Skip to main content
Follow these steps to create a pipe, build a simple pipeline, and extract structured data from a document.

​
Prerequisites

DocPipe is currently in private beta. If you don’t have an account yet, request access at docpipe.ai/beta. Once your invite is approved you’ll receive an email with a link to complete signup.
1

Sign up and log in

Go to docpipe.ai and create your account. After signing in, you land on the Dashboard. Click Pipes in the sidebar to continue.
2

Create your first pipe

Click New Pipe and enter a name (for example, “Invoice Extraction”). A pipe is a container that holds your pipeline configuration, uploaded documents, and processing runs.
3

Build a pipeline

Navigate to the Pipeline tab inside your new pipe. The visual editor opens with an empty canvas.Add these three nodes to create a basic extraction pipeline:
  1. Upload trigger: accepts document uploads
  2. Extract action: uses AI to extract structured data from the document. Configure a schema with the fields you want to extract (for example: vendor_name, invoice_number, total_amount).
  3. Email output: sends the extracted data to an email address when processing completes
Connect the nodes in order: Upload Trigger → Extract Action → Email Output.Click Save to save your pipeline, then Activate to enable it.
4

Upload a document

Inside your pipe, click Upload. In the upload dialog, drag and drop a document or click to browse. DocPipe supports PDF, JPEG, PNG, TIFF, and HEIC formats.Once uploaded, a run starts automatically. You can watch the progress in real time.
5

View results

Click the Runs tab inside your pipe. Click on a run row to open its detail page, which shows each step in your pipeline, its status, and the extracted data.If you configured an email output, the extracted data is also sent to your email address.

​
Next steps

Build your first pipeline

Learn more about the visual pipeline editor and all available node types

Core concepts

Understand pipes, pipelines, runs, and review tasks in depth

Schema design

Design effective extraction schemas for your documents

API access

Trigger pipelines programmatically via the HTTP API