> ## Documentation Index
> Fetch the complete documentation index at: https://private-7c7dfe99-mintlify-fbfa8bee.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Can you use ClickHouse for vector search?

> Learn how to use ClickHouse for vector search, including storing embeddings and searching with distance functions like cosine similarity.

{frontMatter.description}

<h2 id="clickhouse-for-vector-search">
  ClickHouse for Vector Search!
</h2>

Yes, ClickHouse can perform vector search.

The main advantages of using ClickHouse for vector search compared to using more specialized vector databases include:

* Using ClickHouse's filtering and full-text search capabilities to refine your dataset before performing a search.
* Performing analytics on your datasets.
* Running a `JOIN` against your existing data.
* No need to manage yet another database and complicate your infrastructure.

Here is a quick tutorial on how to use ClickHouse for vector search.

<h2 id="1-create-embeddings">
  1. Create embeddings
</h2>

Your data (documents, images, or structured data) must be converted to *embeddings*. We recommend creating embeddings using the [OpenAI Embeddings API](https://platform.openai.com/docs/api-reference/embeddings) or using the open-source Python library [SentenceTransformers](https://www.sbert.net/).

You can think of an embedding as a large array of floating-point numbers that represent your data. [Check out this guide from OpenAI to learn more about embeddings](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings).

<h2 id="2-store-the-embeddings">
  2. Store the embeddings
</h2>

Once you have generated embeddings, you need to store them in ClickHouse. Each embedding should be stored in a separate row and can include metadata for filtering, aggregations, or analytics. Here's an example of a table that can store images with captions:

```sql theme={null}
CREATE TABLE images
(
	`_file` LowCardinality(String),
	`caption` String,
	`image_embedding` Array(Float32)
)
ENGINE = MergeTree;
```

<h2 id="3-search-for-related-embeddings">
  3. Search for related embeddings
</h2>

Let's say you want to search for pictures of dogs in your dataset. You can use a distance function like `cosineDistance` to take an embedding of a dog image and search for related images:

```sql theme={null}
SELECT
    _file,
	caption,
	cosineDistance(
        -- An embedding of your "input" dog picture
        [0.5736801028251648, 0.2516217529773712, ...,  -0.6825592517852783],
        image_embedding
    ) AS score
FROM images
ORDER BY score ASC
LIMIT 10
```

This query returns the `_file` names and `caption` of the top 10 images most likely to be related to your provided dog image.

<h2 id="further-reading">
  Further Reading
</h2>

To follow a more in-depth tutorial on vector search using ClickHouse, please see:

* [Exact and Approximate Vector Search](/reference/engines/table-engines/mergetree-family/annindexes)