Nils Reimers’ Post

View profile for Nils Reimers, graphic

Director of Machine Learning @ Cohere | creator sentence-transformers

Cohere Compressed embeddings can save you 32x on your vector DB cost, while keeping 100% search quality. Now also available on AWS Bedrock.

View organization page for AWS AI, graphic

420,366 followers

Amazon Bedrock now supports compressed embeddings from Cohere Embed. ☁️ https://go.aws/4eBniXm Cohere Embed is a leading text embedding model most frequently used to power RAG & semantic search systems. Compressed embeddings (int8 and binary) enable developers and businesses to build more efficient #generativeAI applications without compromising on performance. #AWS

  • No alternative text description for this image
Andrei Lopatenko 🇺🇦

VP AI & Engineering | Co-Founder | Keynote speaker | Ex-Google, Apple, WML

1mo

It’s super impressive work. Making lower dimensional representations ( 4x and 32x) but still keeping high quality of retrieval tasks is very impactful (and hard. Very impressive )

To view or add a comment, sign in

Explore topics