From 823b2ce7bb9bb314a0947d542ea05a003c77331b Mon Sep 17 00:00:00 2001
From: Xing Han Lu <21180505+xhluca@users.noreply.github.com>
Date: Fri, 8 Nov 2024 14:58:42 -0500
Subject: [PATCH] Update packages

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 45dd0b4..0048b31 100644
--- a/README.md
+++ b/README.md
@@ -113,7 +113,7 @@ There are two ways to load the knowledge base data:
 
 If you are running eval, you may install the following packages:
 ```bash
-pip install llm2vec gritlm bm25
+pip install llm2vec gritlm bm25s
 ```
 
 - Our evaluation requires embed the node documents into `candidate_emb_dict.pt`, which is a dictionary `node_id -> torch.Tensor`. Query embeddings will be automatically generated if not available. You can either run the following the python script to download query embeddings and document embeddings generated by `text-embedding-ada-002`. (We provide them so you can run on our benchmark right away.)