This workflow follows the OpenAI Embeddings → Textsplitterrecursivecharactertextsplitter recipe pattern — see all workflows that pair these two integrations.

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 →

Download .json

{
  "name": "ingest_documents",
  "nodes": [
    {
      "id": "Manual Trigger",
      "name": "Manual Trigger",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        -560,
        140
      ],
      "parameters": {}
    },
    {
      "id": "Load Products",
      "name": "Load Products",
      "type": "n8n-nodes-base.readBinaryFile",
      "typeVersion": 1,
      "position": [
        -320,
        140
      ],
      "parameters": {
        "filePath": "/data/products.json"
      }
    },
    {
      "id": "Split Text",
      "name": "Split Text",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "typeVersion": 1,
      "position": [
        -80,
        140
      ],
      "parameters": {
        "chunkSize": 500,
        "chunkOverlap": 50
      }
    },
    {
      "id": "Embeddings",
      "name": "Embeddings",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1,
      "position": [
        160,
        140
      ],
      "parameters": {
        "model": "text-embedding-3-small"
      }
    },
    {
      "id": "Upsert Qdrant",
      "name": "Upsert Qdrant",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
      "typeVersion": 1,
      "position": [
        420,
        140
      ],
      "parameters": {
        "operation": "insert",
        "collection": "products"
      }
    }
  ],
  "connections": {
    "Manual Trigger": {
      "main": [
        [
          {
            "node": "Load Products",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Load Products": {
      "main": [
        [
          {
            "node": "Split Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Text": {
      "main": [
        [
          {
            "node": "Embeddings",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings": {
      "main": [
        [
          {
            "node": "Upsert Qdrant",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false
}

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

ingest_documents. Uses readBinaryFile, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi, vectorStoreQdrant. Event-driven trigger; 5 nodes.

Source: https://github.com/ogu83/n8n-ai-agent-lab/blob/main/ep3-rag-pipeline/workflows/ingest_documents.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.

AI & RAG

Agent Ia Projet Client

Agent IA Projet Client. Uses executeWorkflowTrigger, lmChatOpenAi, toolWorkflow, vectorStoreQdrant. Event-driven trigger; 79 nodes.

Execute Workflow Trigger, OpenAI Chat, Tool Workflow +16

AI & RAG

Build a Wordpress RAG Chatbot with Openai, Qdrant or Mongodb

Build a powerful, customizable AI chatbot for your WordPress website that intelligently retrieves posts, answers questions, and engages in natural conversations. This complete solution handles content

Qdrant Vector Store, OpenAI Embeddings, Document Default Data Loader +10

AI & RAG

Youtube RAG Search with Frontend Using Apify, Qdrant and AI

I originally started to template to ask questions on the "n8n @ scale office-hours" livestream videos but then extended it to include the latest videos on the official channel.

HTTP Request, Qdrant Vector Store, Document Default Data Loader +7

AI & RAG

Code Extractfromfile (http Request)

Code Extractfromfile. Uses manualTrigger, sort, httpRequest, compression. Event-driven trigger; 50 nodes.

HTTP Request, Compression, Edit Image +15

AI & RAG

2464

2464. Uses httpRequest, compression, editImage, documentDefaultDataLoader. Event-driven trigger; 50 nodes.

HTTP Request, Compression, Edit Image +15

Ingest Documents

The workflow JSON

About this workflow

Related workflows