Turbopuffer Vector Database Integration

This guide walks you through configuring a Retrieval-Augmented Generation (RAG) pipeline in Vectorize using Turbopuffer as the vector database.

Before you Begin

Ensure you have:

• A Vectorize account (Create one free here ↗ )
• A Turbopuffer account and namespace.

Configure the integration

To configure a vector database integration to connect to your Turbopuffer instance:

1. Click Vector Databases from the main menu.

2. Click New Vector Database Integration from the Vector Databases page.

3. Select the Turbopuffer card.

   

4. Enter the parameters in the form using the Turbopuffer Parameters table below as a guide, then click Create Turbopuffer Integration.

   

Turbopuffer Parameters

Field	Description	Required
Name	A descriptive name to identify the integration within Vectorize.	Yes
API Key	Your Turbopuffer API key.	Yes

Configuring the Turbopuffer integration in a RAG Pipeline

You can think of the Turbopuffer integration as having two parts to it. The first is authorization with your Turbopuffer account. This part is re-usable across pipelines and allows you to connect to this same application in different pipelines without providing the credentials every time.

The second part is the configuration that's specific to your RAG Pipeline. This is where you specify the name of the namespace in your Turbopuffer database. If the namespace does not already exist, Vectorize will create it for you.

Enter your namespace name to complete configuration of your Turbopuffer integration for your RAG pipeline.

What's next?

• If you haven't yet built a connector to your source database, go to configure a source connector and select your source data platform.

  OR

• If you're ready to start creating pipelines for vectorizing data, head to Pipeline Basics.