From d29b1db2c74e674f4ecc3db63afb40f99c3e81f2 Mon Sep 17 00:00:00 2001
From: Raja Kolli <rajadilipkolli@gmail.com>
Date: Fri, 5 Apr 2024 08:33:24 +0530
Subject: [PATCH] chore(docs) : adds necessity of GPU

---
 rag/rag-springai-ollama-llm/ReadMe.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/rag/rag-springai-ollama-llm/ReadMe.md b/rag/rag-springai-ollama-llm/ReadMe.md
index 36f4043..f7f8a06 100644
--- a/rag/rag-springai-ollama-llm/ReadMe.md
+++ b/rag/rag-springai-ollama-llm/ReadMe.md
@@ -2,6 +2,8 @@
 
 The use of the pgvector store with the ollama model is not feasible due to the generation of 4096 dimensions by the latter, which exceeds pg vector's indexing support limit of less than 2000 dimensions. This limitation hinders the ease of querying the embedding store due to the absence of indexing.
 
+As LLMs needs heavy computational power, it needs GPU to be enabled for quickly processing using the complex Math operations behind the scenens.
+
 ### Testcontainers support
 
 This project uses [Testcontainers at development time](https://docs.spring.io/spring-boot/docs/3.2.4/reference/html/features.html#features.testing.testcontainers.at-development-time).