---
title: "Discussion on \"Embeddings in RAG: The Core of Semantic Search\" | Hashnode"
description: "Discussion on \"Embeddings in RAG: The Core of Semantic Search\". Retrieval-Augmented Generation (RAG) systems rely on the core idea of converting text into vectors so we can search by meaning instead of keywords. These vectors are called embeddings, and they are th"
url: "https://hashnode.com/posts/embeddings-in-rag-the-core-of-semantic-search/69e89f815d1c1071051ef4d8"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Embeddings in RAG: The Core of Semantic Search](https://blog.chapainaashish.com.np/embeddings-in-rag-the-core-of-semantic-search?utm_source=hashnode&utm_medium=feed)

Retrieval-Augmented Generation (RAG) systems rely on the core idea of converting text into vectors so we can search by meaning instead of keywords. These vectors are called embeddings, and they are th

Apr 22 · 6 min read · blog.chapainaashish.com.np  
Read the article

-   [#rag](https://hashnode.com/tag/rag)
-   [#embedding](https://hashnode.com/tag/embedding)
-   [#semantic-search](https://hashnode.com/tag/semantic-search)
-   [#claude](https://hashnode.com/tag/claude)
-   [#llm](https://hashnode.com/tag/llm)
-   [#ai](https://hashnode.com/tag/ai)

## Written by

[Aashish Chapain](https://hashnode.com/@chapainaashish)

@chapainaashish

  
[View profile](https://hashnode.com/@chapainaashish)

breaking and making

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
