# Multiple keywords using BM25

**URL:** <https://forum.weaviate.io/t/multiple-keywords-using-bm25/131>\
**Category:** Support\
**Created:** [June 6, 2023, 4:27am UTC](https://forum.weaviate.io/t/multiple-keywords-using-bm25/131 "2023-06-06T04:27:51Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![WillHsu](https://avatars.discourse-cdn.com/v4/letter/w/90ced4/32.png) [@WillHsu](https://forum.weaviate.io/u/WillHsu)\
**Post date:** [June 6, 2023, 4:27am UTC](https://forum.weaviate.io/t/multiple-keywords-using-bm25/131/1 "2023-06-06T04:27:51Z")

</div>

We use Hybrid search a lot. Great feature!  
Can we use multiple keywords when using BM25?  
The example provided is only one keyword.

---

<div class="post-metadata">

**Author:** ![felixthekraut](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/felixthekraut/32/134_2.png) [@felixthekraut](https://forum.weaviate.io/u/felixthekraut)\
**Post date:** [June 8, 2023, 7:38pm UTC](https://forum.weaviate.io/t/multiple-keywords-using-bm25/131/2 "2023-06-08T19:38:03Z")

</div>

You can put multiple words into the `query`. As per [GraphQL - Vector search parameters | Weaviate - vector database](https://weaviate.io/developers/weaviate/api/graphql/vector-search-parameters#bm25) , stop words are removed but the rest are all evaluated. If you add `_additional {explainScore}` to your query you will see how your different keywords factored into the score.

Simple example:

```auto
{
  Get {
    MyClass(
      limit: 30
      bm25: {
        query: "italy life insurance"
      }
    ) {
      text
      _additional
      {
          score
          explainScore
      }
    }
  }
}

```

Response:

```auto
{
    "data": {
        "Get": {
            "MyClass": [
                {
                    "_additional": {
                        "explainScore": ", BM25F_insurance_frequency:11, BM25F_insurance_propLength:161, BM25F_italy_frequency:7, BM25F_italy_propLength:161, BM25F_life_frequency:1, BM25F_life_propLength:161",
                        "score": "4.4186454"
                    }
                }
            ]
        }
    }
}

```

Note how all the keywords factored into the score.