SharePoint / OneDrive

Text

The SharePoint / OneDrive connector is a text connector that fetches files from SharePoint sites or personal OneDrive using the Microsoft Graph API. It downloads file content and ingests claims via db.ingest_text().

How it works

Uses the Microsoft Graph API (graph.microsoft.com/v1.0) with Bearer token auth
Supports both SharePoint team sites and personal OneDrive
When site is provided, queries the SharePoint site drive; otherwise uses OneDrive
Lists files in the specified folder path (or root) with optional depth control
Downloads file content and passes it through text extraction
Each file is ingested as a separate text document via db.ingest_text()
Provenance tracks the file path and SharePoint site as source identifiers

SharePoint vs OneDrive

Mode	Parameter	API path
SharePoint site	`site="contoso.sharepoint.com:/sites/team"`	`/sites/{site}/drive/...`
Personal OneDrive	Omit `site`	`/me/drive/...`

1 Register an Azure AD application

In the Azure Portal, register an application with the Files.Read.All delegated permission (or Sites.Read.All for SharePoint access).

2 Get an access token

Use the OAuth 2.0 authorization code flow or client credentials flow to obtain a Bearer token. For testing, use the Graph Explorer.

3 Install requests

$ pip install requests

4 Connect

conn = db.connect("sharepoint",
    token=os.environ["GRAPH_ACCESS_TOKEN"],
    site="contoso.sharepoint.com:/sites/engineering",
)
result = conn.run(db)

Parameter	Required	Default	Description
`token`	Yes	—	Microsoft Graph API Bearer token
`site`	No	OneDrive	SharePoint site identifier (e.g. `contoso.sharepoint.com:/sites/team`)
`folder_path`	No	Root	Path within the drive to list files from
`max_files`	No	`50`	Maximum number of files to process
`extraction`	No	`heuristic`	Text extraction mode: `heuristic` or `llm`
`save`	No	`False`	Encrypt and persist token

SharePoint site

conn = db.connect("sharepoint",
    token=os.environ["GRAPH_ACCESS_TOKEN"],
    site="contoso.sharepoint.com:/sites/engineering",
)
result = conn.run(db)
print(f"Ingested {result.claims_ingested} claims")

Personal OneDrive

conn = db.connect("sharepoint",
    token=os.environ["GRAPH_ACCESS_TOKEN"],
    max_files=100,
)
result = conn.run(db)

With folder path

conn = db.connect("sharepoint",
    token=os.environ["GRAPH_ACCESS_TOKEN"],
    site="contoso.sharepoint.com:/sites/docs",
    folder_path="/General/Reports",
    extraction="llm",
    save=True,
)
result = conn.run(db)