Convert PDF, DOC, and images to Markdown using Datalab.to API
Ready for 3.0What this workflow does
This workflow has 6 nodes and runs when someone submits an n8n form (“upload file”). It uses only n8n's built-in nodes. It also calls datalab.to over HTTP.
How it runs
Trigger: When someone submits an n8n form (“upload file”).
- Send to Datalab API (HTTP Request): calls datalab.to (POST)
- Wait: waits 10 seconds
- Get Markdown (HTTP Request): calls an HTTP API
- Set Fields (Edit Fields (Set)): sets 1 field: markdown
- Switch: routes items into 2 branches
HTTP calls to: datalab.to
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (5)
- n8n Form Trigger
n8n-nodes-base.formTrigger - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Wait
n8n-nodes-base.wait - Switch
n8n-nodes-base.switch
From the author
This n8n workflow converts various file formats (.pdf, .doc, .png, .jpg, .webp) to clean markdown text using the datalab.to API. Perfect for AI agents, LLM processing, and RAG (Retrieval Augmented Generation) data preparation for vector databases. Workflow…