---
title: "Discussion on \"Understanding LLM Embeddings from Scratch — Part 7: Sentence Embeddings, Contrastive Learning & Semantic Search\" | Hashnode"
description: "Discussion on \"Understanding LLM Embeddings from Scratch — Part 7: Sentence Embeddings, Contrastive Learning & Semantic Search\". From contextual token representations to a single vector for an entire sentence and why that vector is useful for retrieval.\nIn Part 6, we learned how self-attention changes a token's representation d"
url: "https://hashnode.com/posts/sentence-embeddings-contrastive-learning-semantic-search/6ae8a94d6231ed1f0af0efab"
---

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

Discussion

# [Understanding LLM Embeddings from Scratch — Part 7: Sentence Embeddings, Contrastive Learning & Semantic Search](https://rounakshow.hashnode.dev/sentence-embeddings-contrastive-learning-semantic-search?utm_source=hashnode&utm_medium=feed)

From contextual token representations to a single vector for an entire sentence and why that vector is useful for retrieval. In Part 6, we learned how self-attention changes a token's representation d

Nov 2 · 16 min read · rounakshow.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#llm](https://hashnode.com/tag/llm)
-   [#rag](https://hashnode.com/tag/rag)
-   [#embeddings](https://hashnode.com/tag/embeddings)

## Written by

[Rounak Show](https://hashnode.com/@ShowRounak)

@ShowRounak · Remote

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

Learning Data Science

Learning Data Science and Sharing the journey through Hashnode.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.