What it does
An n8n workflow that shows several ways to use DeepSeek models. It covers DeepSeek-R1 running locally through Ollama, the DeepSeek Chat V3 API, plain HTTP requests, and a conversational agent with a memory buffer and customizable system message.
Use cases
- 01Compare DeepSeek V3 chat with R1 reasoning on one task
- 02Run a model locally with Ollama instead of an API
- 03Build a chat agent that keeps context between messages
Connects
HTTP Request · AI Agent · Basic LLM Chain · Ollama Chat Model · OpenAI Chat Model · Simple Memory