SharePoint

Use the SharePoint Connector to ingest files or site pages from SharePoint into the mAItion knowledge base.

What It Does

authenticates to Microsoft Entra ID using client credentials (app registration)
fetches files from a SharePoint drive/folder, or pages from a SharePoint site
converts content to Markdown for indexing
runs ingestion on configurable schedules

Modes

File mode (sharepoint_type: file, default): loads files from a drive/folder
Page mode (sharepoint_type: page): loads SharePoint site pages

Authentication

Authentication uses Microsoft Entra ID client credentials (an Azure app registration) — client_id, client_secret, and tenant_id.

Required Environment Variables

Set these in .env.rag:

SHAREPOINT1_CLIENT_ID: Azure app registration client ID
SHAREPOINT1_CLIENT_SECRET: Azure app registration client secret
SHAREPOINT1_TENANT_ID: Azure tenant ID
SHAREPOINT1_SCHEDULES: ingestion interval in seconds (default is 3600)

`config.yaml` Example

File mode

sources:
  - type: "sharepoint"
    name: "sharepoint1"
    enabled: true  # optional, default: true
    config:
      client_id: "${SHAREPOINT1_CLIENT_ID}"
      client_secret: "${SHAREPOINT1_CLIENT_SECRET}"
      tenant_id: "${SHAREPOINT1_TENANT_ID}"
      # sharepoint_site_id can be provided instead of sharepoint_site_name.
      # One of the two is always required to resolve the SharePoint site.
      sharepoint_site_name: "MySite"
      # sharepoint_host_name and sharepoint_relative_url are optional and
      # informational only — they do not affect site resolution.
      # sharepoint_host_name: "contoso.sharepoint.com"
      # sharepoint_relative_url: "sites/YourSiteName"
      # sharepoint_folder_id can be provided instead of sharepoint_folder_path
      sharepoint_folder_path: "Documents/Reports"
      # drive_name: "Documents"                 # optional, name of the document library / drive
      sharepoint_type: "file"                   # "file" (default) or "page"
      recursive: true
      schedules: "${SHAREPOINT1_SCHEDULES}"

File mode — with folder path

sources:
  - type: "sharepoint"
    name: "sharepoint1"
    config:
      client_id: "${SHAREPOINT1_CLIENT_ID}"
      client_secret: "${SHAREPOINT1_CLIENT_SECRET}"
      tenant_id: "${SHAREPOINT1_TENANT_ID}"
      # sharepoint_site_name is required here — it cannot be resolved from
      # sharepoint_site_id alone when sharepoint_folder_path is set.
      sharepoint_site_name: "MySite"
      sharepoint_folder_path: "Documents/Reports"
      sharepoint_type: "file"
      recursive: true
      schedules: "${SHAREPOINT1_SCHEDULES}"

File mode — with site ID

sources:
  - type: "sharepoint"
    name: "sharepoint1"
    config:
      client_id: "${SHAREPOINT1_CLIENT_ID}"
      client_secret: "${SHAREPOINT1_CLIENT_SECRET}"
      tenant_id: "${SHAREPOINT1_TENANT_ID}"
      sharepoint_site_id: "11111111-2222-3333-4444-555555555555"
      sharepoint_type: "file"
      recursive: true
      schedules: "${SHAREPOINT1_SCHEDULES}"

Page mode

sources:
  - type: "sharepoint"
    name: "sharepoint1"
    config:
      client_id: "${SHAREPOINT1_CLIENT_ID}"
      client_secret: "${SHAREPOINT1_CLIENT_SECRET}"
      tenant_id: "${SHAREPOINT1_TENANT_ID}"
      sharepoint_site_name: "MySite"
      sharepoint_type: "page"
      schedules: "${SHAREPOINT1_SCHEDULES}"

`.env.rag` Example

SHAREPOINT1_CLIENT_ID=your-azure-app-client-id
SHAREPOINT1_CLIENT_SECRET=your-azure-app-client-secret
SHAREPOINT1_TENANT_ID=your-azure-tenant-id
SHAREPOINT1_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
`sharepoint_site_name`	one of `sharepoint_site_name` / `sharepoint_site_id`	—	SharePoint site name to resolve. Required (not just `sharepoint_site_id`) when `sharepoint_folder_path` is set in file mode
`sharepoint_site_id`	one of `sharepoint_site_name` / `sharepoint_site_id`	—	SharePoint site ID (alternative to `sharepoint_site_name`)
`sharepoint_host_name`	no	—	Informational only; does not affect site resolution. Site is always resolved via `sharepoint_site_name` or `sharepoint_site_id`
`sharepoint_relative_url`	no	—	Informational only; does not affect site resolution. Site is always resolved via `sharepoint_site_name` or `sharepoint_site_id`
`sharepoint_folder_path`	no (file mode)	—	Folder path to ingest files from; alternative to `sharepoint_folder_id`
`sharepoint_folder_id`	no (file mode)	—	Folder ID to ingest files from; alternative to `sharepoint_folder_path`
`drive_name`	no	—	Name of the document library / drive (file mode)
`sharepoint_type`	no	`file`	`file` to ingest files, or `page` to ingest site pages
`recursive`	no	`true`	Recurse into subfolders in file mode
`schedules`	no	`3600`	Ingestion interval in seconds

Multiple SharePoint Sources

Add more sources entries (sharepoint2, sharepoint3, etc) with separate env vars per source.

Getting started

Features

Connectors

Tools

Configuration

What It Does

Modes

Authentication

Required Environment Variables

`config.yaml` Example

File mode

File mode — with folder path

File mode — with site ID

Page mode

`.env.rag` Example

Configuration Reference

Multiple SharePoint Sources

​What It Does

​Modes

​Authentication

​Required Environment Variables

​config.yaml Example

​File mode

​File mode — with folder path

​File mode — with site ID

​Page mode

​.env.rag Example

​Configuration Reference

​Multiple SharePoint Sources

What It Does

Modes

Authentication

Required Environment Variables

`config.yaml` Example

File mode

File mode — with folder path

File mode — with site ID

Page mode

`.env.rag` Example

Configuration Reference

Multiple SharePoint Sources