Knowledge Ingestion

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": "Knowledge ingestion",
  "nodes": [
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "58cd871e-7c2b-45e9-a5f3-4bd1f7531b03",
              "name": "text",
              "value": "=title :  {{ $json.title }} | abstract : {{ $json.abstract }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        -160,
        656
      ],
      "id": "47fd7dda-960c-41b9-90fd-573b4deaa83a",
      "name": "[Transform] Format Title & Abstract"
    },
    {
      "parameters": {
        "textSplittingMode": "custom",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "typeVersion": 1.1,
      "position": [
        200,
        888
      ],
      "id": "608531a3-434c-4349-a2d8-4de42b0e4230",
      "name": "[Load] Convert to Documents"
    },
    {
      "parameters": {
        "chunkSize": 800,
        "chunkOverlap": 100,
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "typeVersion": 1,
      "position": [
        280,
        1096
      ],
      "id": "73ac8109-df45-4e8b-ae56-95cb2edbf82a",
      "name": "[Split] Chunk Text (800/100)"
    },
    {
      "parameters": {
        "mode": "insert",
        "qdrantCollection": {
          "__rl": true,
          "value": "my_rag",
          "mode": "list",
          "cachedResultName": "my_rag"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
      "typeVersion": 1.3,
      "position": [
        96,
        656
      ],
      "id": "b825f9b6-9e20-431e-98b3-a1d4aad745ef",
      "name": "[Store] Insert to Vector DB",
      "credentials": {
        "qdrantApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1.2,
      "position": [
        72,
        888
      ],
      "id": "299aa97f-34ce-4b81-a252-0df6b28c3309",
      "name": "[Embed] Generate Vectors",
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "pollTimes": {
          "item": [
            {
              "mode": "everyHour"
            }
          ]
        },
        "documentId": "={{ $env.GOOGLE_SHEETS_ID }}",
        "sheetName": "={{ $env.GOOGLE_SHEETS_SHEET_NAME || \"Sheet1\" }}",
        "event": "rowAdded",
        "options": {}
      },
      "type": "n8n-nodes-base.googleSheetsTrigger",
      "typeVersion": 1,
      "position": [
        -384,
        656
      ],
      "id": "50ed2095-a3c4-48af-8bc2-da0d25f29e81",
      "name": "[Trigger] Watch New Paper",
      "credentials": {
        "googleSheetsTriggerOAuth2Api": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "[Transform] Format Title & Abstract": {
      "main": [
        [
          {
            "node": "[Store] Insert to Vector DB",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "[Load] Convert to Documents": {
      "ai_document": [
        [
          {
            "node": "[Store] Insert to Vector DB",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "[Split] Chunk Text (800/100)": {
      "ai_textSplitter": [
        [
          {
            "node": "[Load] Convert to Documents",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "[Embed] Generate Vectors": {
      "ai_embedding": [
        [
          {
            "node": "[Store] Insert to Vector DB",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "[Trigger] Watch New Paper": {
      "main": [
        [
          {
            "node": "[Transform] Format Title & Abstract",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "meta": {
    "templateCredsSetupCompleted": false
  },
  "nodeGroups": [],
  "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.

• googleSheetsTriggerOAuth2Api
• openAiApi
• qdrantApi

About this workflow

Knowledge ingestion. Uses documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, vectorStoreQdrant, embeddingsOpenAi. Event-driven trigger; 6 nodes.

Source: https://github.com/mryusefi/rag-chatbot-qdrant/blob/main/knowledge-ingestion.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.