From 23881842ae33a294e344cef0cc2f1385ea6819f9 Mon Sep 17 00:00:00 2001 From: Lain Soykaf Date: Sun, 19 May 2024 13:04:27 +0400 Subject: [PATCH] B FastembedAPI: Add readme --- supplemental/search/fastembed-api/README.md | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 supplemental/search/fastembed-api/README.md diff --git a/supplemental/search/fastembed-api/README.md b/supplemental/search/fastembed-api/README.md new file mode 100644 index 000000000..63a037207 --- /dev/null +++ b/supplemental/search/fastembed-api/README.md @@ -0,0 +1,6 @@ +# About +This is a minimal implementation of the [OpenAI Embeddings API](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) meant to be used with the QdrantSearch backend. + +# Usage + +The easiest way to run it is to just use docker compose with `docker compose up`. This starts the server on the default configured port. Different models can be used, for a full list of supported models, check the [fastembed documentation](https://qdrant.github.io/fastembed/examples/Supported_Models/). The first time a model is requested it will be downloaded, which can take a few seconds.