{"product_id":"apify-pdf-office-url-to-rag-ready-markdown-chunks-in-n8n","title":"Apify PDF \u0026 Office URL to RAG-Ready Markdown Chunks in n8n","description":"\u003ch3\u003eTurn PDF and Office URLs into RAG-ready Markdown chunks—inside n8n\u003c\/h3\u003e\n\u003cp\u003eThis n8n automation workflow takes \u003cstrong\u003ePDF and Office document URLs\u003c\/strong\u003e, converts them to \u003cstrong\u003eMarkdown\u003c\/strong\u003e with the \u003cstrong\u003eApify Document to Markdown Actor\u003c\/strong\u003e, and outputs \u003cstrong\u003eone n8n item per chunk\u003c\/strong\u003e with citation-friendly metadata for downstream RAG indexing.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRuns manually\u003c\/strong\u003e (Manual Trigger) so you can control when documents are processed.\u003c\/li\u003e\n  \u003cli\u003eLets you set your \u003cstrong\u003efile URLs\u003c\/strong\u003e plus \u003cstrong\u003echunk size\u003c\/strong\u003e and \u003cstrong\u003echunk overlap\u003c\/strong\u003e parameters.\u003c\/li\u003e\n  \u003cli\u003eSends those URLs and chunking settings to the \u003cstrong\u003eApify Document to Markdown Actor\u003c\/strong\u003e using the \u003cstrong\u003eApify API\u003c\/strong\u003e, generating Markdown output and \u003cstrong\u003eextracted tables\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eSplits the actor results into \u003cstrong\u003eone output item per chunk\u003c\/strong\u003e, preserving chunk text along with metadata such as:\n    \u003cul\u003e\n      \u003cli\u003e\u003cstrong\u003esource URL\u003c\/strong\u003e\u003c\/li\u003e\n      \u003cli\u003e\u003cstrong\u003etitle\u003c\/strong\u003e\u003c\/li\u003e\n      \u003cli\u003e\u003cstrong\u003epage range\u003c\/strong\u003e\u003c\/li\u003e\n      \u003cli\u003e\n\u003cstrong\u003enearest heading\u003c\/strong\u003e (for citation-friendly context)\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRAG ingestion for document collections\u003c\/strong\u003e: index PDFs and Office files by turning them into consistent, chunked Markdown.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eSupport knowledge bases\u003c\/strong\u003e: process policy, terms, or manuals stored as URLs to improve retrieval quality.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eSaaS ops and internal tooling\u003c\/strong\u003e: repeatedly re-chunk content with different chunk size\/overlap to optimize search and citations.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eApify integration\u003c\/strong\u003e: uses an Apify API token with an \u003cstrong\u003eHTTP Header Auth\u003c\/strong\u003e credential formatted as \u003ccode\u003eAuthorization: Bearer \u0026lt;YOUR_APIFY_TOKEN\u0026gt;\u003c\/code\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eNodes \/ building blocks\u003c\/strong\u003e: \u003cem\u003eset\u003c\/em\u003e, \u003cem\u003ecode\u003c\/em\u003e, \u003cem\u003esticky note\u003c\/em\u003e, \u003cem\u003eHTTP request\u003c\/em\u003e, \u003cem\u003emanual trigger\u003c\/em\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eConfiguration\u003c\/strong\u003e: replace the sample \u003ccode\u003efileUrls\u003c\/code\u003e with your public or pre-signed document URLs and tune \u003ccode\u003echunkSize\u003c\/code\u003e \/ \u003ccode\u003echunkOverlap\u003c\/code\u003e.\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":46206054138035,"sku":"N8N-20774","price":36.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/4XfUxvZyaXTEAfdtyBiRz_zLYcuhOE.png?v=1791796247","url":"https:\/\/buyflowscripts.com\/products\/apify-pdf-office-url-to-rag-ready-markdown-chunks-in-n8n","provider":"N8N Commerce","version":"1.0","type":"link"}