So I built a semantic search index that lets you search across every episode of the pod with Google-level accuracy.
It uses OpenAI's latest ada-2 embedding model and Pinecone to index the embeddings + k-NN search. Wrapped up in a Next.js + Vercel webapp.
The project is designed to work with any YouTube channel / playlist. I'm just using All-In as a demo.
Would love to hear feedback & suggestions.
Open source here: https://github.com/transitive-bullshit/yt-semantic-search
Note that the source is designed to work with any YouTube playlist / channel. I'm just using the All-In Podcast as a demo because it's my favorite.