> ## 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.

# Semantic Search with Jina Embeddings

> Set up Meilisearch with Jina embedding models for semantic search.

Jina AI provides a range of embedding models with strong multilingual support and competitive pricing. This guide shows you how to configure Meilisearch with Jina embeddings using the REST embedder.

## Requirements

* A Meilisearch project
* A [Jina AI](https://jina.ai/) account with an API key

## Available models

| Model                           | Dimensions                     | Notes                                                      |
| ------------------------------- | ------------------------------ | ---------------------------------------------------------- |
| `jina-embeddings-v4`            | 128, 256, 512, 1,024, or 2,048 | Multimodal (text, images, PDFs), 32K context, multilingual |
| `jina-embeddings-v5-text-small` | 1,024                          | Text-only, balanced quality and speed                      |
| `jina-embeddings-v5-text-nano`  | 768                            | Smallest and fastest v5 model                              |
| `jina-embeddings-v3`            | 1,024                          | Previous generation, well-tested                           |
| `jina-colbert-v2`               | 128                            | Multi-vector model for fine-grained matching               |

For new projects, `jina-embeddings-v4` is the recommended choice with its multimodal support and flexible dimensions. If you only need text embeddings, the v5-text models offer a lighter alternative. See the [Jina models page](https://jina.ai/models/jina-embeddings-v4) for details.

## Configure the embedder

### Standard embedding models

Use this configuration for `jina-embeddings-v5-text-small`, `jina-embeddings-v5-text-nano`, or `jina-embeddings-v3`:

```json theme={null}
{
  "jina": {
    "source": "rest",
    "apiKey": "<JINA_API_KEY>",
    "dimensions": 1024,
    "documentTemplate": "A product named '{{doc.name}}': {{doc.description}}",
    "url": "https://api.jina.ai/v1/embeddings",
    "request": {
      "model": "jina-embeddings-v5-text-small",
      "input": ["{{text}}", "{{..}}"]
    },
    "response": {
      "data": [
        { "embedding": "{{embedding}}" },
        "{{..}}"
      ]
    }
  }
}
```

Adjust `model` and `dimensions` to match the model you choose (1024 for v5-text-small and v3, 768 for v5-text-nano).

### ColBERT multi-vector model

`jina-colbert-v2` uses a different API endpoint and response format:

```json theme={null}
{
  "jina-colbert": {
    "source": "rest",
    "apiKey": "<JINA_API_KEY>",
    "dimensions": 128,
    "documentTemplate": "A product named '{{doc.name}}': {{doc.description}}",
    "url": "https://api.jina.ai/v1/multi-vector",
    "request": {
      "model": "jina-colbert-v2",
      "input_type": "document",
      "embedding_type": "float",
      "input": ["{{text}}", "{{..}}"]
    },
    "response": {
      "data": [
        { "embeddings": ["{{embedding}}"] },
        "{{..}}"
      ]
    }
  }
}
```

### Send the configuration

```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": {
      "jina": {
        "source": "rest",
        "apiKey": "<JINA_API_KEY>",
        "dimensions": 1024,
        "documentTemplate": "A product named '\''{{doc.name}}'\'': {{doc.description}}",
        "url": "https://api.jina.ai/v1/embeddings",
        "request": {
          "model": "jina-embeddings-v5-text-small",
          "input": ["{{text}}", "{{..}}"]
        },
        "response": {
          "data": [
            { "embedding": "{{embedding}}" },
            "{{..}}"
          ]
        }
      }
    }
  }'
```

Replace `<JINA_API_KEY>` with your actual Jina API key.

Meilisearch handles batching and rate limiting automatically. Monitor the [tasks queue](/reference/api/tasks/list-tasks) to track indexing progress.

## Test the search

```json theme={null}
{
  "q": "comfortable shoes for walking",
  "hybrid": {
    "semanticRatio": 0.5,
    "embedder": "jina"
  }
}
```

## Next steps

* [Document template best practices](/capabilities/hybrid_search/advanced/document_template_best_practices) to optimize which fields are embedded
* [Custom hybrid ranking](/capabilities/hybrid_search/advanced/custom_hybrid_ranking) to tune the balance between keyword and semantic results
* [Embedder settings reference](/reference/api/settings/list-all-settings) for all configuration options