---
title: "Comment by Julian Neagu on \"RAG for Microsoft AI Agent through TextSearchProvider and Redis\" | Hashnode"
description: "Moving embeddings out of memory is one of those changes that matters once real traffic shows up. I like the Redis setup here because it keeps storage separate w"
url: "https://hashnode.com/posts/rag-for-microsoft-ai-agent-through-textsearchprovider-and-redis/6a8e69cedeab3ab2cc6fd4ac/comment/6a913dcefd56c90fdd149205"
---

[Discussion](https://hashnode.com/posts/rag-for-microsoft-ai-agent-through-textsearchprovider-and-redis/6a8e69cedeab3ab2cc6fd4ac)

Comment [RAG for Microsoft AI Agent through TextSearchProvider and Redis](https://hashnode.com/posts/rag-for-microsoft-ai-agent-through-textsearchprovider-and-redis/6a8e69cedeab3ab2cc6fd4ac)

[Julian Neagu](https://hashnode.com/@julianneagulab)

[Aug 28](https://hashnode.com/posts/rag-for-microsoft-ai-agent-through-textsearchprovider-and-redis/6a8e69cedeab3ab2cc6fd4ac/comment/6a913dcefd56c90fdd149205)

Moving embeddings out of memory is one of those changes that matters once real traffic shows up. I like the Redis setup here because it keeps storage separate without making retrieval overly complex.