Vector Search with MongoDB

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": "Seoul hackathon",
  "nodes": [
    {
      "parameters": {
        "authentication": "headerAuth",
        "requestMethod": "POST",
        "url": "https://api.openai.com/v1/embeddings",
        "jsonParameters": true,
        "options": {},
        "bodyParametersJson": "={\n  \"model\":\"text-embedding-3-large\",\n\"input\": \"{{ $json.body.text }}\"\n}\n "
      },
      "name": "Convert Text to Vector",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 1,
      "position": [
        7940,
        420
      ],
      "id": "a9b22d84-83c4-44df-8165-65c8e4340b29",
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "functionCode": "return items.map(item => {\n    const { URL, Description, Title, Images, ...rest } = item.json;\n  const imageArray = Images.split(','); // Split the Images string by comma\n    return { json: { url: URL, description: Description, title: Title, image: imageArray[0] } };\n});"
      },
      "name": "Format Response",
      "type": "n8n-nodes-base.function",
      "typeVersion": 1,
      "position": [
        8300,
        420
      ],
      "id": "038d01f8-19a1-4070-812b-b0782d750490"
    },
    {
      "parameters": {
        "operation": "aggregate",
        "collection": "product_v2",
        "query": "=[{\n    \"$vectorSearch\": {\n\"index\": \"vector_index\",\n\"path\": \"embedding\",\n\"numCandidates\": 5,\n\"limit\": 5,\n\"queryVector\": [{{$json.data[0].embedding}}]\n      }\n    }\n]"
      },
      "name": "MongoDB Vector Search",
      "type": "n8n-nodes-base.mongoDb",
      "typeVersion": 1,
      "position": [
        8100,
        420
      ],
      "id": "a82f75b0-41fb-402c-8bb4-d046ceef5aa1",
      "credentials": {
        "mongoDb": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "respondWith": "allIncomingItems",
        "options": {}
      },
      "id": "3c375641-50a5-4cdd-b431-73a5a6fe8cb6",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        8500,
        420
      ]
    },
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "text-to-vector",
        "responseMode": "responseNode",
        "options": {
          "rawBody": false
        }
      },
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        7780,
        420
      ],
      "id": "44e95081-b816-43dc-88ee-8f4441dbae8e"
    }
  ],
  "connections": {
    "Convert Text to Vector": {
      "main": [
        [
          {
            "node": "MongoDB Vector Search",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "MongoDB Vector Search": {
      "main": [
        [
          {
            "node": "Format Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Response": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Webhook": {
      "main": [
        [
          {
            "node": "Convert Text to Vector",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "0b7cdfc3-ab03-40f4-b50b-453d8afa69b4",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "e8okWm6Hm4nloUOe",
  "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.

• httpHeaderAuth
• mongoDb

About this workflow

Seoul hackathon. Uses httpRequest, mongoDb. Webhook trigger; 5 nodes.

Source: https://github.com/x2day/qoupee/blob/fe58d4df9fca977e13a966a9759674149dd8b211/workflows/n8n.json — original creator credit. Request a take-down →

More Data & Sheets workflows → · Browse all categories →

Related workflows

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