How to Create a Confluence API Token

Approximate time to complete: 5-7 minutes, excluding prerequisites

This how to article will give you step by step instructions for creating a Confluence API token. It will also show you how to configure a source connector from Vectorize to your GCS bucket so you can use your bucket in a RAG pipeline.

Before you begin

Before starting, ensure you have access to the credentials, connection parameters, and API keys as appropriate for the following:

• A Vectorize account (Create one free here ↗)

• A Confluence Account (Create one free here ↗)

Step 1: Create a Confluence API Token

1. Open Confluence.

2. Go to your profile, then click on Manage Account.

   

   Go to Manage Account
3. Go to the Security tab, then click on Create and manage API tokens.

   

   Go to API Tokens
4. Click Create API token.
5. Give your token a descriptive name, then click Create.
6. Copy your API token, and save it securely.

Step 5: Configure a Confluence Connector in Vectorize

1. Open the Vectorize Dashboard

   • Navigate to the Vectorize dashboard after logging in.

2. Select "Source Connectors"

   • From the left-hand menu, find the Source Connectors option under Integrations.

To configure a connector to your Confluence instance:

1. Click Source Connectors from the main menu.

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

3. Select the Confluence card.

   

   Confluence Card
4. Enter the integration name, your Confluence username, API token, and domain, and one or more Confluence spaces for your pipeline to pull data from, then click Create Confluence Integration.

   

   Confluence Parameters

The following table outlines the fields available when configuring a Confluence source for use within a Retrieval-Augmented Generation (RAG) pipeline.

Field	Description	Required
Name	The integration's name.	Yes
Username	The username (email address) of the Confluence user to run as.	Yes
API Token	The Confluence API token.	Yes
Domain	The URL for your Confluence installation. Ex. vectorize.atlassian.net.	No
Spaces	One or more Confluence spaces to pull data from. Allowed formats: - Space name (ex. "RAG Pipelines" - Space key (ex. "RP")	Yes

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

The second part is the configuration that's specific to your RAG Pipeline. This allows you to optionally specify a root folder in your Confluence space to pull data from, as opposed to pulling data from the entire space.

Configuring Confluence for RAG Pipeline

After the integration is successfully created, your Confluence connector can now be used as part of a RAG Pipeline.