Document Ingestion

Document ingestion is the critical first step in harnessing the power of Docsumo for efficient data extraction and document processing. This support article will guide you through the process of uploading documents using various methods and explain how to classify and split them for optimal results.

Uploading Documents

Docsumo provides multiple methods to upload documents.

  1. Manual Upload:
    • Log in to your Docsumo account.
    • Navigate to the side navigation and click upload at the top left corner.
    • Choose the document you want to upload from your local device.
    • Confirm the upload, and Docsumo will begin processing the document. Checkout this link for a detailed guide
  2. Using APIs:
    • If you're looking to automate document uploads, Docsumo offers a robust API.
    • Utilise the API to seamlessly integrate document uploads into your existing applications and workflows.
    • Detailed API documentation is available to help you get started.
  3. Zapier Integration:
    • For even more automation possibilities, you can integrate Docsumo with Zapier.
    • Create custom workflows to automatically trigger document uploads and processing based on specific events in other applications.

Classifying & Splitting a Document

Once your documents are uploaded, you may need to classify and split them for efficient processing.

  1. Classifying Documents:

    • Document classification helps classify different type or category of a document to the relevant document type for accurate results.
    • You can either manually classify documents and upload them to the right document type or manually classify them again if uploaded to the wrong document type while reviewing the document.
    • Setup Auto Classification model, so you do not have to put in manual effort to classify them and upload to the right document type.
  2. Splitting a Document:

    • Document splitting is useful when a single document contains multiple sections or entities that you want to process separately or only a part of document is relevant for extraction everything else is of no use.
    • Similar to classification you can setup an auto split rule based on your needs.
    • Or you can also, split them manually while reviewing the documents on the review screen and then classify them to the right document type or even delete the parts which are of no use.

Whether you're dealing with invoices, receipts, contracts, or any other type of document, Docsumo's versatile document ingestion capabilities make it easy to handle your document processing needs.