Vector Store — Index & Search

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": "Vector Store \u2014 Index & Search",
  "nodes": [
    {
      "parameters": {},
      "id": "trg-01",
      "name": "When clicking Execute",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        0,
        0
      ]
    },
    {
      "parameters": {
        "content": "## Vector Store \u2014 Index & Search\n\nUpserts 3 toy vectors (dim 4) with metadata, then runs a similarity search.\n\n**Before running:**\n1. Create a **Vector Store API** credential and assign it to both Vector Store nodes.\n2. Set its **Dimension = 4** (must match the toy vectors here) and a **Store Directory** (absolute path).\n\nReal embeddings are higher-dimensional (e.g. 768/1536) \u2014 see the RAG example.",
        "height": 260,
        "width": 380
      },
      "id": "note-01",
      "name": "How to use",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -40,
        -300
      ]
    },
    {
      "parameters": {
        "jsCode": "return [\n  { json: { id: 'a', vector: [1, 0, 0, 0], metadata: { title: 'Alpha' } } },\n  { json: { id: 'b', vector: [0, 1, 0, 0], metadata: { title: 'Beta' } } },\n  { json: { id: 'c', vector: [0.9, 0.1, 0, 0], metadata: { title: 'Gamma' } } }\n];"
      },
      "id": "code-01",
      "name": "Documents",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        220,
        0
      ]
    },
    {
      "parameters": {
        "operation": "set",
        "collection": "demo",
        "id": "={{ $json.id }}",
        "vector": "={{ $json.vector }}",
        "metadata": "={{ $json.metadata }}"
      },
      "id": "vs-upsert-01",
      "name": "Upsert Vectors",
      "type": "n8n-nodes-js-vector-store.vectorStore",
      "typeVersion": 1,
      "position": [
        440,
        0
      ],
      "credentials": {
        "vectorStoreApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "operation": "search",
        "collection": "demo",
        "queryVector": "[1, 0, 0, 0]",
        "limit": 3
      },
      "id": "vs-search-01",
      "name": "Search",
      "type": "n8n-nodes-js-vector-store.vectorStore",
      "typeVersion": 1,
      "position": [
        660,
        0
      ],
      "executeOnce": true,
      "credentials": {
        "vectorStoreApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "When clicking Execute": {
      "main": [
        [
          {
            "node": "Documents",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Documents": {
      "main": [
        [
          {
            "node": "Upsert Vectors",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Upsert Vectors": {
      "main": [
        [
          {
            "node": "Search",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {}
}

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.

• vectorStoreApi

About this workflow

Vector Store — Index & Search. Uses n8n-nodes-js-vector-store. Event-driven trigger; 5 nodes.

Source: https://github.com/MauricioPerera/n8n-nodes-js-vector-store/blob/c628d33a6184980ade67a4f18b84f3c9f9acef60/examples/01-index-and-search.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.