Skip to main content

Notion Source Connector

The Notion Source Connector allows you to integrate Notion as a data source for your pipelines. This guide explains the configuration options available when setting up a Notion connector.

Configure the connector

To configure a connector to your Notion account:

  1. Click Source Connectors from the main menu.

  2. Click New Source Connector from the Source Connectors page.

  3. Select the Notion card.

  4. Enter a name for your integration, then click Authorize. Follow the prompts to grant Vectorize permission to access your Notion account.

    Authorize

    Important Note: When you authorize the Notion connector, your authorization choices affect which files you give access to for all current and future pipelines. For example, if you select a specific database, the connector will only have access to that database and its pages. If you select a workspace, the connector will have access to all databases and pages within that workspace. Keep this in mind when selecting permissions during the authorization process.

  5. Once permission is granted, you'll be returned to Vectorize and Notion Connected will display on the page.

  6. Click Create Notion Integration to complete the process.

Configuring the Notion Connector in a RAG Pipeline

When configuring the Notion connector in a RAG pipeline:

  1. You'll need to select which Notion databases and pages to include in your pipeline. Click Select Notion Resources to open the picker.

    Resource Selection

  2. In the resource picker, select the Notion databases and pages you want to include in your pipeline.

    Notion Resource Picker

  3. Click Save Selection to confirm your choices.

What's next?

  • If you haven't yet built a connector to your vector database, go to Configuring Vector Database Connectors and select the platform you prefer to use for storing output vectors.

    OR

  • If you're ready to start producing vector embeddings from your input data, head to Pipeline Basics. Select your new connector as the data source to use it in your pipeline.

Was this page helpful?