Parse and Extract Data from Documents/Images with Mistral OCR

by Jimleuk ✓ · 44,545 views · created 2025-03-06 · Document Extraction, Multimodal AI

What this workflow does

This workflow has 17 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Drive. It also calls api.mistral.ai over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Document URL (Edit Fields (Set)): sets 1 field: url
2. Image URL (Edit Fields (Set)): sets 1 field: url
3. Mistral DOC OCR (HTTP Request): calls api.mistral.ai (POST)
4. Mistral IMAGE OCR (HTTP Request): calls api.mistral.ai (POST)
5. Import PDF (Google Drive): download
6. Mistral Upload (HTTP Request): calls api.mistral.ai (POST)
7. Mistral Signed URL (HTTP Request): calls an HTTP API
8. Mistral DOC OCR (HTTP Request): calls api.mistral.ai (POST)
9. Import Image (Google Drive): download
10. Mistral Upload (HTTP Request): calls api.mistral.ai (POST)

…plus 6 more steps. See the full node list below.

Services it uses

Google Drive

HTTP calls to: api.mistral.ai

Before you upgrade to n8n 3.0

Nodes used (4)

• HTTP Requestn8n-nodes-base.httpRequest
• Manual Triggern8n-nodes-base.manualTrigger
• Google Driven8n-nodes-base.googleDrive
• Edit Fields (Set)n8n-nodes-base.set

From the author

Mistral OCR is a super convenient way to parse and extract data from multi-page PDFs or single images using AI. What makes it special and differs it from the competition is that Mistral OCR also performs document page splitting and markdown conversion. This…

View the original on n8n.io → Check your own copy