Sign up
All data sources

Document Ingestion

OAuthdocument_ingestion

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.

Get this contract as JSON

Provenance

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

Freshness & coverage

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

Methods (4)

  • ingest_onedrive_folder

    unknown

    List, download, parse, and normalize OneDrive files from a folder.

    Input schema
    {
  "type": "object",
  "properties": {
    "folderId": {
      "type": "string",
      "description": "Optional OneDrive folder ID."
    },
    "folderPath": {
      "type": "string",
      "description": "Optional OneDrive folder path."
    },
    "query": {
      "type": "string",
      "description": "Optional search query."
    },
    "fileTypes": {
      "type": "array",
      "description": "Allowed file extensions such as pdf, docx, or xlsx.",
      "items": {
        "type": "string"
      }
    },
    "skipUnchanged": {
      "type": "boolean",
      "description": "Skip unchanged files."
    }
  },
  "additionalProperties": true
}

  • ingest_sharepoint_library

    unknown

    Resolve a SharePoint site and library, then ingest and normalize files.

    Input schema
    {
  "type": "object",
  "properties": {
    "siteId": {
      "type": "string",
      "description": "Optional SharePoint site ID."
    },
    "siteQuery": {
      "type": "string",
      "description": "Optional SharePoint site search query."
    },
    "driveId": {
      "type": "string",
      "description": "Optional SharePoint drive ID."
    },
    "query": {
      "type": "string",
      "description": "Optional search query."
    },
    "fileTypes": {
      "type": "array",
      "description": "Allowed file extensions such as pdf, docx, or xlsx.",
      "items": {
        "type": "string"
      }
    },
    "skipUnchanged": {
      "type": "boolean",
      "description": "Skip unchanged files."
    }
  },
  "additionalProperties": true
}

  • extract_structured_data

    unknown

    Extract structured fields from normalized documents.

    Required paramsschemaTypedocuments
    Input schema
    {
  "type": "object",
  "properties": {
    "schemaType": {
      "type": "string",
      "description": "Extraction schema such as invoice, lease, or report."
    },
    "documents": {
      "type": "array",
      "description": "Normalized documents to extract from.",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "schemaType",
    "documents"
  ],
  "additionalProperties": true
}

  • upsert_document_record

    write

    Merge normalized documents and extracted data into deterministic records.

    Required paramsrecords
    Input schema
    {
  "type": "object",
  "properties": {
    "records": {
      "type": "array",
      "description": "Document/extraction record pairs.",
      "items": {
        "type": "object"
      }
    },
    "existingRecords": {
      "type": "array",
      "description": "Existing stored records for incremental merging.",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "records"
  ],
  "additionalProperties": true
}