RAG Pipeline with Qdrant & Ollama

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": "RAG Pipeline",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "rag",
        "responseMode": "onReceived",
        "options": {}
      },
      "id": "webhook-rag",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        250,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://api.openai.com/v1/embeddings",
        "authentication": "genericCredentialType",
        "genericCredentialType": "httpHeaderAuth",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer {{ $env.OPENAI_API_KEY }}"
            }
          ]
        },
        "bodyParametersJson": "={\n  \"model\": \"text-embedding-3-small\",\n  \"input\": \"{{ $node[\\\"Webhook\\\"].json.text }}\"\n}",
        "options": {}
      },
      "id": "openai-embedding",
      "name": "Generate Embedding",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        450,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "={{ $env.SUPABASE_DB_URL }}/rest/v1/embeddings",
        "authentication": "genericCredentialType",
        "genericCredentialType": "httpHeaderAuth",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer {{ $env.SUPABASE_SERVICE_ROLE_KEY }}"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "bodyParametersJson": "={\n  \"document_id\": \"{{ $node[\\\"Webhook\\\"].json.document_id }}\",\n  \"text_chunk\": \"{{ $node[\\\"Webhook\\\"].json.text }}\",\n  \"embedding_vector\": {{ $node[\\\"Generate Embedding\\\"].json.data[0].embedding }},\n  \"metadata\": { \"source\": \"{{ $node[\\\"Webhook\\\"].json.source }}\" }\n}",
        "options": {}
      },
      "id": "supabase-embedding",
      "name": "Save Embedding",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        650,
        300
      ]
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Generate Embedding",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate Embedding": {
      "main": [
        [
          {
            "node": "Save Embedding",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

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.

• ollamaApi
• qdrantApi

About this workflow

RAG Pipeline. Uses formTrigger, vectorStoreQdrant, embeddingsOllama, documentDefaultDataLoader. Event-driven trigger; 13 nodes.

Source: https://github.com/Codimart/n8n-ai-agents-starter-kit/blob/main/workflows/ai-agent-rag.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.