# Vector Databases

This guide walks you through deploying a vector database on the Dynamiq platform, which allows you to integrate open-source vector databases like Weaviate seamlessly. 

<figure><img src="/files/8XUgla5fCzQFWIsbMdpz" alt=""><figcaption></figcaption></figure>

1. Navigate to the **Deployments** page.
2. Select the **Vector Databases** sub-tab within the **Deployments** page.
   * If no vector databases have been created yet, you’ll see a message: “You don't have any vector databases yet.” Click on **Deploy a vector database** to get started.
3. In the **Add new deployment** form, provide the following details:
   * **Name**: Enter a unique name for your vector database deployment.
   * **Description**: Optionally, add a brief description to clarify the database’s purpose or any specific details about its use.
   * **Engine**: Choose the database engine you want to use. Currently, Dynamiq supports **Weaviate**.
   * **Engine Version**: Select the version of the Weaviate engine. For example, **1.25.0**.
   * Choose a **Resource Profile** from the options available. Each profile specifies the computational resources for the deployment.
   * **Advanced Configuration:**
     * **Replicas**: Set the number of replicas for your vector database. The default is 1.
     * **Storage Size**: Specify the storage size for the database (e.g., 10Gi).
4. After filling out the advanced configurations, click **Create** to initiate the database deployment. Once you submit the form, Dynamiq will initiate the deployment process. You’ll be redirected to a page where you can view the status of your deployment. It may initially show as **Pending**. The database will be available for usage in a couple of minutes once the status is transitioned to **Running**.
5. Connect to the database:
   * After the deployment is complete (it has status **Running**), navigate to the **Access** section.
   * You’ll see the connection details, including two pairs of roles and API keys. These keys are essential for secure access to the vector database.
   * To connect to your vector database:
     * Set `WEAVIATE_API_KEY` environment variable with the credentials found in the **Access** section.
     * Use the provided code snippet in **Python** to establish a connection to Weaviate.
     * Ensure you have the necessary client library installed. Run:

{% code fullWidth="false" %}

```bash
pip install weaviate-client
```

{% endcode %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.getdynamiq.ai/deployments/vector-databases.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.