Skip to main content

Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API

Workflow preview

Workflow preview
100%
Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API preview
Open on n8n.io

1. Workflow Overview

N8N AI LLM Unstructured Invoice data PDF OCR recognition to JSON output API What this workflow does 1. Accepts a PDF or image upload via Webhook as binary property "data" 2. Runs OCR with the Mistr...

Best for

  • Invoice Processing automation workflows
  • AI Summarization automation workflows
  • intermediate n8n builders looking for reusable templates

Tools used

n8n-nodes-base.webhook, n8n-nodes-base.mistralai, n8n-nodes-base.code, n8n-nodes-base.httprequest, n8n-nodes-base.if, n8n-nodes-base.respondtowebhook, n8n-nodes-base.stickynote

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Venkata V.

Original n8n.io source

1.1 Workflow description

Title
Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API
Workflow name
Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API

N8N AI LLM Unstructured Invoice data PDF OCR recognition to JSON output API

What this workflow does

  1. Accepts a PDF or image upload via Webhook as binary property "data"
  2. Runs OCR with the Mistral OCR node
  3. Normalizes OCR text
  4. Sends OCR text to an LLM to extract structured JSON
  5. Cleans and normalizes the JSON
  6. Returns either:
  • status: ok
  • status: review_needed

Setup

  1. Import the workflow JSON into n8n
  2. Create/attach Mistral AI credentials on the "Mistral OCR" node
  3. Create/attach your choice LLM AI credentials on the OCR text to JSON converson node
  4. Activate the workflow
  5. POST a file to: /webhook/ocr-to-json

Notes

  • This starter is tuned for invoices/documents but can be adapted for receipts, purchase orders, or forms.
  • Depending on your installed n8n version, the Mistral node parameter names may need minor adjustment after import.
  • The workflow returns review_needed when confidence is below 0.5.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Webhook

Type / Role
n8n-nodes-base.webhook - webhook
Config choices
Version 2

Block 2 - Mistral OCR

Type / Role
n8n-nodes-base.mistralAi - mistralAi
Config choices
Version 1

Block 3 - Normalize OCR Text

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 4 - LLM Extract JSON

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Block 5 - Clean JSON

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 6 - Confidence >= 0.5?

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.2

Block 7 - Respond OK

Type / Role
n8n-nodes-base.respondToWebhook - respondToWebhook
Config choices
Version 1.1

Block 8 - Respond Review

Type / Role
n8n-nodes-base.respondToWebhook - respondToWebhook
Config choices
Version 1.1

Block 9 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 10 - Sticky Note1

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 11 - Sticky Note3

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 12 - Sticky Note5

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 13 - Sticky Note2

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

3. Summary Table

Workflow Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API
Complexity intermediate
Nodes 13
Categories Invoice Processing, AI Summarization
Author Venkata V
Published 22 Apr 2026

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/15220/15220.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Extract structured invoice JSON from PDFs with Mistral OCR and an LLM API do?

N8N AI LLM Unstructured Invoice data PDF OCR recognition to JSON output API What this workflow does 1. Accepts a PDF or image upload via Webhook as binary property "data" 2. Runs OCR with the Mistr...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Invoice Processing, AI Summarization use case.