This workflow follows the Documentdefaultdataloader → Textsplittertokensplitter 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 →
{
"createdAt": "2025-10-05T16:58:20.858Z",
"updatedAt": "2025-10-08T15:17:29.000Z",
"id": "Cr5GbenQMcpGRbH0",
"name": "IMS - Backend",
"active": true,
"isArchived": false,
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{}
]
}
},
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
-224,
96
],
"id": "32adb0cc-2bb5-4b80-881f-1362be3bd9fe",
"name": "Schedule Trigger"
},
{
"parameters": {
"mode": "combine",
"fieldsToMatchString": "table_name",
"options": {}
},
"type": "n8n-nodes-base.merge",
"typeVersion": 3.2,
"position": [
224,
96
],
"id": "a02548ee-25b7-40ea-9314-454f8416aa8c",
"name": "Merge"
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT\n tc.table_name,\n kcu.column_name,\n ccu.table_name AS foreign_table_name,\n ccu.column_name AS foreign_column_name,\n tc.constraint_name\nFROM information_schema.table_constraints AS tc\nJOIN information_schema.key_column_usage AS kcu\n ON tc.constraint_name = kcu.constraint_name\nJOIN information_schema.constraint_column_usage AS ccu\n ON ccu.constraint_name = tc.constraint_name\nWHERE tc.constraint_type = 'FOREIGN KEY'\nORDER BY tc.table_name;\n",
"options": {}
},
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.6,
"position": [
0,
192
],
"id": "c0f2381d-40b2-4be2-a400-44310fef3681",
"name": "Extract FKs",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT \n t.table_name,\n array_agg(\n json_build_object(\n 'column', c.column_name,\n 'type', c.data_type,\n 'nullable', c.is_nullable,\n 'default', c.column_default\n ) ORDER BY c.ordinal_position\n ) as columns,\n obj_description((t.table_schema||'.'||t.table_name)::regclass, 'pg_class') as table_description\nFROM information_schema.tables t\nJOIN information_schema.columns c \n ON t.table_name = c.table_name \n AND t.table_schema = c.table_schema\nWHERE t.table_schema = 'public' \n AND t.table_type = 'BASE TABLE'\nGROUP BY t.table_name, t.table_schema\nORDER BY t.table_name;\n",
"options": {}
},
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.6,
"position": [
0,
0
],
"id": "d70377b4-ad86-4381-ad13-72f265cccaef",
"name": "Extract Schemas",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Get all items from merged PostgreSQL results\nconst allItems = $input.all();\n\n// Group by unique table to avoid duplicates\nconst tableMap = new Map();\n\nallItems.forEach(item => {\n const data = item.json;\n const tableName = data.table_name;\n \n // Initialize table entry if doesn't exist\n if (!tableMap.has(tableName)) {\n tableMap.set(tableName, {\n table_name: tableName,\n columns: data.columns || [],\n relationships: []\n });\n }\n \n // Add relationship if present\n if (data.column_name && data.foreign_table_name) {\n tableMap.get(tableName).relationships.push({\n column: data.column_name,\n foreign_table: data.foreign_table_name,\n foreign_column: data.foreign_column_name,\n constraint: data.constraint_name\n });\n }\n});\n\n// Convert map to array and create descriptions\nconst descriptions = Array.from(tableMap.values()).map(table => {\n const tableName = table.table_name;\n const columns = table.columns;\n const relationships = table.relationships;\n \n // Create column descriptions\n const columnDesc = columns.map(col => \n `${col.column} (${col.type}${col.nullable === 'NO' ? ', required' : ''})`\n ).join(', ');\n \n // Create relationship descriptions\n const relDesc = relationships.length > 0 \n ? relationships.map(r => \n `${r.column} \u2192 ${r.foreign_table}.${r.foreign_column}`\n ).join('; ')\n : 'No foreign keys';\n \n // Build comprehensive description\n const fullDescription = `Table: ${tableName}. Columns: ${columnDesc}. Foreign Keys: ${relDesc}.`;\n \n return {\n json: {\n pageContent: fullDescription,\n metadata: {\n doc_type: 'schema',\n table_name: tableName,\n column_count: columns.length,\n fk_count: relationships.length.toString(),\n has_relationships: relationships.length > 0 ? 'yes' : 'no'\n }\n }\n };\n});\n\nreturn descriptions;\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
448,
96
],
"id": "2753d73d-9e51-48ad-bc7d-c336918add10",
"name": "Code in JavaScript"
},
{
"parameters": {
"mode": "insert",
"milvusCollection": {
"__rl": true,
"value": "inventory_schema_kb",
"mode": "list",
"cachedResultName": "inventory_schema_kb"
},
"options": {
"clearCollection": true
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
"typeVersion": 1.3,
"position": [
704,
96
],
"id": "a7630333-1a29-45e1-99fc-120f940efd03",
"name": "Milvus Vector Store",
"credentials": {
"milvusApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.embeddingsCohere",
"typeVersion": 1,
"position": [
672,
320
],
"id": "a19fb2a0-29ed-46b5-af04-c24dd9530fb2",
"name": "Embeddings Cohere",
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{ $json.pageContent }}",
"textSplittingMode": "custom",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
800,
320
],
"id": "b169a309-11fa-4dc2-ad38-8a4b1749db8d",
"name": "Default Data Loader"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"typeVersion": 1,
"position": [
880,
528
],
"id": "3f662c48-3ff0-49e8-9916-0a43f222283e",
"name": "Token Splitter"
}
],
"connections": {
"Schedule Trigger": {
"main": [
[
{
"node": "Extract Schemas",
"type": "main",
"index": 0
},
{
"node": "Extract FKs",
"type": "main",
"index": 0
}
]
]
},
"Extract FKs": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Extract Schemas": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Code in JavaScript",
"type": "main",
"index": 0
}
]
]
},
"Code in JavaScript": {
"main": [
[
{
"node": "Milvus Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Cohere": {
"ai_embedding": [
[
{
"node": "Milvus Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Milvus Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"staticData": {
"node:Schedule Trigger": {
"recurrenceRules": []
}
},
"meta": {
"templateCredsSetupCompleted": true
},
"versionId": "9d86da11-31fc-45ef-8480-142e128b1caa",
"triggerCount": 1,
"tags": [
{
"createdAt": "2025-10-05T16:56:30.557Z",
"updatedAt": "2025-10-05T16:56:30.557Z",
"id": "aIO4nhMQOfAgk71k",
"name": "IMS"
}
],
"shared": [
{
"createdAt": "2025-10-05T16:58:20.864Z",
"updatedAt": "2025-10-05T16:58:20.864Z",
"role": "workflow:owner",
"workflowId": "Cr5GbenQMcpGRbH0",
"projectId": "0tBJbgcFWwxEMKPn",
"project": {
"createdAt": "2025-10-05T16:55:31.619Z",
"updatedAt": "2025-10-05T16:55:58.616Z",
"id": "0tBJbgcFWwxEMKPn",
"name": "Bikash Panda <oksbwn@gmail.com>",
"type": "personal",
"icon": null,
"description": null
}
}
]
}
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.
cohereApimilvusApipostgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
IMS - Backend. Uses postgres, vectorStoreMilvus, embeddingsCohere, documentDefaultDataLoader. Scheduled trigger; 9 nodes.
Source: https://github.com/oksbwn/Inventory-Management-System/blob/7f26462a83a574049df178775808226e970cd4f8/n8n/Cr5GbenQMcpGRbH0.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Search Worflow Docker Complete. Uses documentDefaultDataLoader, textSplitterCharacterTextSplitter, vectorStoreSupabase, embeddingsOllama. Scheduled trigger; 71 nodes.
Document Default Data Loader, Text Splitter Character Text Splitter, Supabase Vector Store +14
Wordpress Ai Chatbot To Enhance User Experience With Supabase And Openai. Uses manualTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterTokenSplitter. Event-driven trigger; 53 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Token Splitter +9
RAG & GenAI App With WordPress Content. Uses manualTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterTokenSplitter. Event-driven trigger; 53 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Token Splitter +9
RAG & GenAI App With WordPress Content. Uses manualTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterTokenSplitter. Event-driven trigger; 53 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Token Splitter +9
/billing - For payment and invoice questions /tech-support - For technical assistance /return-policy - For returns and refunds Command-based routing Direct department access via slash commands Tracks
Telegram, Pinecone Vector Store, Google Drive Trigger +9