This workflow follows the Agent → 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": "Related-item",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "related-item",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-32,
0
],
"id": "660815d1-28c5-4680-8589-ace315ae06db",
"name": "Webhook"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.body.cn }},{{ $json.body.en }}",
"options": {
"systemMessage": "\u4f60\u662f\u4e00\u4e2a\u52a9\u624b\u3002\u7528\u6237\u4f1a\u7ed9\u4f60\u4e00\u4e2a\u7269\u54c1\u7684\u4e2d\u6587\u540d\u5b57\u548c\u82f1\u6587\u540d\u5b57\u3002 \n\u8bf7\u8f93\u51fa\u4e00\u4e2aJSON\uff0c\u5305\u542b\uff1a \n1. related_items: 3\u4e2a\u4e0e\u8be5\u7269\u54c1\u76f8\u5173\u7684\u4e2d\u6587\u548c\u82f1\u6587\u540d\u5b57\u3002 \n2. example_sentences: 3\u4e2a\u53e5\u5b50\uff0c\u6bcf\u4e2a\u53e5\u5b50\u540c\u65f6\u5305\u542b\u4e2d\u6587\u548c\u82f1\u6587\uff0c\u53e5\u5b50\u91cc\u8981\u4f7f\u7528\u5230\u8fd9\u4e2a\u7269\u54c1\u3002 \n\n\u5fc5\u987b\u662f\u5408\u6cd5\u7684JSON\u683c\u5f0f\uff0c\u4e0d\u8981\u8f93\u51fa\u5176\u4ed6\u5185\u5bb9\u3002\n\n\u793a\u4f8b\uff08\u8bf7\u4e25\u683c\u6309\u4e0a\u9762\u7ed3\u6784\u8f93\u51fa\uff0c\u4e0d\u8981\u5728\u771f\u5b9e\u8f93\u51fa\u4e2d\u5305\u542b\u6ce8\u91ca\uff09\uff1a\n{\n \"related_items\": [\n {\"cn\": \"\u725b\u5976\", \"en\": \"milk\"},\n {\"cn\": \"\u7cd6\", \"en\": \"sugar\"},\n {\"cn\": \"\u676f\u5b50\", \"en\": \"cup\"}\n ],\n \"example_sentences\": [\n {\"cn\": \"\u6211\u65e9\u4e0a\u559d\u4e86\u4e00\u676f\u5496\u5561\u3002\", \"en\": \"I drank a cup of coffee this morning.\"},\n {\"cn\": \"\u5496\u5561\u592a\u70eb\u4e86\uff0c\u5c0f\u5fc3\u522b\u88ab\u70eb\u5230\u3002\", \"en\": \"The coffee is too hot; be careful not to burn yourself.\"},\n {\"cn\": \"\u6211\u4eec\u53bb\u5496\u5561\u5e97\u5750\u5750\u5427\u3002\", \"en\": \"Let's go to the coffee shop and sit for a while.\"}\n ]\n}"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
208,
0
],
"id": "3dcb4782-5c9c-4fd0-9209-3dea5353e17f",
"name": "AI Agent"
},
{
"parameters": {
"respondWith": "allIncomingItems",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
768,
0
],
"id": "b61facde-996c-4271-9b59-8f678e94d0ac",
"name": "Respond to Webhook"
},
{
"parameters": {
"jsCode": "// n8n Code \u8282\u70b9\nreturn items.map(item => {\n let parsed;\n try {\n parsed = JSON.parse(item.json.output); // \u628a output \u91cc\u7684\u5b57\u7b26\u4e32\u89e3\u6790\u6210\u5bf9\u8c61\n } catch (e) {\n throw new Error(\"JSON \u89e3\u6790\u5931\u8d25: \" + e.message);\n }\n\n return {\n json: parsed\n };\n});\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
560,
0
],
"id": "2977f9b1-5875-413c-9a05-b43f723f27dc",
"name": "Code in JavaScript"
},
{
"parameters": {
"model": "meta.llama3-70b-instruct-v1:0",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAwsBedrock",
"typeVersion": 1.1,
"position": [
208,
192
],
"id": "fb98becc-23af-44f4-bef6-c068372d4970",
"name": "AWS Bedrock Chat Model",
"credentials": {
"aws": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "=http://172.31.30.231:3005/api/words",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ $json.data }}",
"options": {}
},
"id": "be151d84-6b49-4b5e-b1ab-6243cf7cad5f",
"name": "POST2",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
1312,
-176
]
},
{
"parameters": {
"url": "http://172.31.30.231:3005/api/profile",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1040,
-176
],
"id": "049f4904-45f7-4d46-8c9a-a2f4b517de72",
"name": "HTTP Request"
},
{
"parameters": {
"url": "=http://172.31.30.231:3005/api/user-statistics/{{ $json.data.id }}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1216,
0
],
"id": "eddabedf-48b5-4000-8306-08b84118a519",
"name": "Get Cache Statistics"
},
{
"parameters": {
"url": "=http://172.31.30.231:3005/api/profile",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
976,
0
],
"id": "0b334064-a098-4df2-afef-48837c944067",
"name": "HTTP Request3"
},
{
"parameters": {
"method": "PUT",
"url": "=http://172.31.30.231:3005/api/user-statistics/{{ $json.data.users_id }}",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ $json.data }}",
"options": {}
},
"id": "e180e48d-fe7f-47bb-a443-e899d8c10c80",
"name": "Update Statistics",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
1616,
0
]
},
{
"parameters": {
"jsCode": "return items.map(item => {\n const old = item.json;\n\n return {\n json: {\n ...old,\n data: {\n ...old.data,\n words_learned: (old.data.words_learned || 0) + 3\n }\n }\n };\n});\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1424,
0
],
"id": "8c9cd0bf-50b7-4466-a7c6-97367ea6ac7b",
"name": "Code in JavaScript4"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Code in JavaScript",
"type": "main",
"index": 0
}
]
]
},
"Code in JavaScript": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"AWS Bedrock Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Respond to Webhook": {
"main": [
[
{
"node": "HTTP Request3",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[
{
"node": "POST2",
"type": "main",
"index": 0
}
]
]
},
"Get Cache Statistics": {
"main": [
[
{
"node": "Code in JavaScript4",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request3": {
"main": [
[
{
"node": "Get Cache Statistics",
"type": "main",
"index": 0
}
]
]
},
"Code in JavaScript4": {
"main": [
[
{
"node": "Update Statistics",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "50e331c2-4f96-4458-bcfb-44944f915267",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "ksjqJdms3YMOWRnp",
"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.
aws
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Related-item. Uses agent, lmChatAwsBedrock, httpRequest. Webhook trigger; 11 nodes.
Source: https://github.com/gohyumin/amadues/blob/033615f2949d87617d54e817f3985c9b3742e112/workflow/Related-item.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.
TestFluxNova. Uses httpRequest, agent, outputParserStructured, lmChatAwsBedrock. Webhook trigger; 18 nodes.
HTTP Request, Agent, Output Parser Structured +2
Agent-Combined-Flow. Uses httpRequest, agent, outputParserStructured, lmChatAwsBedrock. Webhook trigger; 18 nodes.
HTTP Request, Agent, Output Parser Structured +2
Agent-Trainer-Micro. Uses agent, lmChatAwsBedrock, outputParserStructured, httpRequest. Webhook trigger; 10 nodes.
Agent, Lm Chat Aws Bedrock, Output Parser Structured +1
⏺ 🚀 How it works
Agent, Anthropic Chat, Output Parser Structured +6
L&D_AgentsAI_ATIVO. Uses httpRequest, agent, googleCalendarTool, toolSerpApi. Webhook trigger; 93 nodes.
HTTP Request, Agent, Google Calendar Tool +9