An n8n workflow extracts metadata from new PDFs, finds related papers on Semantic Scholar and PubMed, builds an APA citation, logs to Sheets and creates a Notion summary.
An n8n workflow extracts metadata from new PDFs, finds related papers on Semantic Scholar and PubMed, builds an APA citation, logs to Sheets and creates a Notion summary.
A Google Drive trigger fires when a PDF lands in a folder, and the workflow downloads it. The PDF Vector community node extracts metadata, abstract, study type and findings. It then searches Semantic Scholar and PubMed using the top 3 keywords, builds an APA citation, appends a row to Google Sheets, and creates a Notion page.
Each paper takes about 20-30 seconds. The author reports about 98% metadata accuracy on digital PDFs, about 90% on study type, and about 85% on scanned papers. Niche topics may return only 3-5 related papers.
It needs self-hosted n8n. PDF Vector costs about 4-5 credits per paper, so the free 100 credits cover roughly 20-25 papers a month. Check the APA citations before using them.
Build an n8n workflow that triggers when a new PDF lands in my [Google Drive folder], extracts the title, authors, year and abstract, finds 3-5 related papers on Semantic Scholar and PubMed, and builds an APA citation. Log everything in a Google Sheet and create a Notion page with a plain-language summary and the related papers. Done when one test PDF produces a sheet row and a Notion page, which you show me.
Score every demo request against your ICP, update HubSpot and ping the right rep in Slack within a minute of the form submit.
Every new Zendesk ticket gets a category, priority and sentiment tag plus a draft reply in an internal note before an agent opens it.
Each month, find posts whose search clicks dropped, research what changed with Perplexity, and get a Claude-written refresh brief for each one.