What it does
A hands-on n8n tutorial for building a RAG pipeline. One part scrapes the n8n documentation, splits it into chunks and stores embeddings in a vector store. The other part is a chat agent that finds the relevant chunks and has Gemini answer from them.
Use cases
- 01Learn how a RAG pipeline is put together
- 02Build a chatbot over product documentation
- 03Adapt the pipeline to your own help center
Connects
HTTP Request · HTML · AI Agent · Simple Memory · Recursive Character Text Splitter · Simple Vector Store · Default Data Loader · Embeddings Google Gemini · Google Gemini Chat Model