RAG-KI-Agent mit Milvus und Cohere erstellen

Fortgeschritten

Dies ist ein Support, AI, IT Ops-Bereich Automatisierungsworkflow mit 14 Nodes. Hauptsächlich werden GoogleDrive, Agent, ExtractFromFile, GoogleDriveTrigger, ChatTrigger und andere Nodes verwendet, kombiniert mit KI-Technologie für intelligente Automatisierung. Ein Dokumenten-Frage-Antwort-RAG-System für Google Drive mit Milvus, Cohere und OpenAI erstellen

Voraussetzungen
  • Google Drive API-Anmeldedaten
  • OpenAI API Key
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
  "id": "2Eba0OHGtOmoTWOU",
  "meta": {
    "instanceId": "9219ebc7795bea866f70aa3d977d54417fdf06c41944be95e20cfb60f992db19",
    "templateCredsSetupCompleted": true
  },
  "name": "RAG AI Agent with Milvus and Cohere",
  "tags": [
    {
      "id": "yj7cF3GCsZiargFT",
      "name": "rag",
      "createdAt": "2025-05-03T17:14:30.099Z",
      "updatedAt": "2025-05-03T17:14:30.099Z"
    }
  ],
  "nodes": [
    {
      "id": "361065cc-edbf-47da-8da7-c59b564db6f3",
      "name": "Standard-Datenlader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        0,
        320
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "a01b9512-ced1-4e28-a2aa-88077ab79d9a",
      "name": "Embeddings Cohere",
      "type": "@n8n/n8n-nodes-langchain.embeddingsCohere",
      "position": [
        -140,
        320
      ],
      "parameters": {
        "modelName": "embed-multilingual-v3.0"
      },
      "credentials": {
        "cohereApi": {
          "id": "8gcYMleu1b8Hm03D",
          "name": "CohereApi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "1da6ea4b-de88-44d3-a215-78c55b5592a2",
      "name": "Bei Chat-Nachrichtenempfang",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -800,
        520
      ],
      "webhookId": "a4257301-3fb9-4b9d-a965-1fa66f314696",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "23004477-3f6d-4909-a626-0eba0557a5bd",
      "name": "Neue Dateien überwachen",
      "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": "https://drive.google.com/drive/folders/15gjDQZiHZuBeVscnK8Ic_kIWt3mOaVfs",
          "cachedResultName": "RAG template"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "r1DVmNxwkIL8JO17",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "001fbdbe-dfcb-4552-bf09-de416b253389",
      "name": "Neue herunterladen",
      "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
    },
    {
      "id": "c1116cba-beb9-4d28-843d-c5c21c0643de",
      "name": "In Milvus einfügen",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
      "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
    },
    {
      "id": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
      "name": "RAG-Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -540,
        520
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.8
    },
    {
      "id": "a103506e-9019-41f2-9b0d-9b831434c9e9",
      "name": "Aus Milvus abrufen",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
      "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
    },
    {
      "id": "74ccdff1-b976-4e1c-a2c4-237ffff19e34",
      "name": "OpenAI 4o",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "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
    },
    {
      "id": "36e35eaf-f723-4eeb-9658-143d5bc390a0",
      "name": "Speicher",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -460,
        740
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "ec7b6b92-065c-455c-a3f0-17586d9e48d7",
      "name": "Cohere-Embeddings",
      "type": "@n8n/n8n-nodes-langchain.embeddingsCohere",
      "position": [
        -220,
        900
      ],
      "parameters": {
        "modelName": "embed-multilingual-v3.0"
      },
      "credentials": {
        "cohereApi": {
          "id": "8gcYMleu1b8Hm03D",
          "name": "CohereApi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "3c3a8900-0b98-4479-8602-16b21e011ba1",
      "name": "Chunks setzen",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        80,
        480
      ],
      "parameters": {
        "options": {},
        "chunkSize": 700,
        "chunkOverlap": 60
      },
      "typeVersion": 1
    },
    {
      "id": "3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07",
      "name": "Aus Datei extrahieren",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        -360,
        100
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "e0c9d4d7-5e3e-4e47-bb1f-dbdca360b20a",
      "name": "Haftnotiz",
      "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](https://zilliz.com/) 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](https://cohere.com)\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](https://zilliz.com/rag-cost-calculator/)\n\n### Get in touch with us\nWant to implement a RAG AI agent for your company? [Shoot us a message](https://1node.ai)\n"
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "8b5fc2b8-50f7-425c-8fc8-94ba4f76ecf3",
  "connections": {
    "36e35eaf-f723-4eeb-9658-143d5bc390a0": {
      "ai_memory": [
        [
          {
            "node": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "74ccdff1-b976-4e1c-a2c4-237ffff19e34": {
      "ai_languageModel": [
        [
          {
            "node": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "3c3a8900-0b98-4479-8602-16b21e011ba1": {
      "ai_textSplitter": [
        [
          {
            "node": "361065cc-edbf-47da-8da7-c59b564db6f3",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "001fbdbe-dfcb-4552-bf09-de416b253389": {
      "main": [
        [
          {
            "node": "3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "23004477-3f6d-4909-a626-0eba0557a5bd": {
      "main": [
        [
          {
            "node": "001fbdbe-dfcb-4552-bf09-de416b253389",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "ec7b6b92-065c-455c-a3f0-17586d9e48d7": {
      "ai_embedding": [
        [
          {
            "node": "a103506e-9019-41f2-9b0d-9b831434c9e9",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "a01b9512-ced1-4e28-a2aa-88077ab79d9a": {
      "ai_embedding": [
        [
          {
            "node": "c1116cba-beb9-4d28-843d-c5c21c0643de",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "3a43bf1a-7e22-4b5e-bbb1-6bb2c1798c07": {
      "main": [
        [
          {
            "node": "c1116cba-beb9-4d28-843d-c5c21c0643de",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "361065cc-edbf-47da-8da7-c59b564db6f3": {
      "ai_document": [
        [
          {
            "node": "c1116cba-beb9-4d28-843d-c5c21c0643de",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "a103506e-9019-41f2-9b0d-9b831434c9e9": {
      "ai_tool": [
        [
          {
            "node": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "1da6ea4b-de88-44d3-a215-78c55b5592a2": {
      "main": [
        [
          {
            "node": "2dbc7139-46f6-41d8-8c13-9fafad5aec55",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Häufig gestellte Fragen

Wie verwende ich diesen Workflow?

Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.

Für welche Szenarien ist dieser Workflow geeignet?

Fortgeschritten - Support, Künstliche Intelligenz, IT-Betrieb

Ist es kostenpflichtig?

Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.

Workflow-Informationen
Schwierigkeitsgrad
Fortgeschritten
Anzahl der Nodes14
Kategorie3
Node-Typen12
Schwierigkeitsbeschreibung

Für erfahrene Benutzer, mittelkomplexe Workflows mit 6-15 Nodes

Autor
Aitor | 1node.ai

Aitor | 1node.ai

@aitoralonso

Hi, I’m Aitor, cofounder of 1node.ai. We help businesses integrate full-scale AI solutions that save time, cut costs, and increase revenue. Guaranteed. Need help building smarter workflows? Visit 1node.ai and let's connect.

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34