
OPENAI_API_KEY=""
PINECONE_API_KEY=""
PINECONE_ENVIRONMENT=""
PINECONE_INDEX=""

Get API keys:

IMPORTANT: Verify that .gitignore contains .env in it.

Handle massive data

Outline:

  • Export metadata (.csv) of YouTube videos ⬇️
  • Download the audio files
  • Transcribe audio files

Navigate to scripts folder, which will host all of the data from the YouTube videos.

cd scripts

Setup python environemnt:

conda env list
conda activate youtube-chat
pip install -r requirements.txt

Scrape YouTube channel-- replace @mkbhd with channel of your choice. Replace 100 with the number of videos you want included (the script traverses backwards starting from most recent upload). A new file mkbhd.csv will be created at the directory as referenced below:

python scripts/scrape_vids.py https://www.youtube.com/@mkbhd 100 scripts/vid_list/mkbhd.csv

Refer to example_mkbhd.csv inside folder and verify your output matches this format:

image

Download audio files:

python scripts/download_yt_audios.py scripts/vid_list/mkbhd.csv scripts/audio_files/
image

We will utilize AssemblyAI's API wrapper class for OpenAI's Whisper API. Their script provides step-by-step directions for a more efficient, faster speech-to-text conversion as Whisper is way too slow and will cost you more. I spent ~ $3.50 to transcribe the 100 videos for MKBHD.

image
python scripts/transcribe_audios.py scripts/audio_files/ scripts/transcripts
image

Upsert to Pinecone database:

python scripts/pinecone_helper.py scripts/vid_list/mkbhd.csv scripts/transcripts/

Pinecone index setup I used below. I used P1 since this is optimized for speed. 1536 is OpenAI's standard we're limited to when querying data from the vectorstore: image

Embeddings and database backend

Breaking down scripts/pinecone_helper.py :

  • Chunk size of 1000 characters with 500 character overlap. I found this working for me but obviously experiment and adjust according to your content library's size, complexity, etc.
  • Metadata: (1) video url and (2) video title

With Pinecone vectorstore loaded, we use Langchain's Conversational Retrieval QA to ask questions, extract relevant metadata from our embeddings, and deliver back to the user in a packaged format as an answer.

The relevant video titles are cited via hyperlinks directly to the video url.

Frontend UI with chat

NextJs styled with Tailwind CSS. src/pages/index.tsx contains base skeleton. src/pages/api/chat-chain.ts is heart of the code where the Langchain connections are outlined. You should be able to type and ask questions now. Done βœ…

Logo Screenshot 2023-06-20 at 4 17 08 PM

πŸš€Next Steps

  • Add sidebar of video links to reference
  • User auth + DB backend to store chat history / log queries
  • Improve bot personality: edit prompt template in /src/pages/api/chat-chain.ts to fine-tune output to sound more realistic.

πŸ”§Tools Used

Python Langchain OpenAI AssemblyAI Pinecone Next Typescript Tailwind CSS Vercel

πŸ‘€Contact

Email Twitter

About

YouTubeGPT β€’ AI Chat with 100+ videos ft. YouTuber Marques Brownlee (@ MKBHD) βš‘οΈπŸ”΄πŸ€–πŸ’¬

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published