OneDrive

Use the OneDrive Connector to ingest files from Microsoft OneDrive for Business (Microsoft 365) into the mAItion knowledge base.

What It Does

discovers files via the Microsoft Graph API by folder ID, folder path, file IDs, file paths, or the whole drive
recursively traverses subfolders and follows OneDrive shared/remote items
converts downloaded files to Markdown for indexing
filters by MIME type and skips files above a configurable size limit
runs ingestion on configurable schedules

Authentication

The connector uses App authentication (client credentials) via client_id, client_secret, and tenant_id. Only OneDrive for Business is supported — OneDrive Personal accounts are not supported. The Azure app registration needs the application permission Files.Read.All with admin consent granted. Without it, Graph API calls fail with a 403 error.

Required Environment Variables

Set these in .env.rag:

ONEDRIVE1_CLIENT_ID: Azure app registration client ID
ONEDRIVE1_CLIENT_SECRET: Azure app registration client secret
ONEDRIVE1_TENANT_ID: Azure tenant ID
ONEDRIVE1_USER_PRINCIPAL_NAME: user principal name / email of the OneDrive owner (example: user@your-org.onmicrosoft.com)
ONEDRIVE1_SCHEDULES: ingestion interval in seconds (default: 3600)

`config.yaml` Example

sources:
  - type: "onedrive"
    name: "onedrive1"
    enabled: true  # optional, default: true
    config:
      client_id: "${ONEDRIVE1_CLIENT_ID}"
      client_secret: "${ONEDRIVE1_CLIENT_SECRET}"
      tenant_id: "${ONEDRIVE1_TENANT_ID}"
      userprincipalname: "${ONEDRIVE1_USER_PRINCIPAL_NAME}"
      folder_path: "Documents/Reports"  # optional: hardcode directly in config
      folder_id:                        # optional: OneDrive folder ID
      file_ids:                         # optional: comma-separated file IDs
      file_paths:                       # optional: comma-separated file paths
      mime_types:                       # optional: comma-separated MIME types to filter
      recursive: true                   # optional, default true
      max_file_size_mb: 50              # optional, default 50; files larger than this are skipped
      schedules: "${ONEDRIVE1_SCHEDULES}"

`.env.rag` Example

ONEDRIVE1_CLIENT_ID=your-azure-app-client-id
ONEDRIVE1_CLIENT_SECRET=your-azure-app-client-secret
ONEDRIVE1_TENANT_ID=your-azure-tenant-id
ONEDRIVE1_USER_PRINCIPAL_NAME=user@your-org.onmicrosoft.com
ONEDRIVE1_SCHEDULES=3600

Configuration Reference

Field	Required	Default	Description
`enabled`	no	`true`	Set to `false` to skip this source entirely
`client_id`	yes	—	Azure app registration client ID
`client_secret`	yes	—	Azure app registration client secret
`tenant_id`	yes	—	Azure tenant ID
`userprincipalname`	yes	—	User principal name / email of the OneDrive owner
`folder_id`	no	—	OneDrive folder ID to ingest
`folder_path`	no	—	Relative path of the OneDrive folder to ingest
`file_ids`	no	—	Comma-separated OneDrive file IDs to ingest
`file_paths`	no	—	Comma-separated OneDrive file paths to ingest
`mime_types`	no	all	Comma-separated MIME types to filter
`recursive`	no	`true`	Traverse subfolders recursively
`max_file_size_mb`	no	`50`	Skip files larger than this size
`schedules`	no	`3600`	Ingestion interval in seconds

If none of folder_id, folder_path, file_ids, or file_paths are set, all files from the drive root are loaded.

Multiple OneDrive Sources

Add more sources entries (onedrive2, onedrive3, etc) with separate env vars per source.

Getting started

Features

Connectors

Tools

Configuration

What It Does

Authentication

Required Environment Variables

`config.yaml` Example

`.env.rag` Example

Configuration Reference

Multiple OneDrive Sources

​What It Does

​Authentication

​Required Environment Variables

​config.yaml Example

​.env.rag Example

​Configuration Reference

​Multiple OneDrive Sources

What It Does

Authentication

Required Environment Variables

`config.yaml` Example

`.env.rag` Example

Configuration Reference

Multiple OneDrive Sources