AI - Document Parser in Make

What this module does

PDF4me AI - Document Parser extracts structured fields from any document type by running a saved Analyzer Template against the file. Pick the built-in default_invoice_extraction template or create a custom one in the PDF4me dashboard for receipts, contracts, purchase orders, lab results, ID cards, or any custom form. The module returns the extracted data on a single Doc Text output ready to feed into Parse JSON, Airtable, Google Sheets, or any downstream Make module. One template-driven action covers every document type you handle.

Related Blog Posts(1)

AI-Extract and Smart-Rename Any PDF in Make: A 4-Module Dropbox Workflow with PDF4me AI - Document Parser

Four-module Make scenario: pull a vendor PDF from Dropbox, run AI - Document Parser with default_invoice_extraction, Parse JSON to expose the vendorName, then re-upload with vendorName.pdf as the filename. Real screenshots, exact field values, no manual data entry.

Read post →

Authenticating Your API Request

Every PDF4me module in Make requires a valid Connection. Create or select one that holds your PDF4me API key so the scenario can authenticate AI extraction requests securely.

Get your API Key

Important Facts You Should Not Miss

Analyzer Template Id is what makes this module flexible

The AI Analyzer Id dropdown lets you swap between document types without changing any other module setting. Built-in default_invoice_extraction covers AP workflows; custom templates handle receipts, contracts, purchase orders, lab results, custom forms, anything you train.

Output is JSON on a single Doc Text field

The extracted data lands on the Doc Text output as a JSON string. Add a JSON → Parse JSON module immediately after, point JSON string at Doc Text, and every field becomes an individually mappable token downstream.

Smart-rename pattern: feed a parsed field into Upload File Name

After Parse JSON exposes the fields, drop the parsed token (for example vendorName) into the File Name field of the downstream Dropbox / Google Drive / OneDrive Upload module. The output file is automatically renamed using the extracted value, the cleanest AP-automation pattern.

Set File to Map, wire File Name and Document from the prior module, then pick the AI Analyzer Id (here the built-in default_invoice_extraction). Click Analyzer Template in the hint to create a custom template.

Parameters

Required: Connection, File Name (when File is Map), Document (when File is Map), and AI Analyzer Id.

Parameter	Required	What it does	Example
Connection	Yes	PDF4me connection. Click Add and paste your API key the first time, then reuse the connection across every PDF4me module.	My PDF4me connection
File	Yes	Radio button picking how the source document arrives at the module. Pick a quick storage option (Dropbox - Download a File) or choose Map to bind File Name and Document from any prior module.	Map
File Name	Conditional	Sub-field of File, shown when Map is selected. Filename of the source document including its extension (.pdf, .png, .jpg, .jpeg). Map from the prior module File Name output.	1. File Name
Document	Conditional	Sub-field of File, shown when Map is selected. Binary content of the document to be parsed. Map from the prior module Data / binary output.	1. Data
AI Analyzer Id	Yes	Dropdown picking the Analyzer Template the AI runs against the document. default_invoice_extraction is the built-in invoice template. Click Analyzer Template in the hint to create custom templates for receipts, contracts, purchase orders, or any document type.	default_invoice_extraction

Output

Field	Type	What it contains
Doc Text	String (JSON)	The full extracted JSON payload. Field names match what the chosen Analyzer Template returns (vendorName, invoiceNumber, totalAmount, lineItems, etc for default_invoice_extraction). Always wire into a JSON Parse JSON module to expose every field as an individually mappable Make token.

Sample file

Try the action end-to-end with a real vendor invoice. Drop this into your Dropbox source folder and run the scenario.

sample-vendor-invoice.pdf

Real 1-page vendor invoice used in the screenshots. Pairs cleanly with the built-in default_invoice_extraction analyzer template. returns vendorName, invoiceNumber, totalAmount, and line items.

Quick Setup

1. Add PDF4me to AI - Document Parser in your Make scenario.
2. Select Connection (or click Add to create one with your API key).
3. Set File to Map. Map File Name (1. File Name) and Document (1. Data) from the prior module.
4. Pick an AI Analyzer Id: default_invoice_extraction for invoices, or click Analyzer Template to build a custom one for receipts, contracts, purchase orders, or any document type.
5. Save and run. Pipe the Doc Text output into a JSON → Parse JSON module to expose every field as a mappable token downstream.

Workflow Examples

Common scenario patternsThree common ways to chain AI - Document Parser into a Make flow.

Vendor invoice to Airtable with smart rename

1. Dropbox Download a File pulls the new vendor invoice.
2. AI - Document Parser runs the default_invoice_extraction template.
3. JSON Parse JSON exposes vendorName, invoiceNumber, totalAmount, line items, etc.
4. Airtable Create a Record writes the parsed fields into the AP register.
5. Dropbox Upload a File archives the invoice with File Name set to {{vendorName}}.pdf for clean filing.

Custom contract clause extraction

1. Build a custom contract_clauses Analyzer Template in the PDF4me dashboard (effective_date, termination_clause, governing_law, parties, contract_value).
2. Trigger fires when a contract PDF lands in SharePoint.
3. AI - Document Parser runs the custom template.
4. Parse JSON + Google Sheets Add a Row writes a contract summary into the legal team tracker.

Email attachment to Slack approval

1. Outlook trigger fires on new email with PDF attachment.
2. AI - Document Parser runs default_invoice_extraction.
3. Parse JSON exposes total amount.
4. Make Filter routes invoices above $5,000 to Slack #approvals; the rest go straight to Airtable.

Frequently Asked Questions

What is the difference between AI - Document Parser and AI-Invoice Parser?+

AI-Invoice Parser uses a fixed invoice schema (vendor, line items, totals, dates). AI - Document Parser is template-driven: you pick an Analyzer Template by Id. The default_invoice_extraction template covers invoices; custom templates handle receipts, contracts, purchase orders, lab results, ID cards, custom forms. Use AI - Document Parser when you need flexibility or non-invoice document types in the same module.

Where do I create a custom Analyzer Template?+

From the AI Analyzer Id dropdown click the Analyzer Template link in the hint, or visit dev.pdf4me.com directly. Define the fields you want extracted, name the template, save. The new template appears in the AI Analyzer Id dropdown in Make on the next scenario edit.

What does the module output?+

A single Doc Text field on the module bundle containing the extracted data as a JSON string. Add a JSON → Parse JSON module right after, point JSON string at Doc Text, and every field becomes an individually mappable token downstream (Airtable, Google Sheets, Slack, HTTP, etc).

Can I use one of the extracted fields to rename the output file?+

Yes, and this is the cleanest AP-automation pattern. After Parse JSON exposes the fields, drop the parsed token (for example vendorName) directly into the File Name field of a downstream Upload module. The output file is automatically renamed using the extracted vendor.

What document formats does the module accept?+

PDF, PNG, JPG, and JPEG. Map any of these binary types into Document from a prior module (Dropbox, Google Drive, OneDrive, HTTP, Outlook attachment). The Analyzer Template handles the rest.

How does this compare to PDF4me Parse Document?+

Parse Document uses a regex / JavaScript Expression template you author in the dashboard for exact pattern matching. AI - Document Parser uses an AI Analyzer Template trained on a broader signal so it tolerates layout variation between vendors. Use Parse Document when fields land in fixed regions every time; AI - Document Parser when vendor / supplier layouts vary.

Related Modules

AI-Invoice Parser

Fixed-schema invoice parser. Use when you only handle invoices and want confidence scores per field out of the box.

Parse a Document (Regex / JS template)

Pattern-matching alternative. Use when fields land in fixed positions every time (same form, no layout variation).

AI-Process Receipt

Receipt-specific AI parser tuned for retail/expense receipts (merchant, items, tax, total).

Get Help

PDF4me on MakeGet your API KeyConnect PDF4me to Make