# Jina AI

On Epsilla Cloud, you can enable Jina AI integration by providing your Jina AI API key (we securely manage your keys using AWS KMS):

<figure><img src="https://2532879721-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FM0ZX7fId7ifK45ldHWEp%2Fuploads%2Fgit-blob-d93f63040df42efdb36d852059caf1dbd4addd36%2FScreenshot%202024-05-18%20at%208.52.08%20AM.png?alt=media" alt=""><figcaption></figcaption></figure>

## Embeddings

Epsilla integrates with Jina AI with the following embedding models.

| Name                                    | Dimensions |
| --------------------------------------- | ---------- |
| **jinaai/jina-embeddings-v2-base-en**   | 768        |
| **jinaai/jina-embeddings-v2-base-de**   | 768        |
| **jinaai/jina-embeddings-v2-base-es**   | 768        |
| **jinaai/jina-embeddings-v2-base-zh**   | 768        |
| **jinaai/jina-embeddings-v2-base-code** | 768        |
| **jinaai/jina-embeddings-v2-small-en**  | 512        |

For Epsilla open source vector db, you just need to add a header in the data ingestion and semantic search queries [like this](https://epsilla-inc.gitbook.io/epsilladb/advanced-topics/embeddings#jina-ai-embedding).

Then you can start using the jinaai embedding model during vector table schema creation:

<figure><img src="https://2532879721-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FM0ZX7fId7ifK45ldHWEp%2Fuploads%2Fgit-blob-427b57942d4305068740c3962cbf9faf3efc1704%2FScreenshot%202024-01-10%20at%2010.52.40%20AM.png?alt=media" alt=""><figcaption></figcaption></figure>