From crawling and embedding web content, deploying your model with Docker, to talking to the content of a website in n8n. Build AI workflows that are not just powerful – but fully yours and open-source.
From crawling and embedding web content, deploying your model with Docker, to talking to the content of a website in n8n. Build AI workflows that are not just powerful – but fully yours and open-source.
With tools like Ollama and DigitalOcean, deploying your own LLM server is fast, affordable, and production-ready. In this guide, we’ll show you how to set it up in minutes – no API keys, no lock-in.
A simple setup to perform a breadth-first crawl of a given web-domain, storing per page (meta)data such as internal and external links etc and semantically split chunks with embeddings for consumption of a RAG applications.
Build internal AI tools, chatbots, or content analysis with up-to-date, searchable knowledge. Use the open-source stack of Crawl4AI, Supabase, and n8n for building Retrieval-Augmented Generation workflows.
