Set up production- and compliance-ready data extraction in minutes with easybits
Hey there 
I’m Felix from easybits and if you’ve enjoyed this article then please consider giving us a like and follow on Linkedin.
Here is how to connect easybits data extraction solution to n8n for automated document data extraction.
What is easybits?
easybits data extraction platform is the easiest way to transform unstructured documents (PDFs, images) into clean, structured JSON data. You simply define which fields to extract, and the API returns them in a consistent format and what made it especially interesting for me: No complex setups, no maintenance.
Use cases:
-
Invoice processing
-
Insurance claim documents processing
-
ID and license extraction
-
Any document with repeatable structure
Step 1: Get Your Credentials from easybits
Before configuring n8n, you need your Pipeline ID and API Key from the easybits platform.
- Sign up for free and log in at https://extractor.easybits.tech/
Important: Discover how to build custom data extraction pipelines with the Quick Start Guide.
-
On your dashboard, click Pipelines in the left sidebar
-
Click View Pipeline on the pipeline you want to connect
-
On the Pipeline Details page, you will find:
-
API URL:
https://extractor.easybits.tech/api/pipelines/[YOUR_PIPELINE_ID] -
API Key: Your unique authentication token
-
-
Copy both values. You will need them in the next step.
Important: Each pipeline has its own API Key and Pipeline ID. If you have multiple pipelines (for example, one for invoices and one for driver licenses), you will need separate credentials for each.
Step 2: Create Credentials in n8n
-
In n8n, go to Settings > Credentials
-
Click Add Credential
-
Search for Header Auth
-
Configure:
-
Name: easybits - [Pipeline Name] (for example: “easybits - Invoices Pipeline”)
-
Header Name: Authorization
-
Header Value: Bearer [paste your API Key here]
-
-
Click Save
For multiple pipelines: Create a separate credential for each pipeline. Name them clearly so you know which is which (for example: “easybits - Invoices Pipeline”, “easybits - Driver Licenses Pipeline”, “easybits - Claims Pipeline”).
Step 3: Configure the HTTP Request Node
Add an HTTP Request node with these settings:
| Setting | Value |
|---|---|
| Method | POST |
| URL | https://extractor.easybits.tech/api/pipelines/[YOUR_PIPELINE_ID] |
| Authentication | Predefined Credential Type |
| Credential Type | Header Auth |
| Credential | Select your easybits credential |
| Send Body | ON |
| Body Content Type | JSON |
| Specify Body | Using JSON |
Request body:
{
”files”: [
”https://example.com/your-document.pdf”
]
}
Working with Multiple Pipelines
If you process different document types, you have two options:
Option A: Separate Workflows
Create a separate workflow for each document type. Each workflow uses its own pipeline URL and credentials.
-
Workflow 1: Invoice Processing (uses Invoice Pipeline)
-
Workflow 2: Driver License Verification (uses Driver License Pipeline)
-
Workflow 3: Claims Processing (uses Claims Pipeline)
Option B: Dynamic Pipeline Selection
Use a Switch node to route documents to different HTTP Request nodes based on document type.
Multi-Page Documents
Each request processes one document. For multi-page documents, include a URL for each page (processed together as one document):
{
“files”: [
“https://example.com/page1.pdf”,
“https://example.com/page2.pdf”
]
}
Maximum 5 pages per request.
Using Base64 Encoded Files
If you receive files as binary data (for example, email attachments):
{
“files”: [
“data:application/pdf;base64,JVBERi0xLjQK…”
]
}
Example Response
The response follows the schema you defined in your pipeline. For example (Invoice Pipeline):
{
“data”: {
“invoice_no”: “INV-2024-001”,
“date”: “2024-01-15”,
“total_amount”: 1250.00
}
}
Supported File Types
-
PDF (.pdf)
-
PNG (.png)
-
JPEG (.jpg, .jpeg)
We’re now live on n8n! Try our free data extraction workflow here: