From 8c34a2529a9582877be01e93c119e98a68e54828 Mon Sep 17 00:00:00 2001 From: Vladimir Prelovac Date: Tue, 24 Oct 2023 17:34:38 -0700 Subject: [PATCH] Readme --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 63e9b53..a5a5edc 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,8 @@ VectorDB is a lightweight, low-latency Python package for storing and retrieving text using chunking, embedding, and vector search techniques. It provides an easy-to-use interface for saving, searching, and managing textual data with associated metadata and is designed for use cases where low latency is essential. +Because of low latency and memory footpring, VectorDB is used to power AI features inside [Kagi search](https://kagi.com). + ## Installation To install VectorDB, use pip (note vectordb2 package name): @@ -201,7 +203,7 @@ Output: ## Embeddings performance -Models are evaulated using standaridzed embeddings benchmarks *higher is better). Data pulled from [MTEB](https://huggingface.co/spaces/mteb/leaderboard). Average latency measured on CPU (lower is better). +Models are evaulated using standaridzed embeddings benchmarks (higher is better). Data pulled from [MTEB](https://huggingface.co/spaces/mteb/leaderboard). Average latency measured on CPU (lower is better).