Getting Started

Welcome to Tavnit

Tavnit helps you automatically extract data from documents like invoices, receipts, and forms. Instead of manually typing information from each document, Tavnit reads them for you and organizes the data in a structured way.

This guide will walk you through creating your first flow and processing documents.

Step 1: Create a Flow

A “flow” is like a template that tells Tavnit what information to look for in your documents. For example, an invoice flow might look for invoice numbers, dates, and line items.

  1. 1Click the "New Flow" button on the Flows page
  2. 2Enter a name for your flow (e.g., "Invoice Processing")
  3. 3Select the type of document you'll be processing
  4. 4Review and customize the fields Tavnit discovered
  5. 5Click "Activate" to make your flow ready to use

Step 2: Understanding Fields

When you upload sample documents, Tavnit uses AI to discover what information can be extracted. There are two types of fields:

Metadata Fields

Single values that appear once per document, like invoice number, date, or vendor name.

Table Fields

Repeating data like line items on an invoice, each with columns like description, quantity, and price.

You can add, remove, or rename fields to match exactly what you need.

Step 3: Process Documents

Once your flow is active, you can process documents in several ways:

Manual Upload

Go to the Runs page, select your flow, and upload documents directly through the web interface.

Email Integration

Send documents as email attachments to your flow's unique email address. See the Email Integration tab for details.

API Integration

Send documents programmatically from your own applications or automation tools. See the API Integration tab for details.

After processing, you'll see the extracted data on the run details page. You can also export results or receive them via webhook.