Chat with Local LLMs via Ollama in n8n

This n8n workflow provides a simple chat interface for talking directly to locally hosted large language models running through Ollama, without sending any data to external cloud AI providers. It's built for privacy-conscious teams, developers testing open-source models, or anyone who wants to experiment with local LLMs without API costs or internet dependency. The setup connects n8n's chat trigger straight to Ollama, making it easy to swap between different local models like Llama or Mistral variants. The result is a fast, private, and cost-free way to chat with self-hosted AI models directly inside your automation platform.

Category: AI Chatbots