AI · 06 — RAG 1: load, split, store

The ingest half of RAG: a document is loaded, split into sentence chunks, and embedded into the 'ai-demo-kb' vector store by the ◈-wired store node (local nomic-embed-text). Run this once, then ask questions with demo 07.

What’s inside

6 nodes — every type links to its full reference page.

Step	Node	Type
Company handbook	Inject	`input.inject`
Load document	Document Loader	`processing.document-loader`
Split	Text Splitter	`processing.text-splitter`
Store in kb	AI Vector Store	`ai.vector-store`
Embeddings (local)	AI Model	`ai.model`
Done	Console	`utility.console`

Import it

Studio → Import — paste the JSON below (or the URL /docs/templates/ai-06-rag-1-load-split-store.json).

Or ask the AI Copilot with the JSON pasted after the phrase:

import this workflow json into a new workflow named "AI · 06 — RAG 1: load, split, store"

Any credentials the nodes need are ${credential.…} references — add them once in Admin → Credentials and the template picks them up. Nothing secret ships in a template.

The workflow document (flowdrome.workflow.v1, 6 node types)

{
  "schemaVersion": "flowdrome.workflow.v1",
  "id": "",
  "name": "AI · 06 — RAG 1: load, split, store",
  "version": "0",
  "status": "draft",
  "nodes": [
    {
      "id": "seed",
      "type": "input.inject",
      "label": "Company handbook",
      "category": "trigger",
      "config": {
        "contentType": "application/json",
        "payload": {
          "doc": "Acme ships all orders within 2 business days. Returns are accepted within 30 days of delivery for a full refund. Support is available Monday to Friday, 9am to 6pm Eastern. Express shipping upgrades cost $12 and arrive next day. Gift cards never expire and are not refundable."
        }
      },
      "position": {
        "x": 0,
        "y": 0
      }
    },
    {
      "id": "load",
      "type": "processing.document-loader",
      "label": "Load document",
      "category": "ai",
      "config": {
        "source": "field",
        "field": "doc",
        "stripHtml": true,
        "timeoutMs": 30000
      },
      "position": {
        "x": 530,
        "y": 0
      }
    },
    {
      "id": "split",
      "type": "processing.text-splitter",
      "label": "Split",
      "category": "ai",
      "config": {
        "strategy": "sentences",
        "chunkSize": 80,
        "chunkOverlap": 0,
        "textField": "text",
        "outputField": "chunks"
      },
      "position": {
        "x": 1060,
        "y": 0
      }
    },
    {
      "id": "store",
      "type": "ai.vector-store",
      "label": "Store in kb",
      "category": "ai",
      "config": {
        "operation": "insert",
        "store": "ai-demo-kb",
        "provider": "ollama",
        "baseUrl": "",
        "apiKey": "",
        "model": "nomic-embed-text",
        "textField": "chunks",
        "metadataField": "",
        "topK": 4,
        "keywordWeight": "0",
        "backend": "memory",
        "backendUrl": "",
        "backendKey": "",
        "timeoutMs": 120000
      },
      "position": {
        "x": 1590,
        "y": 0
      },
      "attachments": {
        "model": "emb"
      }
    },
    {
      "id": "emb",
      "type": "ai.model",
      "label": "Embeddings (local)",
      "category": "ai",
      "config": {
        "provider": "ollama",
        "baseUrl": "",
        "apiKey": "",
        "model": "nomic-embed-text",
        "models": [],
        "temperature": 0.2,
        "maxTokens": 512
      },
      "position": {
        "x": 1590,
        "y": 222
      }
    },
    {
      "id": "out",
      "type": "utility.console",
      "label": "Done",
      "category": "utility",
      "config": {
        "message": "Ingested {{ $json.inserted }} chunks into 'ai-demo-kb' — now Test demo 07."
      },
      "position": {
        "x": 2120,
        "y": 0
      }
    }
  ],
  "edges": [
    {
      "id": "e0",
      "sourceNodeId": "seed",
      "sourcePort": "output",
      "targetNodeId": "load",
      "targetPort": "input"
    },
    {
      "id": "e1",
      "sourceNodeId": "load",
      "sourcePort": "output",
      "targetNodeId": "split",
      "targetPort": "input"
    },
    {
      "id": "e2",
      "sourceNodeId": "split",
      "sourcePort": "output",
      "targetNodeId": "store",
      "targetPort": "input"
    },
    {
      "id": "e3",
      "sourceNodeId": "store",
      "sourcePort": "output",
      "targetNodeId": "out",
      "targetPort": "input"
    }
  ],
  "triggers": [
    {
      "id": "t0",
      "nodeId": "seed"
    }
  ],
  "meta": {
    "snippets": [],
    "source": "template-gallery",
    "description": "The ingest half of RAG: a document is loaded, split into sentence chunks, and embedded into the 'ai-demo-kb' vector store by the ◈-wired store node (local nomic-embed-text). Run this once, then ask questions with demo 07."
  }
}

Generated from the verified demo corpus — this exact document seeds and runs on a fresh Flowdrome. Raw JSON: ai-06-rag-1-load-split-store.json.