# Understanding vector search and HNSW index with pgvector

DevFeed: [Understanding vector search and HNSW index with pgvector](<https://devfeed.tech/articles/understanding-vector-search-and-hnsw-index-with-pgvector-5838.md>)

Original publisher: [Read original article](<https://neon.com/blog/understanding-vector-search-and-hnsw-index-with-pgvector>)

Author: Raouf Chebri

Published: 2023-09-20T15:22:06Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [LLMs](<https://devfeed.tech/topics/llms.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Algorithms, Complexity](<https://devfeed.tech/topics/algorithms-complexity.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llms](<https://devfeed.tech/tags/llms.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [product](<https://devfeed.tech/tags/product.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

## AI overview

This article explains vector embeddings, semantic similarity search, and the HNSW index introduced in pgvector 0.5.0. It describes how embeddings represent text and other data as vectors, how vector search supports Generative AI and LLM applications, and how HNSW improves approximate nearest-neighbor query performance.

## Source excerpt

Vector embeddings have become an essential component of Generative AI applications. These embeddings encapsulate the meaning of the text, thus enabling AI models to understand which texts are semantically similar. The process of extracting the most similar texts from your databas...