Invoice data extraction with LlamaParse and OpenAI

2. Advanced PDF Processing with LlamaParse [Read more about using HTTP Requests](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.httprequest/) LlamaIndex's LlamaCloud is a cloud-based service that allows you to upload, parse, and index document. LlamaParse is a tool offered by LlamaCloud to parse for complex PDFs with embedded objects ie PDF Tables and figures. At time of writing, you can parse 1000 pdfs/day with LlamaCloud's free plan by signing up at [https://cloud.llamainde

Workflow Structure (17 nodes)
100%
Gmail Trigger
Receiving Invoices
Split Out
Split Out Labels
Gmail
Get Labels Names
Merge
Email with Label Names
If
Should Process Email?
Http Request
Upload to LlamaParse
Http Request
Get Processing Status
Switch
Is Job Ready?
Http Request
Get Parsed Invoice Data
Langchain.lm Open Ai
OpenAI Model
Langchain.chain Llm
Apply Data Extraction Rules
Langchain.output Parser Structured
Structured Output Parser
Set
Map Output
Google Sheets
Append to Reconciliation Sheet
Gmail
Add "invoice synced" Label
Aggregate
Combine Label Names
Wait
Wait to stay within service limits
Node Types:
default
http
trigger
action
logic
transform
Requires credentials

Prerequisites

Required Credentials (4)

Gmail

Used by: Receiving Invoices, Add "invoice synced" Label +1 more

Docs

Google Sheets

Used by: Append to Reconciliation Sheet

Docs

HTTP Header Auth

Used by: Upload to LlamaParse, Get Processing Status +1 more

Docs

OpenAI

Used by: OpenAI Model

Docs

Multiple services required

This workflow needs 4 different credentials. Make sure you have accounts for all services before importing.

Complexity

Advanced

Expert level. Custom code, complex logic, many integrations.

Setup time: ~55 min
Score: 70/100
Conditional Logic
5 Integrations

When to Use This Workflow

Automated Reporting

Automatically collect and organize data into spreadsheets for analysis.

Spend less time on data entry and more time on insights.

Email Automation

Automate email responses, forwarding, or organization based on rules.

Handle routine email tasks automatically and focus on what matters.

Real-time Response

React instantly when events happen - new orders, form submissions, or API calls.

Zero delay between trigger and action for time-sensitive workflows.

workflow.json
{
  "meta": {
    "instanceId": "26ba763460b97c249b82942b23b6384876dfeb9327513332e743c5f6219c2b8e"
  },
  "nodes": [
    {
      "id": "7076854e-c7e8-45b5-9e5e-16678bffa254",
      "name": "OpenAI Model",
      "type": "@n8n/n8n-nodes-langchain.lmOpenAi",
      "position": [
        2420,
        480
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-3.5-turbo-1106",
          "cachedResultName": "gpt-3.5-turbo-1106"
        },
...

Workflow Details

Nodes
26
Trigger
Event
Source
awesome
Added
Dec 4, 2025

Need Help?

Check out the official n8n documentation for detailed guides.

Related Workflows

Extract data from resume and create PDF with Gotenberg

Add chat ID Remember to set your actual ID to trigger automation from Telegram.

Lmchatopenai
Outputparserautofixing
Outputparserstructured
Telegram
43 nodesEvent
Curated

Extract spend details (template)

A. Get data - Set up labels in Gmail - Suggested using Gmail filters to move emails to labels automatically

Gmail
Outputparserstructured
Lmchatgooglegemini
Google-sheets
24 nodesEvent
Curated

Social Media Analysis and Automated Email Generation

Personalize here Set: - your name - your company name - your company activity, used to find a match with your leads - y...

Http-request
Lmchatopenai
Outputparserstructured
Chainllm
19 nodesEvent
Curated

CV Resume PDF Parsing with Multimodal Vision AI

Try me out! This workflow converts a Candidate Resume PDF to an image which is then "read" by a Vision Language Model (...

Outputparserstructured
Google-drive
Http-request
Editimage
13 nodesManual
Curated

Visual Regression Testing with Apify and AI Vision Model

Part A. Generate Base Images Before we can run our visual regression tests, we must generate a series of base screenshot...

Google-drive
Lmchatgooglegemini
Outputparserstructured
Http-request
34 nodesScheduled
Curated

Monthly Spotify Track Archiving and Playlist Classification

Monthly Spotify Track Archiving and Playlist Classification This n8n workflow allows you to automatically archive your m...

Http-request
Lmchatanthropic
Spotify
Outputparserstructured
37 nodesScheduled
Curated