AutomationFlowsAI & RAG › DeepSeek V3 Chat & R1 Reasoning Quick Start

DeepSeek V3 Chat & R1 Reasoning Quick Start

Original n8n title: 🐋deepseek V3 Chat & R1 Reasoning Quick Start

🐋DeepSeek V3 Chat & R1 Reasoning Quick Start. Uses chatTrigger, agent, lmChatOpenAi, memoryBufferWindow. Chat trigger; 15 nodes.

Chat trigger trigger★★★★☆ complexityAI-powered15 nodesChat TriggerAgentOpenAI ChatMemory Buffer WindowChain LlmOllama ChatHTTP Request
AI & RAG Trigger: Chat trigger Nodes: 15 Complexity: ★★★★☆ AI nodes: yes Added:

This workflow follows the Agent → Chainllm recipe pattern — see all workflows that pair these two integrations.

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "id": "IyhH1KHtXidKNSIA",
  "name": "\ud83d\udc0bDeepSeek V3 Chat & R1 Reasoning Quick Start",
  "tags": [],
  "nodes": [
    {
      "id": "54c59cae-fbd0-4f0d-b633-6304e6c66d89",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -840,
        -740
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "ef85680e-569f-4e74-a1b4-aae9923a0dcb",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "onError": "continueErrorOutput",
      "position": [
        -320,
        40
      ],
      "parameters": {
        "agent": "conversationalAgent",
        "options": {
          "systemMessage": "You are a helpful assistant."
        }
      },
      "retryOnFail": true,
      "typeVersion": 1.7,
      "alwaysOutputData": true
    },
    {
      "id": "07a8c74c-768e-4b38-854f-251f2fe5b7bf",
      "name": "DeepSeek",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -360,
        220
      ],
      "parameters": {
        "model": "=deepseek-reasoner",
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "a6d58a8c-2d16-4c91-adde-acac98868150",
      "name": "Window Buffer Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -220,
        220
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "401a5932-9f3e-4b17-a531-3a19a6a7788a",
      "name": "Basic LLM Chain2",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        -320,
        -800
      ],
      "parameters": {
        "messages": {
          "messageValues": [
            {
              "message": "You are a helpful assistant."
            }
          ]
        }
      },
      "typeVersion": 1.5
    },
    {
      "id": "215dda87-faf7-4206-bbc3-b6a6b1eb98de",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -440,
        -460
      ],
      "parameters": {
        "color": 5,
        "width": 420,
        "height": 340,
        "content": "## DeepSeek using HTTP Request\n### DeepSeek Reasoner R1\nhttps://api-docs.deepseek.com/\nRaw Body"
      },
      "typeVersion": 1
    },
    {
      "id": "6457c0f7-ad02-4ad3-a4a0-9a7a6e8f0f7f",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -440,
        -900
      ],
      "parameters": {
        "color": 4,
        "width": 580,
        "height": 400,
        "content": "## DeepSeek with Ollama Local Model"
      },
      "typeVersion": 1
    },
    {
      "id": "2ac8b41f-b27d-4074-abcc-430a8f5928e8",
      "name": "Ollama DeepSeek",
      "type": "@n8n/n8n-nodes-langchain.lmChatOllama",
      "position": [
        -320,
        -640
      ],
      "parameters": {
        "model": "deepseek-r1:14b",
        "options": {
          "format": "default",
          "numCtx": 16384,
          "temperature": 0.6
        }
      },
      "credentials": {
        "ollamaApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "37a94fc0-eff3-4226-8633-fb170e5dcff2",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -440,
        -80
      ],
      "parameters": {
        "color": 3,
        "width": 600,
        "height": 460,
        "content": "## DeepSeek Conversational Agent w/Memory\n"
      },
      "typeVersion": 1
    },
    {
      "id": "52b484bb-1693-4188-ba55-643c40f10dfc",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        20,
        -460
      ],
      "parameters": {
        "color": 6,
        "width": 420,
        "height": 340,
        "content": "## DeepSeek using HTTP Request\n### DeepSeek Chat V3\nhttps://api-docs.deepseek.com/\nJSON Body"
      },
      "typeVersion": 1
    },
    {
      "id": "ec46acef-60f6-4d34-b636-3654125f5897",
      "name": "DeepSeek JSON Body",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        160,
        -320
      ],
      "parameters": {
        "url": "https://api.deepseek.com/chat/completions",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n \"model\": \"deepseek-chat\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"{{ $json.chatInput }}\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ],\n \"stream\": false\n}",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "e5295120-57f9-4e02-8b73-f00e4d6baa48",
      "name": "DeepSeek Raw Body",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -300,
        -320
      ],
      "parameters": {
        "url": "https://api.deepseek.com/chat/completions",
        "body": "={\n \"model\": \"deepseek-reasoner\",\n \"messages\": [\n {\"role\": \"user\", \"content\": \"{{ $json.chatInput.trim() }}\"}\n ],\n \"stream\": false\n }",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "raw",
        "authentication": "genericCredentialType",
        "rawContentType": "application/json",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "571dc713-ce54-4330-8bdd-94e057ecd223",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1060,
        -460
      ],
      "parameters": {
        "color": 7,
        "width": 580,
        "height": 840,
        "content": "# Your First DeepSeek API Call\n\nThe DeepSeek API uses an API format compatible with OpenAI. By modifying the configuration, you can use the OpenAI SDK or softwares compatible with the OpenAI API to access the DeepSeek API.\n\nhttps://api-docs.deepseek.com/\n\n## Configuration Parameters\n\n| Parameter | Value |\n|-----------|--------|\n| base_url | https://api.deepseek.com |\n| api_key | https://platform.deepseek.com/api_keys |\n\n\n\n## Important Notes\n\n- To be compatible with OpenAI, you can also use `https://api.deepseek.com/v1` as the base_url. Note that the v1 here has NO relationship with the model's version.\n\n- The deepseek-chat model has been upgraded to DeepSeek-V3. The API remains unchanged. You can invoke DeepSeek-V3 by specifying `model='deepseek-chat'`.\n\n- deepseek-reasoner is the latest reasoning model, DeepSeek-R1, released by DeepSeek. You can invoke DeepSeek-R1 by specifying `model='deepseek-reasoner'`."
      },
      "typeVersion": 1
    },
    {
      "id": "f0ac3f32-218e-4488-b67f-7b7f7e8be130",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1060,
        -900
      ],
      "parameters": {
        "color": 2,
        "width": 580,
        "height": 400,
        "content": "## Four Examples for Connecting to DeepSeek\nhttps://api-docs.deepseek.com/\nhttps://platform.deepseek.com/api_keys"
      },
      "typeVersion": 1
    },
    {
      "id": "91642d68-ab5d-4f61-abaf-8cb7cb991c29",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -180,
        -640
      ],
      "parameters": {
        "color": 7,
        "width": 300,
        "height": 120,
        "content": "### Ollama Local\nhttps://ollama.com/\nhttps://ollama.com/library/deepseek-r1"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "e354040e-7898-4ff9-91a2-b6d36030dac8",
  "connections": {
    "AI Agent": {
      "main": [
        []
      ]
    },
    "DeepSeek": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Ollama DeepSeek": {
      "ai_languageModel": [
        [
          {
            "node": "Basic LLM Chain2",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Window Buffer Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Basic LLM Chain2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

How this works

This workflow delivers rapid, intelligent responses to user queries by harnessing DeepSeek V3's advanced chat and reasoning capabilities, saving you hours on complex problem-solving or customer interactions. It's ideal for developers, AI enthusiasts, or businesses needing a straightforward AI assistant that remembers conversation context for more natural exchanges. The core step involves the AI agent routing inputs through the DeepSeek model via OpenAI-compatible integration, enhanced by a window buffer memory to maintain dialogue flow across sessions.

Use this quick-start setup when prototyping conversational AI bots or testing DeepSeek's reasoning prowess in low-stakes environments, such as internal tools or personal projects. Avoid it for production-scale applications requiring robust error handling or high-volume traffic, where custom scaling would be necessary. Common variations include swapping the OpenAI node for Ollama to run DeepSeek locally, or adding chain LLM nodes for multi-step reasoning tasks like data analysis.

About this workflow

🐋DeepSeek V3 Chat & R1 Reasoning Quick Start. Uses chatTrigger, agent, lmChatOpenAi, memoryBufferWindow. Chat trigger; 15 nodes.

Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

This Chatbot automates the process of discovering job openings and generating tailored job application emails.

Chat Trigger, OpenAI Chat, Mcp Client Tool +12
AI & RAG

Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.

Chat Trigger, OpenAI Chat, Mcp Client Tool +12
AI & RAG

🐋DeepSeek V3 Chat & R1 Reasoning Quick Start. Uses chatTrigger, agent, lmChatOpenAi, memoryBufferWindow. Chat trigger; 15 nodes.

Chat Trigger, Agent, OpenAI Chat +4
AI & RAG

🐋DeepSeek V3 Chat & R1 Reasoning Quick Start. Uses chatTrigger, agent, lmChatOpenAi, memoryBufferWindow. Chat trigger; 15 nodes.

Chat Trigger, Agent, OpenAI Chat +4
AI & RAG

agente_extração_leads_empresariais/modelo. Uses lmChatOpenAi, httpRequestTool, memoryBufferWindow, chatTrigger. Chat trigger; 15 nodes.

OpenAI Chat, HTTP Request Tool, Memory Buffer Window +5