This n8n workflow creates an intelligent AI chatbot that answers website-related questions using content extracted from a specified URL. The workflow guides users through submitting a website URL, scrapes relevant content, processes and splits the data into manageable chunks, and stores the embeddings in a Supabase vector database. When users ask questions, the chatbot retrieves relevant information from the stored embeddings and generates accurate, document-based responses using OpenAI’s GPT-4 model. Practical use cases include building a knowledge base chatbot for customer support, website FAQs, or content assistance that is always grounded in actual website data.

Node Count

11 – 20 Nodes

Nodes Used

@n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsCohere, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.memoryPostgresChat, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStoreSupabase, convertToFile, formTrigger, htmlExtract, httpRequest, stickyNote