# BM25 CJK (Chinese, Japanese, Korean) Support

**URL:** https://forum.weaviate.io/t/bm25-cjk-chinese-japanese-korean-support/5762
**Category:** Support
**Created:** [October 18, 2024, 8:03am UTC](https://forum.weaviate.io/t/bm25-cjk-chinese-japanese-korean-support/5762 "2024-10-18T08:03:39Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![henry\_m](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/henry_m/32/1479_2.png) [@henry\_m](https://forum.weaviate.io/u/henry_m)
#### Post date: [October 18, 2024, 8:03am UTC](https://forum.weaviate.io/t/bm25-cjk-chinese-japanese-korean-support/5762/1 "2024-10-18T08:03:39Z")

</div>

### Description

I’m exploring keyword search using BM25.

From [Multiple keywords using BM25](https://forum.weaviate.io/t/multiple-keywords-using-bm25/131) I see that multiple words can be supplied. However we’re handling Chinese text:

```py
>>> collection.query.bm25("水痘是怎樣形成的？")
QueryReturn(objects=[])
>>> collection.query.bm25("水痘")
QueryReturn(objects=[Object(uuid=...),Object(uuid=...),Object(uuid=...)])
>>> collection.query.bm25("水 痘 是 怎 樣 形 成 的 ？")
QueryReturn(objects=[])
>>> collection.query.bm25("水痘 是 怎 樣 形 成 的 ？")
QueryReturn(objects=[Object(uuid=...),Object(uuid=...),Object(uuid=...)])

```

Can weaviate expose the underlying BM25 tokenizer so that CJK texts are handled properly?

### Server Setup Information

- Weaviate Server Version: **1.25.2**
- Deployment Method: **docker** (semitechnologies/weaviate:1.25.2)
- Multi Node? Number of Running Nodes: **1**

### Any additional Information

---

<div class="post-metadata">

### Author: ![Dirk](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dirk/32/46_2.png) [@Dirk](https://forum.weaviate.io/u/Dirk)
#### Post date: [October 18, 2024, 8:12am UTC](https://forum.weaviate.io/t/bm25-cjk-chinese-japanese-korean-support/5762/2 "2024-10-18T08:12:09Z")

</div>

Hello!

We have special tokenizers for chinese+japanese and korean 🙂

Please have a look here: [Collection schema | Weaviate](https://weaviate.io/developers/weaviate/config-refs/schema#gse-and-trigram-tokenization-methods)