Mastodawn

Pplx-Embed: Embedding Models for Web-Scale Retrieval

https://research.perplexity.ai/articles/pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval

pplx-embed: State-of-the-Art Embedding Models for Web-Scale Retrieval

Today we are releasing pplx-embed-v1 and pplx-embed-context-v1, two state-of-the-art text embedding models built for real-world, web-scale retrieval.

Show thread

emschwartz Feb 27

This is exciting work. I especially appreciate that it was trained to support binary quantization (I wrote about how cool binary quantized vector embeddings are in https://emschwartz.me/binary-vector-embeddings-are-so-cool/)

Binary vector embeddings are so cool

Vector embeddings by themselves are pretty neat. Binary quantized vector embeddings are extra impressive. In short, they can retain 95+% retrieval accuracy with 32x compression 🤯.

Evan Schwartz