Apple RAG ChatBot

★ 6.9 · n8n · complex · 19 nodes

Apple RAG ChatBot is an n8n automation template that builds a retrieval-augmented generation (RAG) chatbot powered by locally running language models via Ollama. Reach for it when you need an internal knowledge assistant that answers questions based on company documents without sending data to the cloud, or when you want to connect a chat interface to files stored in Google Drive and run inference entirely on your own hardware. Trigger: chat. Integrations: Google Drive (document source), Ollama, Lm Ollama (local LLM inference), Time Saved. Deploy by importing the workflow into an existing n8n instance; requires a running Ollama instance with a model already loaded. The direction here is document-grounded answer generation, not web crawling or RSS processing. Works well for teams prioritising data privacy and avoiding third-party API costs. Not a fit if you lack the hardware to run local LLMs or need multimodal input support.