What it does
A small n8n workflow that connects an open-source model from HuggingFace to a Basic LLM Chain. A chat message triggers the run and a prompt guides the answer. It uses Mistral-7B-Instruct-v0.1 by default, and you can change it to another supported model or to Ollama.
Use cases
- 01Test an open-source model before choosing one for a project
- 02Compare answers from different HuggingFace models
- 03Prototype a chat step that does not rely on a paid API
Connects
Basic LLM Chain · Hugging Face Inference Model