> ## Documentation Index
> Fetch the complete documentation index at: https://www.meilisearch.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Configure Cohere embedder

> Set up the Cohere embedder for semantic and hybrid search using Cohere's embedding models.

The Cohere embedder connects Meilisearch to Cohere's embedding API. Cohere models support multiple languages and offer different model sizes for different performance needs. Since Meilisearch does not have a built-in Cohere source, you configure it using the [`rest` embedder](/capabilities/hybrid_search/how_to/configure_rest_embedder) source.

<Note>
  This guide requires a [Cohere account](https://cohere.com/) with an API key.
</Note>

## Choose a model

Cohere offers several embedding models:

| Model                           | Dimensions                | Notes                                                     |
| ------------------------------- | ------------------------- | --------------------------------------------------------- |
| `embed-v4.0`                    | 256, 512, 1,024, or 1,536 | Latest generation, multilingual, supports text and images |
| `embed-english-v3.0`            | 1,024                     | Best accuracy for English-only content                    |
| `embed-multilingual-v3.0`       | 1,024                     | Best v3 option for multilingual datasets                  |
| `embed-english-light-v3.0`      | 384                       | Faster, lower cost for English content                    |
| `embed-multilingual-light-v3.0` | 384                       | Faster, lower cost for multilingual content               |

For new projects, `embed-v4.0` is the recommended choice as it supports both text and images with flexible dimensions. If you only need English text embeddings and want a proven model, `embed-english-v3.0` remains a solid option. The light variants are faster and cheaper but may return slightly less accurate results.

See the [Cohere Embed documentation](https://docs.cohere.com/docs/cohere-embed) for the full model catalog.

## Configure the embedder

Because Cohere uses the REST embedder source, you must define the `request` and `response` structures that match Cohere's API. Create the following embedder configuration:

<CodeGroup>
  ```json theme={null}
  {
    "my-cohere": {
      "source": "rest",
      "url": "https://api.cohere.com/v1/embed",
      "apiKey": "COHERE_API_KEY",
      "dimensions": 1024,
      "documentTemplate": "A product named '{{doc.name}}' described as '{{doc.description}}'",
      "request": {
        "model": "embed-english-v3.0",
        "texts": ["{{text}}", "{{..}}"],
        "input_type": "search_document"
      },
      "response": {
        "embeddings": ["{{embedding}}", "{{..}}"]
      }
    }
  }
  ```
</CodeGroup>

In this configuration:

* `source`: must be `"rest"` because Cohere uses the REST embedder integration
* `url`: the Cohere embeddings API endpoint
* `apiKey`: your Cohere API key
* `dimensions`: the number of dimensions for the chosen model (1024 for `embed-english-v3.0`)
* `documentTemplate`: a [Liquid template](/capabilities/hybrid_search/advanced/document_template_best_practices) that converts your documents into text for embedding
* `request`: defines the structure of requests sent to Cohere, including the model and input format
* `response`: tells Meilisearch where to find the embeddings in Cohere's response

<Note>
  The `input_type` parameter is required by Cohere's API. Set it to `"search_document"` when indexing documents. Meilisearch automatically uses `"search_query"` for search queries.
</Note>

## Update your index settings

Send the embedder configuration to Meilisearch:

<CodeGroup>
  ```sh theme={null}
  curl \
    -X PATCH 'MEILISEARCH_URL/indexes/INDEX_NAME/settings' \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer MEILISEARCH_KEY' \
    --data-binary '{
      "embedders": {
        "my-cohere": {
          "source": "rest",
          "url": "https://api.cohere.com/v1/embed",
          "apiKey": "COHERE_API_KEY",
          "dimensions": 1024,
          "documentTemplate": "A product named '\''{{doc.name}}'\'' described as '\''{{doc.description}}'\''",
          "request": {
            "model": "embed-english-v3.0",
            "texts": ["{{text}}", "{{..}}"],
            "input_type": "search_document"
          },
          "response": {
            "embeddings": ["{{embedding}}", "{{..}}"]
          }
        }
      }
    }'
  ```
</CodeGroup>

Replace `MEILISEARCH_URL` with the address of your Meilisearch project, `INDEX_NAME` with your index name, `MEILISEARCH_KEY` with your Meilisearch API key, and `COHERE_API_KEY` with your [Cohere API key](https://dashboard.cohere.com/api-keys).

Meilisearch will start generating embeddings for all documents in the index. Monitor progress through the [task queue](/reference/api/tasks/list-tasks).

<Warning>
  Never share your Cohere API key publicly or commit it to version control. Use environment variables or a secrets manager to store it securely.
</Warning>

## Test the embedder

Once indexing is complete, perform a search using the `hybrid` parameter:

<CodeGroup>
  ```json theme={null}
  {
    "q": "something to stir soup with",
    "hybrid": {
      "semanticRatio": 0.5,
      "embedder": "my-cohere"
    }
  }
  ```
</CodeGroup>

A [`semanticRatio`](/capabilities/hybrid_search/advanced/custom_hybrid_ranking) of `0.5` returns a balanced mix of keyword and semantic results. Adjust this value based on your needs.

## Next steps

<CardGroup cols={2}>
  <Card title="Choose an embedder" href="/capabilities/hybrid_search/how_to/choose_an_embedder">
    Compare Cohere with other embedder providers
  </Card>

  <Card title="Document templates" href="/capabilities/hybrid_search/advanced/document_template_best_practices">
    Optimize which fields are embedded for better results
  </Card>
</CardGroup>