AI RAG Agent with OpenAI Chat

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 →

{
  "name": "ragflow-agent",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.1,
      "position": [
        200,
        0
      ],
      "id": "53305578-19c9-404e-a7b3-d70f1d6ca07f",
      "name": "When chat message received"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.input }}",
        "options": {
          "systemMessage": "You are an AI assistant with access to RAGFlow, a document-grounded retrieval-augmented generation system. Your sole purpose is to assist users by retrieving and summarizing factual, citation-supported content from the RAGFlow knowledge base using the retrieve_knowledge tool.\n\nStrict Behavior Guidelines:\n\n    No Prior Knowledge Use: You must never respond using your own knowledge or training data. All responses must be entirely based on the output of the retrieve_knowledge tool.\n\n    Citations Required: Every response must include citations or source links provided by RAGFlow. These references should be clearly associated with the information presented.\n\n    Fallback on No Result: If retrieve_knowledge returns no relevant content for a given query, respond politely and state:\n    \"Sorry, I couldn't find any information on this topic in the available documents.\"\n    Do not attempt to generate an answer independently.\n\n    Faithful Summarization Only: Do not paraphrase or interpret retrieved content beyond what is clearly supported by the source. Maintain fidelity to the retrieved data.\n\n    Tool Invocation: Always use the retrieve_knowledge tool before forming a response. Do not speculate or answer without tool output.\n\nYou are a transparent interface to trusted document-based information and should clearly reflect the limits and provenance of what you return."
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.9,
      "position": [
        152,
        180
      ],
      "id": "4e8d2aaf-52ec-4b19-9be9-f2d0b5ce742d",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.2,
      "position": [
        120,
        400
      ],
      "id": "a2fccb09-1c56-4e08-9084-773ee6f365cd",
      "name": "OpenAI Chat Model",
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "connectionType": "sse"
      },
      "type": "n8n-nodes-mcp.mcpClientTool",
      "typeVersion": 1,
      "position": [
        240,
        400
      ],
      "id": "7770f043-4a78-4456-8f33-66eb90f08558",
      "name": "MCP Client",
      "credentials": {
        "mcpClientSseApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "connectionType": "sse",
        "operation": "executeTool",
        "toolName": "retrieve_knowledge"
      },
      "type": "n8n-nodes-mcp.mcpClientTool",
      "typeVersion": 1,
      "position": [
        360,
        400
      ],
      "id": "3a3c08f3-7c79-44c8-9ecd-7f0193f36861",
      "name": "retrieve_knowledge",
      "credentials": {
        "mcpClientSseApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "inputSource": "jsonExample",
        "jsonExample": "{\n  \"input\": \"find information about climate change with proper citations\",\n  \"reason\": \"The request involves retrieving factual information with citations, which is the primary function of the RAGFlow Agent's document-grounded retrieval system.\",\n  \"selectedAgent\": \"ragflow-agent\"\n}"
      },
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1.1,
      "position": [
        -100,
        180
      ],
      "id": "fb9dfd5d-d4cb-440f-88a0-8c7a055d81dd",
      "name": "When Executed by Another Workflow"
    }
  ],
  "connections": {
    "When chat message received": {
      "main": [
        []
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "retrieve_knowledge": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "c7c45036-9bc8-4b1f-bec7-b081cbcce253",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "297gKElp4LWZs47l",
  "tags": []
}

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.

• openAiApi

About this workflow

ragflow-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.

Source: https://github.com/dujonwalker/project-nova/blob/1cfff76201b1f929687d3d0b2e93aa82f4633418/n8n-workflows/ragflow_agent.json — 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.