This workflow automates the process of evaluating candidate resumes by converting PDF documents into images and analyzing them with a multimodal vision-language model. Starting with a manual trigger, the workflow downloads a candidate’s resume PDF from Google Drive, then uses Stirling PDF API to convert the PDF to an image, which is resized for efficiency. The image is then processed by a multimodal Language Learning Model (LLM), such as Google’s Gemini, to assess the candidate’s qualifications without text extraction issues or manipulation risks. The analysis results are parsed and evaluated to determine whether the candidate moves to the next stage of the hiring process. This setup provides a secure, AI-powered method for resume screening, useful for avoiding “hidden prompts” and ensuring fairer, more accurate candidate evaluations.
Automated Resume Screening with AI and Image Processing
Node Count | 11 – 20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.chainLlm, @n8n/n8n-nodes-langchain.lmChatGoogleGemini, @n8n/n8n-nodes-langchain.outputParserStructured, editImage, googleDrive, httpRequest, if, manualTrigger, stickyNote |
Reviews
There are no reviews yet.