Sign up
All data sources

Document Ingestion

Your account

Unified OneDrive + SharePoint document ingestion and structured extraction. CRITICAL USAGE RULES: 1. Use ingest_onedrive_folder() to list/search OneDrive files, download, parse, and normalize. 2. Use ingest_sharepoint_library() to resolve site/drive, ingest library files, and normalize. 3. Parsers support: PDF, CSV, XLSX/XLS, DOCX/DOC, TXT (max file size configurable). 4. Incremental mode supports existing itemId + etag/lastModified to skip unchanged files. 5. Use extract_structured_data() for strict typed extraction (invoice, lease, report). 6. Use upsert_document_record() to keep raw text and extracted JSON separate in a deterministic record shape.

Set up this sourceGet the full contract and schemas as JSON

Sign in with your Document Ingestion account. Included on Free.

What you can ask

  • “What does Document Ingestion have for the area or asset I'm working on?”
  • “Pull the most recent Document Ingestion records and put them in a table.”
  • “What does Document Ingestion cover, and how fresh is the data?”

About this source

Unified OneDrive + SharePoint document ingestion and structured extraction. CRITICAL USAGE RULES: 1. Use ingest_onedrive_folder() to list/search OneDrive files, download, parse, and normalize. 2. Use ingest_sharepoint_library() to resolve site/drive, ingest library files, and normalize. 3. Parsers support: PDF, CSV, XLSX/XLS, DOCX/DOC, TXT (max file size configurable). 4. Incremental mode supports existing itemId + etag/lastModified to skip unchanged files. 5. Use extract_structured_data() for strict typed extraction (invoice, lease, report). 6. Use upsert_document_record() to keep raw text and extracted JSON separate in a deterministic record shape.

Connector ID document_ingestion

Provenance

PublisherDocument Ingestion
API basehttps://graph.microsoft.com/

Freshness & coverage

FreshnessFreshness not declared
GeographicNot declared
TemporalNot declared
AuthenticationCredentials required (OAuth)

› Methods (5)

Technical detail for developers: parameters, pagination, units, and freshness per method.

  • parse_document

    unknown

    Parse document text from a URL, share link, drive item, or content.

  • ingest_onedrive_folder

    unknown

    Bulk document ingestion: parse and normalize every file in a OneDrive folder into clean text.

    Entitiesdocument

  • ingest_sharepoint_library

    unknown

    Bulk document ingestion: parse and normalize every file in a SharePoint library into clean text.

    Entitiesdocument

  • extract_structured_data

    unknown

    Extract structured fields from normalized documents.

    Required paramsschemaTypedocuments

  • upsert_document_record

    write

    Merge normalized documents and extracted data into deterministic records.

    Required paramsrecords