About All-In On AI

All-In On AI” is an innovative project developed by Travis Fischer that leverages the power of artificial intelligence to enhance the podcast listening experience. It is designed to solve the problem of search and discovery in podcasts, which can often be challenging. The project uses the latest models from OpenAI to build a semantic search index across every episode of the All-In Podcast, allowing users to find their favorite moments with Google-level accuracy and rewatch the exact clips they’re interested in.

Here are three key features of the All-In On AI project

  1. Semantic Search: The project uses OpenAI’s text-embedding-ada-002 embedding model to create a semantic search index across every episode of the All-In Podcast. This allows users to go beyond keyword search and search by higher-level topics.
  2. Vector Search: It uses Pinecone, a hosted vector search tool, to perform k-NN searches across the embeddings, enabling efficient and accurate search results.
  3. Open Source: The project is open source, allowing anyone to contribute to its development and improvement. It uses a variety of technologies including Node.js, the YouTube API v3, and the React web framework Next.js.