OneDrive
Last updated
Last updated
The OneDrive Source Connector allows you to integrate OneDrive as a data source for your pipelines. This guide explains the configuration options available when setting up a OneDrive connector.
Before starting, you'll need:
A Microsoft Entra ID application.
One or more Microsoft 365 users.
The following information for your app:
Client Id
Tenant Id
Client Secret
User email address(es)
If you don't have an application created yet, check out our guide How to Create a Microsoft Entra ID Application.
To configure a OneDrive connector to your Microsoft Entra ID application:
Click Source Connectors from the main menu.
Click New Source Connector from the Source Connectors page.
Select the OneDrive card.
Enter the name, client id, tenant id, client secret, and user email address(es) in the form using the OneDrive Parameters table below as a guide, then click Create OneDrive Integration.
Name
A descriptive name to identify the connector within Vectorize.
Yes
Client Id
The Microsoft Entra Id application's client id.
Yes
Tenant Id
The Microsoft Entra Id application's tenant
Yes
Client Secret
The Microsoft Entra Id application's client secret value.
Yes
Users
The email addresses for the OneDrive users whose files will be ingested. Enter one address per line, and select + Add to add each additional user.
Yes
You can think of the OneDrive connector as having two parts to it. The first is authorization with your Microsoft Entra ID application. 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, such as which files and directories should be processed.
The following table outlines the fields available when configuring a OneDrive source for use within a Retrieval-Augmented Generation (RAG) pipeline.
File Extensions
Specifies the types of files to be included (e.g., PDF, HTML, Markdown, Text, DOCX).
Yes
Read starting from this folder
Specifies the OneDrive root folder to pull content from. Content will be ingested from any subfolders under the root folder.
No
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.