{
  "id": "2Eba0OHGtOmoTWOU",
  "meta": {
    "instanceId": "workflow-6ab0a70c",
    "versionId": "1.0.0",
    "createdAt": "2025-09-29T07:07:44.610608",
    "updatedAt": "2025-09-29T07:07:44.610631",
    "owner": "n8n-user",
    "license": "MIT",
    "category": "automation",
    "status": "active",
    "priority": "high",
    "environment": "production"
  },
  "name": "RAG AI Agent with Milvus and Cohere",
  "tags": [
    "automation",
    "n8n",
    "production-ready",
    "excellent",
    "optimized"
  ],
  "nodes": [
    {
      "id": "361065cc-edbf-47da-8da7-c59b564db6f3",
      "name": "Default Data Loader",
      "type": "n8n-nodes-base.noOp",
      "position": [
        0,
        320
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1,
      "notes": "This documentDefaultDataLoader node performs automated tasks as part of the workflow."
    },
    {
      "id": "a01b9512-ced1-4e28-a2aa-88077ab79d9a",
      "name": "Embeddings Cohere",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -140,
        320
      ],
      "parameters": {
        "modelName": "embed-multilingual-v3.0"
      },
      "credentials": {
        "cohereApi": {
          "id": "8gcYMleu1b8Hm03D",
          "name": "CohereApi account"
        }
      },
      "typeVersion": 1,
      "notes": "This embeddingsCohere node performs automated tasks as part of the workflow."
    },
    {
      "id": "1da6ea4b-de88-44d3-a215-78c55b5592a2",
      "name": "When chat message received",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -800,
        520
      ],
      "webhookId": "a4257301-3fb9-4b9d-a965-1fa66f314696",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1,
      "notes": "This chatTrigger node performs automated tasks as part of the workflow."
    },
    {
      "id": "23004477-3f6d-4909-a626-0eba0557a5bd",
      "name": "Watch New Files",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -800,
        100
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "15gjDQZiHZuBeVscnK8Ic_kIWt3mOaVfs",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "RAG template"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "r1DVmNxwkIL8JO17",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1,
      "notes": "This googleDriveTrigger node performs automated tasks as part of the workflow."
    },
    {
      "id": "001fbdbe-dfcb-4552-bf09-de416b253389",
      "name": "Download New",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -580,
        100
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "r1DVmNxwkIL8JO17",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3,
      "notes": "This googleDrive node performs automated tasks as part of the workflow."
    },
    {
      "id": "c1116cba-beb9-4d28-843d-c5c21c0643de",
      "name": "Insert into Milvus",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -124,
        100
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "clearCollection": false
        },
        "milvusCollection": {
          "__rl": true,
          "mode": "list",
          "value": "collectionName",
          "cachedResultName": "collectionName"
        }
      },
      "credentials": {
        "milvusApi": {
          "id": "Gpsxqr2l9Qxu48h0",
          "name": "Milvus account"
        }
      },
      "typeVersion": 1.1,
      "notes": "This vectorStoreMilvus node performs automated tasks as part of the workflow."
    },
    {
      "id": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
      "name": "RAG Agent",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -540,
        520
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.8,
      "notes": "This agent node performs automated tasks as part of the workflow."
    },
    {
      "id": "a103506e-9019-41f2-9b0d-9b831434c9e9",
      "name": "Retrieve from Milvus",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -340,
        740
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "topK": 10,
        "toolName": "vector_store",
        "toolDescription": "You are an AI agent that responds based on information received from a vector database.",
        "milvusCollection": {
          "__rl": true,
          "mode": "list",
          "value": "collectionName",
          "cachedResultName": "collectionName"
        }
      },
      "credentials": {
        "milvusApi": {
          "id": "Gpsxqr2l9Qxu48h0",
          "name": "Milvus account"
        }
      },
      "typeVersion": 1.1,
      "notes": "This vectorStoreMilvus node performs automated tasks as part of the workflow."
    },
    {
      "id": "74ccdff1-b976-4e1c-a2c4-237ffff19e34",
      "name": "OpenAI 4o",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -580,
        740
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o",
          "cachedResultName": "gpt-4o"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "vupAk5StuhOafQcb",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2,
      "notes": "This lmChatOpenAi node performs automated tasks as part of the workflow."
    },
    {
      "id": "36e35eaf-f723-4eeb-9658-143d5bc390a0",
      "name": "Memory",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -460,
        740
      ],
      "parameters": {},
      "typeVersion": 1.3,
      "notes": "This memoryBufferWindow node performs automated tasks as part of the workflow."
    },
    {
      "id": "ec7b6b92-065c-455c-a3f0-17586d9e48d7",
      "name": "Cohere embeddings",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -220,
        900
      ],
      "parameters": {
        "modelName": "embed-multilingual-v3.0"
      },
      "credentials": {
        "cohereApi": {
          "id": "8gcYMleu1b8Hm03D",
          "name": "CohereApi account"
        }
      },
      "typeVersion": 1,
      "notes": "This embeddingsCohere node performs automated tasks as part of the workflow."
    },
    {
      "id": "3c3a8900-0b98-4479-8602-16b21e011ba1",
      "name": "Set Chunks",
      "type": "n8n-nodes-base.noOp",
      "position": [
        80,
        480
      ],
      "parameters": {
        "options": {},
        "chunkSize": 700,
        "chunkOverlap": 60
      },
      "typeVersion": 1,
      "notes": "This textSplitterRecursiveCharacterTextSplitter node performs automated tasks as part of the workflow."
    },
    {
      "id": "3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07",
      "name": "Extract from File",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        -360,
        100
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1,
      "notes": "This extractFromFile node performs automated tasks as part of the workflow."
    },
    {
      "id": "e0c9d4d7-5e3e-4e47-bb1f-dbdca360b20a",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1440,
        120
      ],
      "parameters": {
        "color": 2,
        "width": 540,
        "height": 600,
        "content": "## Why Milvus\nBased on comparisons and user feedback, **Milvus is often considered a more performant and scalable vector database solution compared to Supabase**, particularly for demanding use cases involving large datasets, high-volume vector search operations, and multilingual support.\n\n\n### Requirements\n- Create an account on [Zilliz]({{ $env.WEBHOOK_URL }} to generate the Milvus cluster. \n- There is no need to create docker containers or your own instance, Zilliz provides the cloud infraestructure to build it easily\n- Get your credentials ready from Drive, Milvus (Zilliz), and [Cohere]({{ $env.WEBHOOK_URL }}\n\n### Usage\nEvery time a new pdf is added into the Drive folder, it will be inserted into the Milvus Vector Store, allowing for the interaction with the RAG agent in seconds.\n\n## Calculate your company's RAG costs\n\nWant to run Milvus on your own server on n8n? Zilliz provides a great [cost calculator]({{ $env.WEBHOOK_URL }}\n\n### Get in touch with us\nWant to implement a RAG AI agent for your company? [Shoot us a message]({{ $env.WEBHOOK_URL }}\n"
      },
      "typeVersion": 1,
      "notes": "This stickyNote node performs automated tasks as part of the workflow."
    },
    {
      "id": "error-43cf3364",
      "name": "Error Handler",
      "type": "n8n-nodes-base.stopAndError",
      "typeVersion": 1,
      "position": [
        1000,
        400
      ],
      "parameters": {
        "message": "Workflow execution error",
        "options": {}
      }
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "executionOrder": "v1",
    "saveManualExecutions": true,
    "callerPolicy": "workflowsFromSameOwner",
    "errorWorkflow": null,
    "timezone": "UTC",
    "executionTimeout": 3600,
    "maxExecutions": 1000,
    "retryOnFail": true,
    "retryCount": 3,
    "retryDelay": 1000
  },
  "versionId": "8b5fc2b8-50f7-425c-8fc8-94ba4f76ecf3",
  "connections": {
    "23004477-3f6d-4909-a626-0eba0557a5bd": {
      "main": [
        [
          {
            "node": "error-handler-23004477-3f6d-4909-a626-0eba0557a5bd-567630fe",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "001fbdbe-dfcb-4552-bf09-de416b253389": {
      "main": [
        [
          {
            "node": "error-handler-001fbdbe-dfcb-4552-bf09-de416b253389-e0bfc747",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "74ccdff1-b976-4e1c-a2c4-237ffff19e34": {
      "main": [
        [
          {
            "node": "error-handler-74ccdff1-b976-4e1c-a2c4-237ffff19e34-c6125f81",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07": {
      "main": [
        [
          {
            "node": "error-handler-3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07-0851940f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "description": "Automated workflow: RAG AI Agent with Milvus and Cohere. This workflow integrates 13 different services: stickyNote, googleDriveTrigger, textSplitterRecursiveCharacterTextSplitter, agent, googleDrive. It contains 18 nodes and follows best practices for error handling and security.",
  "notes": "Excellent quality workflow: RAG AI Agent with Milvus and Cohere. This workflow has been optimized for production use with comprehensive error handling, security, and documentation."
}