From bcf3cee8b8043cedfa1cceb09ad5865fe3c13644 Mon Sep 17 00:00:00 2001 From: Rishav Dash <57321948+Rishav-hub@users.noreply.github.com> Date: Sun, 3 Sep 2023 13:37:14 +0530 Subject: [PATCH] Updated the hyperlink for "Retrieval with FastEmbed" prev -: https://qdrant.github.io/fastembed/examples/Retrieval%20with%20FastEmbed/ now -: https://qdrant.github.io/fastembed/examples/Retrieval_with_FastEmbed/ --- docs/index.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/index.md b/docs/index.md index b24d060..dd82491 100644 --- a/docs/index.md +++ b/docs/index.md @@ -4,7 +4,7 @@ FastEmbed is an easy to use -- lightweight, fast, Python library built for retri The default embedding supports "query" and "passage" prefixes for the input text. The default model is [Flag Embedding](https://github.com/FlagOpen/FlagEmbedding), which is top of the [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard. -Advanced user? Skip ahead to [Retrieval with FastEmbed](https://qdrant.github.io/fastembed/examples/Retrieval%20with%20FastEmbed/) +Advanced user? Skip ahead to [Retrieval with FastEmbed](https://qdrant.github.io/fastembed/examples/Retrieval_with_FastEmbed/) To install the FastEmbed library, pip works: @@ -42,4 +42,4 @@ It's important we justify the "fast" in FastEmbed. FastEmbed is fast because: ### Why accurate? 1. Better than OpenAI Ada-002 -2. Top of the Embedding leaderboards e.g. [MTEB](https://huggingface.co/spaces/mteb/leaderboard) \ No newline at end of file +2. Top of the Embedding leaderboards e.g. [MTEB](https://huggingface.co/spaces/mteb/leaderboard)