DeepSeek v3 Chat - Reasoning Quick Start

This n8n workflow provides a quick and easy way to interact with a DeepSeek v3 chat model for reasoning tasks, leveraging the power of AI agents and conversational memory. It demonstrates how to set up a basic chat interface within n8n, allowing users to send messages and receive AI-generated responses.

What it does

This workflow simplifies the process of interacting with a chat-based AI model by:

1. Listening for chat messages: It acts as a trigger, initiating the workflow whenever a new chat message is received.
2. Maintaining conversational memory: It uses a simple memory buffer to keep track of previous messages, enabling the AI to maintain context throughout a conversation.
3. Processing messages with an AI agent: An AI agent is employed to interpret the incoming message and generate a relevant response.
4. Utilizing a DeepSeek v3 chat model: The agent interacts with a DeepSeek v3 chat model (or optionally, an OpenAI or Ollama chat model) to generate the actual conversational output.
5. Making HTTP requests (optional/placeholder): Includes an HTTP Request node, which can be configured for various integrations, though it's not directly connected in the provided JSON, suggesting it might be a placeholder for future expansion or a demonstration of a common n8n node.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n instance: A running n8n instance (cloud or self-hosted).
• AI Model Access:
  • DeepSeek v3 Chat Model: Access to a DeepSeek v3 chat model. This typically involves an API key or a self-hosted instance.
  • OR OpenAI API Key: If you choose to use the OpenAI Chat Model.
  • OR Ollama instance: If you choose to use the Ollama Chat Model.
• n8n LangChain Nodes: Ensure you have the @n8n/n8n-nodes-langchain package installed on your n8n instance, as it provides the AI Agent, Basic LLM Chain, and Chat Model nodes.

Setup/Usage

1. Import the workflow:
   • Copy the provided JSON code.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the "Import from JSON" button (usually a {} icon) and paste the JSON.
   • Click "Import".
2. Configure Credentials:
   • AI Chat Model: Locate the "DeepSeek Chat Model" node (or "Ollama Chat Model" / "OpenAI Chat Model" if you switch to them). You will need to configure its credentials. This typically involves providing an API key or connection details for your chosen AI service.
   • Other nodes: If you enable or connect the "HTTP Request" node, configure its credentials or settings as needed for your specific use case.
3. Activate the Workflow: Once configured, activate the workflow by toggling the "Active" switch in the top right corner of the workflow editor.
4. Interact with the Chat Trigger: The "When chat message received" node acts as the entry point. Depending on how your n8n instance is set up for chat triggers (e.g., via a specific chat service integration like Slack, Telegram, Mattermost, or a custom webhook), you would send a message to that configured endpoint to initiate the workflow.
5. Test the Workflow: Send a chat message to the configured trigger. The workflow will process it, and the AI agent will generate a response, which will then be sent back to the chat service.