---
title: "Discussion on \"The Live Index: Why Vector Search Should Be a Streaming Problem\" | Hashnode"
description: "Discussion on \"The Live Index: Why Vector Search Should Be a Streaming Problem\". Vector databases assume the corpus is static. Real workloads aren't. Here's why vector search belongs in a streaming database, and how RisingWave's native vector type and streaming HNSW indexes close the gap between data that exists and data you can search."
url: "https://hashnode.com/posts/risingwave-native-vector-search-streaming-live-index/6a10ea3f4d3bc7cca81699e0"
---

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

Discussion

# [The Live Index: Why Vector Search Should Be a Streaming Problem](https://risingwave.com/blog/risingwave-native-vector-search-streaming-live-index?utm_source=hashnode&utm_medium=feed)

Vector databases assume the corpus is static. Real workloads aren't. Here's why vector search belongs in a streaming database, and how RisingWave's native vector type and streaming HNSW indexes close the gap between data that exists and data you can search.

May 22 · 10 min read · risingwave.com  
Read the article

-   [#vector-search](https://hashnode.com/tag/vector-search)
-   [#streaming-database](https://hashnode.com/tag/streaming-database)
-   [#risingwave](https://hashnode.com/tag/risingwave)
-   [#ai-infrastructure](https://hashnode.com/tag/ai-infrastructure)

## Written by

[Yuhao Su](https://hashnode.com/@yuhao)

@yuhao

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

## Responses

Markdown supported · ⌘↵ to post

No responses yet.