From 98aef1f53ad0dd7b157d1eede207f3b8b0b3256f Mon Sep 17 00:00:00 2001 From: Fanis Tharropoulos Date: Mon, 7 Oct 2024 18:26:47 +0300 Subject: [PATCH] docs(vector-search): add tip mentioning gpu usage --- docs-site/content/27.1/api/vector-search.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/docs-site/content/27.1/api/vector-search.md b/docs-site/content/27.1/api/vector-search.md index a36c2141..a3262db1 100644 --- a/docs-site/content/27.1/api/vector-search.md +++ b/docs-site/content/27.1/api/vector-search.md @@ -773,6 +773,10 @@ If you need support for additional publicly-available models, feel free to conve Embedding models are computationally intensive to run. So when using one of the [built-in models](#using-built-in-models), you might want to consider running Typesense on a server with a GPU to improve the performance of embedding generation, especially for large datasets. +:::tip +The GPU is only used for generating embeddings and not when using the embeddings generated for Vector Search. +::: + #### On Typesense Cloud: For [select RAM / CPU configurations](https://typesense-cloud.helpscoutdocs.com/article/4-gpu-acceleration), you'll find the option to turn on "GPU Acceleration" when provisioning a new cluster or under Cluster Configuration > Modify for Typesense versions `0.25.0` and above.