N8N Resume Data Extraction Workflow (Groq, Nvidia & Web Form)

Turn resume uploads into structured candidate profiles—automatically

This n8n Resume Data Extraction Workflow collects a resume PDF via an n8n form, extracts the text, uses an OpenAI-compatible chat model to convert it into structured JSON candidate data, and then shows a second review form prefilled with the extracted details (including technical skills).

What this workflow does

• Receives a resume upload through an n8n form submission trigger.
• Extracts text from the uploaded PDF (up to two pages).
• Sends the extracted resume text to an OpenAI-compatible chat model with instructions to return a JSON candidate profile (name, email, phone, and technical skills).
• Validates and auto-fixes the model output against a structured JSON schema to keep results consistent.
• Displays a second n8n form that pre-fills the candidate’s fields and skills for review and final submission.

Use cases

• SaaS hiring pipelines: streamline inbound applications by extracting key details and skills from resumes.
• Recruiting operations: reduce manual copy/paste from PDF resumes into your internal application form.
• Automation engineers: deploy a proven n8n automation workflow pattern for document-to-structured-data processing.

Technical details

• n8n form and form trigger for resume submission.
• Extract from file to read text from the uploaded PDF (configured for up to two pages).
• n8nn8n-nodes-langchainlm chat groq (Groq) and n8nn8n-nodes-langchainlm chat open ai (OpenAI-compatible) for JSON extraction.
• n8nn8n-nodes-langchainagent (LangChain agent tooling) for orchestrating the extraction step.
• JSON schema validation and auto-fix to ensure structured candidate output.

Setup (quick)

Add an OpenAI API credential (or compatible provider), publish the initial resume upload form, then review the second form fields and defaults to match what the extraction prompt returns (for example, removing fields like Location if not produced).