From 84f9bae1294bfd6b9da62e2ab0aa734ae12255e9 Mon Sep 17 00:00:00 2001
From: Nayeon Kim <76769919+n-y-kim@users.noreply.github.com>
Date: Tue, 20 Aug 2024 03:21:40 +0900
Subject: [PATCH] Update 0-architecture.md (#961)

---
 docsite/posts/index/0-architecture.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docsite/posts/index/0-architecture.md b/docsite/posts/index/0-architecture.md
index c00e6e8802..5b9a691fa7 100644
--- a/docsite/posts/index/0-architecture.md
+++ b/docsite/posts/index/0-architecture.md
@@ -65,7 +65,7 @@ Our underlying dataframe technology may change over time, but our primary goal i
 
 ### LLM Caching
 
-The GraphRAG library was designed with LLM interactions in mind, and a common setback when working with LLM APIs is various errors errors due to network latency, throttling, etc..
+The GraphRAG library was designed with LLM interactions in mind, and a common setback when working with LLM APIs is various errors due to network latency, throttling, etc..
 Because of these potential error cases, we've added a cache layer around LLM interactions.
 When completion requests are made using the same input set (prompt and tuning parameters), we return a cached result if one exists.
 This allows our indexer to be more resilient to network issues, to act idempotently, and to provide a more efficient end-user experience.