TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Why would I use a vector db instead of the db I already use?

3 点作者 KennyFromIT大约 2 年前
I use postgres and it has pgvector - why should I consider using Chroma, Pinecone, or any other dedicated vector db for my llm-based application that needs to store embeddings information?

1 comment

andre-z大约 2 年前
You can do everything with PostGres:<p>Full-text search, but there are better engines for it: Elastic, Meilisearch, etc. right?<p>You can also store JSON into Postgres, but you should better use MongoDB for NoSQL purposes, right?<p>The reason for this is: dedicated tools are always better, faster, and more feature-rich.<p>The ANN index IVF implemented in pgvector has very poor performance, with only around 50% recall. Is it something you are looking for?<p>Disclaimer: I&#x27;m a co-founder at Qdrant, an open-source vector database written in Rust. <a href="https:&#x2F;&#x2F;github.com&#x2F;qdrant&#x2F;qdrant">https:&#x2F;&#x2F;github.com&#x2F;qdrant&#x2F;qdrant</a><p>PS: Chroma isn&#x27;t a database but а Python wrapper around ClickHouse DB.