languid willow
I love the All-In Podcast, but search and discovery with podcasts can be really challenging.
So I decided to build a solution to this problem... and I also wanted to play around with cool AI stuff. 😂
This project uses the latest text-embedding-ada-002 embedding model to build a semantic search index across every episode of the Pod. It allows you to find your favorite moments with Google-level accuracy and rewatch the exact clips you're interested in.
It also makes heavy use of Pinecone for indexing these embeddings and performing kNN lookups.
You can use it to power advanced search across any YouTube channel or playlist btw. The demo uses the All-In Podcast because it's my favorite 💕, but it's designed to work with any playlist.
https://all-in-on-ai.vercel.app
https://github.com/transitive-bullshit/yt-semantic-search
Would love to hear your thoughts & suggestions.
oblique temple