This workflow follows the Datatable → HTTP Request 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 →
{
"name": "concept-comparison",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
0,
0
],
"id": "dd28341c-cb87-49a5-8562-4a809bc0915c",
"name": "When clicking \u2018Execute workflow\u2019"
},
{
"parameters": {
"jsCode": "// utils\n\nfunction indexBy(f, objs) {\n return objs.reduce((acc, c) => {\n acc[f(c)] = c;\n return acc;\n },\n {});\n}\n\nreturn [{\n json: {\n properties: $('Set properties').first().json,\n parameters: indexBy((c) => c.parameter, items.map(item => item.json))\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
560,
0
],
"id": "5e60a30a-9e0c-4207-bb56-4a1a14f53389",
"name": "Merge items"
},
{
"parameters": {
"jsCode": "// utils\nfunction toPerc(x) {\n return Math.round(x * 100) + '%'\n}\n// core\nconst perspective_aspects = \n $('AI-function: compare concepts').first().json.result.perspective_aspects;\n//console.log(perspective_aspects);\nlet features = perspective_aspects.reduce((acc, aspect) => \n [...acc, ...aspect.aspect_features.map(feature => \n ({\n LLM_model: $('Merge items').first().json.parameters.LLM_model.value,\n type: 'feature_score',\n ...feature,\n aspect_name: aspect.aspect_name,\n a_winner: feature.normalized_comparison > 0,\n a_score: feature.normalized_comparison >= 0 ? toPerc(feature.normalized_comparison) : 0,\n b_winner: feature.normalized_comparison < 0,\n b_score: feature.normalized_comparison <= 0 ? toPerc(-feature.normalized_comparison) : 0,\n message: `a_concept: ${$('Merge items').first().json.parameters.a_concept.value}, b_concept: ${$('Merge items').first().json.parameters.b_concept.value}`})\n )]\n , []);\nconst comparison_total = $('AI-function: compare concepts').first().json.result.comparison_total;\nconst a_winner_total = comparison_total > 0;\nconst b_winner_total = comparison_total < 0;\nfeatures = [{\n LLM_model: $('Merge items').first().json.parameters.LLM_model.value,\n type: 'model_total',\n aspect_name: '-',\n feature_name: '-',\n a_winner: a_winner_total,\n a_score: toPerc(comparison_total),\n b_winner: b_winner_total,\n b_score: toPerc(-comparison_total),\n message: `Winner concept: ${$('AI-function: compare concepts').first().json.result.comparison_winner}\\nOther_details:\\nperspective_observer_strategy: ${$('AI-function: compare concepts').first().json.result.perspective_observer_strategy}\\npoint_of_view: ${$('AI-function: compare concepts').first().json.result.point_of_view}\\nsuperordinate_concept: ${$('AI-function: compare concepts').first().json.result.superordinate_concept}`\n }, \n ... features];\nreturn features;"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
992,
0
],
"id": "be2e3669-b8f9-4bf8-aeb0-e6b8f2443acc",
"name": "Split items"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "ad40503a-0154-401b-98cb-5151db0c93bd",
"name": "ai_functions_url",
"value": "http://127.0.0.1:5001",
"type": "string"
},
{
"id": "a0fb242a-270d-4343-afdd-2ea693c9e4b3",
"name": "ai_functions_api_token",
"value": "xxx",
"type": "string"
},
{
"id": "8d4b81b8-5f92-4ff9-97c4-5ebcbc54f66e",
"name": "extra_information_retrieval_strategy",
"value": "Only_unbiased_authorative_sources: true",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
208,
0
],
"id": "0765eb51-9878-4f11-b357-1796083b6386",
"name": "Set properties"
},
{
"parameters": {
"method": "PUT",
"url": "={{ $json.properties.ai_functions_url }}/ai-func/concept_aspect_comparison",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "Accept",
"value": "application/json"
},
{
"name": "Api-Token",
"value": "={{ $json.properties.ai_functions_api_token }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\"observer_context_description\": \"{{ $json.parameters.observer_context_description.value }}\", \"frame_of_reference\": \"{{ $json.parameters.frame_of_reference.value }}\",\n\"a_concept\": \"{{ $json.parameters.a_concept.value }}\",\n\"b_concept\": \"{{ $json.parameters.b_concept.value }}\", \"output_content_language\": \"{{ $json.parameters.output_content_language.value }}\",\n\"extra_information_retrieval_strategy\": \"{{ $json.properties.extra_information_retrieval_strategy }}\",\n\"meta\": {\"model\": \"{{ $json.parameters.LLM_model.value }}\"}} ",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.3,
"position": [
768,
0
],
"id": "86e2f6af-3efd-403d-bf95-8ea687b8e489",
"name": "AI-function: compare concepts"
},
{
"parameters": {
"operation": "get",
"dataTableId": {
"__rl": true,
"value": "Mc7cdh2eJFl2DB5Z",
"mode": "list",
"cachedResultName": "concept-comparison-input",
"cachedResultUrl": "/projects/QosD6QypqpaVnHlA/datatables/Mc7cdh2eJFl2DB5Z"
},
"returnAll": true
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1,
"position": [
384,
0
],
"id": "2e17c18c-142d-49b0-896f-e40207ae316b",
"name": "Read input table"
},
{
"parameters": {
"operation": "deleteRows",
"dataTableId": {
"__rl": true,
"value": "c9OXF8AX7G7DVI9n",
"mode": "list",
"cachedResultName": "concept-comparison-output",
"cachedResultUrl": "/projects/QosD6QypqpaVnHlA/datatables/c9OXF8AX7G7DVI9n"
},
"filters": {
"conditions": [
{
"condition": "isNotEmpty"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1,
"position": [
0,
192
],
"id": "7e18d02f-49e0-491b-abcc-8624c883dd98",
"name": "Clear output table",
"alwaysOutputData": true,
"disabled": true
},
{
"parameters": {
"dataTableId": {
"__rl": true,
"value": "c9OXF8AX7G7DVI9n",
"mode": "list",
"cachedResultName": "concept-comparison-output",
"cachedResultUrl": "/projects/QosD6QypqpaVnHlA/datatables/c9OXF8AX7G7DVI9n"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"a_concept_score": "={{ $json.a_score }}",
"b_concept_score": "={{ $json.b_score }}",
"aspect_feature": "={{ $json.feature_name || '-' }}",
"aspect_name": "={{ $json.aspect_name || '-' }}",
"a_concept_winner": "={{ $json.a_winner }}",
"b_concept_winner": "={{ $json.b_winner }}",
"type": "={{ $json.type }}",
"message": "={{ $json.message }}",
"LLM_model": "={{ $json.LLM_model }}"
},
"matchingColumns": [],
"schema": [
{
"id": "LLM_model",
"displayName": "LLM_model",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "type",
"displayName": "type",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "aspect_name",
"displayName": "aspect_name",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "aspect_feature",
"displayName": "aspect_feature",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "a_concept_winner",
"displayName": "a_concept_winner",
"required": false,
"defaultMatch": false,
"display": true,
"type": "boolean",
"readOnly": false,
"removed": false
},
{
"id": "a_concept_score",
"displayName": "a_concept_score",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "b_concept_winner",
"displayName": "b_concept_winner",
"required": false,
"defaultMatch": false,
"display": true,
"type": "boolean",
"readOnly": false,
"removed": false
},
{
"id": "b_concept_score",
"displayName": "b_concept_score",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "message",
"displayName": "message",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1,
"position": [
1184,
0
],
"id": "68406bab-5063-4cf3-ba64-c3b0e9dcf37b",
"name": "Update output table"
}
],
"connections": {
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Set properties",
"type": "main",
"index": 0
}
]
]
},
"Merge items": {
"main": [
[
{
"node": "AI-function: compare concepts",
"type": "main",
"index": 0
}
]
]
},
"Split items": {
"main": [
[
{
"node": "Update output table",
"type": "main",
"index": 0
}
]
]
},
"Set properties": {
"main": [
[
{
"node": "Read input table",
"type": "main",
"index": 0
}
]
]
},
"AI-function: compare concepts": {
"main": [
[
{
"node": "Split items",
"type": "main",
"index": 0
}
]
]
},
"Read input table": {
"main": [
[
{
"node": "Merge items",
"type": "main",
"index": 0
}
]
]
},
"Clear output table": {
"main": [
[]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "490c9a24-135e-4e10-94ff-27aaf44235c0",
"id": "Oa0L0tGz2uumQHDe",
"tags": []
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
concept-comparison. Uses httpRequest, dataTable. Event-driven trigger; 8 nodes.
Source: https://github.com/ady1981/core-kbt/blob/b9b4556b04515eca87ffa83a9c2966bf3c0cca5c/examples/n8n/concept-comparison.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.
This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detai
HTTP Request, XML, Data Table
This workflow automates the management of Zoom OAuth tokens and the creation of new Zoom users through the Zoom API.
Data Table, HTTP Request
62 - TOOL - read_competitor_posts. Uses executeWorkflowTrigger, httpRequest, dataTable. Event-driven trigger; 23 nodes.
Execute Workflow Trigger, HTTP Request, Data Table
This workflow runs a manual health assessment of a Wazuh deployment by querying the Wazuh Manager API, Wazuh Indexer API, and host metrics over SSH, then scores the results, generates prioritized reco
HTTP Request, Ssh, Data Table +1
This workflow runs daily (or manually) to pull vulnerability findings from Wazuh Indexer, enriches CVEs with FIRST EPSS and the CISA KEV catalog, calculates a priority score, tracks finding lifecycle
HTTP Request, Data Table, Email Send