n8n Documentation: Expert Chatbot with OpenAI RAG Pipeline

# How It Works This template is a complete, hands-on tutorial for building a **RAG (Retrieval-Augmented Generation)** pipeline. In simple terms, you'll teach an AI to become an expert on a specific topic—in this case, the official **n8n documentation**—and then build a chatbot to ask it questions. Think of it like this: instead of a general-knowledge AI, you're building an **expert librarian**. --- ## Workflow Overview The workflow is split into two main parts: ### Part 1: Indexing the Knowledge (Building the Library) This is a **one-time process** you run manually. The workflow will: - Automatically scrape all pages of the **n8n documentation**. - Break them down into small, digestible chunks. - Use an AI model to create a numerical representation (an **embedding**) for each chunk. - Store these embeddings in **n8n's built-in Simple Vector Store**. > This is like a librarian reading every book and creating a hyper-detailed index card for every paragraph. > **Important:** This in-memory knowledge base is **temporary**. It will be erased if you restart your n8n instance. You'll need to run the indexing process again in that case. --- ### Part 2: The AI Agent (The Expert Librarian) This is the **chat interface**. When you ask a question: 1. The AI agent **doesn't guess** the answer. 2. It searches the knowledge base to find the most relevant "index cards" (chunks). 3. It feeds those chunks to a language model (**Gemini**) with strict instructions: > "Answer the user's question using ONLY this information." This ensures answers are accurate, factual, and grounded in your documents. --- ## Setup Steps > **Total setup time**: ~2 minutes > **Indexing time**: ~15-20 minutes This template uses **n8n's built-in tools**, so no external database is needed. ### 1. Configure OpenAI Credentials - You'll need an **OpenAI API key** (for GPT models). - In your n8n workflow: - Go to any of the three OpenAI nodes (e.g., `OpenAI Chat Model`). - Click the **Credential** dropdown → `+ Create New Credential`. - Enter your OpenAI API key and **save**. ### 2. Apply Credentials to All Nodes - Your new credential is now saved. - Go to the other two OpenAI nodes (e.g., `OpenAI Embeddings`) and select the newly created credential from the dropdown. ### 3. Build the Knowledge Base - Find the **Start Indexing** manual trigger node (top-left of the workflow). - Click the **Execute Workflow** button to start indexing. > **Be patient**: This takes 15-20 minutes to scrape and process the full documentation. > You only need to do this **once per n8n session**. ### 4. Chat With Your Expert Agent - After indexing completes, **activate** the entire workflow (toggle at the top). - Open the **RAG Chatbot** chat trigger node (bottom-left). - Copy its **Public URL**. - Open it in a new tab and ask questions about n8n! Example questions: - How does the IF node work? - What is a sub-workflow? --- ## Credits All credits go to **Lucas Peyrin** — [lucaspeyrin on n8n.io](https://n8n.io/creators/lucaspeyrin/)