Status: Done

A short clip of me walking through the basics of semantic vectors: embeddings as high-dimensional lists of numbers that represent unstructured data (text, images, audio), how we extract them from APIs like OpenAI / Hugging Face / Cohere, and how cosine similarity finds the nearest neighbors in that space.

It’s the same mental model behind my vector embeddings post and the Redis vector search work from that era.

Short clip on semantic vectors, embeddings, and cosine similarity.

For more about Arcade check out the website at https://www.arcade.dev/ and the GitHub https://github.com/arcadeai/