TopAI Web-to-Markdown API for n8n HTTP Request Workflows

Turn any webpage into clean, RAG-ready Markdown—inside n8n

This n8n workflow converts a specified website URL into cleaned Markdown by calling TopAI Gateway’s Web-to-Markdown API over HTTP, automatically removing common HTML noise (like ads, cookie popups, and scripts) while preserving useful structure for downstream retrieval and ingestion.

What this workflow does

• Triggers on demand or on schedule: start manually, via a webhook, or using a recurring scheduled trigger in n8n.
• Sends a fast POST request: uses an HTTP Request node to call TopAI Gateway’s Anycast Edge Web-to-Markdown API, passing your target webpage URL and cleanup configuration.
• Produces cleaned Markdown: strips HTML boilerplate, promotional ads, cookie popups, and scripts while keeping document metadata and markdown table compatibility for RAG workflows.

Use cases

• Build RAG document sources by converting product docs, blog posts, or knowledge base pages into structured Markdown.
• Reduce retrieval noise for SaaS operators by removing ads and other non-content elements before indexing.
• Automate content ingestion when you need repeatable conversions across multiple URLs (manual, webhook-driven, or recurring).

Technical details

• TopAI Gateway API Key (free tier available): create an account at https://topaigateway.com and generate your key.
• Authentication: set the HTTP Request node Authorization header to Bearer <YOUR_TOPAI_API_KEY>.
• Request body: provide the target website url and adjust cleanup options such as:
  • strip_ads_and_scripts (set to true to eliminate noise)
  • preserve_tables (set to true to keep HTML tables formatted as Markdown tables)
• n8n nodes used: Manual Trigger / webhook / scheduled trigger, HTTP Request, and a Sticky Note for guidance.

Perfect for n8n users and automation engineers who want a reliable Web-to-Markdown step powered by TopAI Gateway, ready for RAG ingestion.