This workflow follows the Chainllm → OpenAI Chat 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 →
{
"id": "cKRViOHDPsosO7UX",
"name": "[AI/LangChain] Output Parser 4",
"tags": [],
"nodes": [
{
"id": "3d669ba2-65b7-4502-92d9-645c4e51b26d",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
380,
240
],
"parameters": {},
"typeVersion": 1
},
{
"id": "9a509299-746d-4a3f-b379-8a4a9a92c75a",
"name": "Prompt",
"type": "n8n-nodes-base.set",
"position": [
600,
240
],
"parameters": {
"values": {
"string": [
{
"name": "input",
"value": "Return the 5 largest states by area in the USA with their 3 largest cities and their population."
}
]
},
"options": {}
},
"typeVersion": 2
},
{
"id": "e2092fe6-d803-43e9-b2df-b0fc7aa83b02",
"name": "LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1060,
240
],
"parameters": {},
"typeVersion": 1
},
{
"id": "711734d0-1003-4639-bdee-c160f6f976b3",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1560,
900
],
"parameters": {
"jsonSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"state\": {\n \"type\": \"string\"\n },\n \"cities\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": \"string\",\n \"population\": \"number\"\n }\n }\n }\n }\n}"
},
"typeVersion": 1
},
{
"id": "f9b782f8-bb7b-4d65-be0d-d65c11de03d2",
"name": "Auto-fixing Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserAutofixing",
"position": [
1260,
540
],
"parameters": {},
"typeVersion": 1
},
{
"id": "a26f034e-ea19-47ba-8fef-4f0a0d447c01",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
1480,
795
],
"parameters": {
"height": 264.69900963477494,
"content": "### Parser which defines the output format and which gets used to validate the output"
},
"typeVersion": 1
},
{
"id": "d902971a-e304-449c-a933-900c9c49ce55",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1080,
792
],
"parameters": {
"height": 266.9506012398238,
"content": "### The LLM which gets used to try to autofix the output in case it was not valid"
},
"typeVersion": 1
},
{
"id": "b4c3b935-61b1-4243-b7df-ba4b7fd6e3ce",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
920,
440
],
"parameters": {
"height": 245.56048099185898,
"content": "### The LLM to process the original prompt"
},
"typeVersion": 1
},
{
"id": "916d2998-cf0e-40f9-a373-149c609ed229",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1200,
449
],
"parameters": {
"width": 348.0763970423483,
"height": 233.17672716408998,
"content": "### Autofixing parser which tries to fix invalid outputs with the help of an LLM"
},
"typeVersion": 1
},
{
"id": "5cabf993-6bdd-4401-bb6d-fa20ff703127",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
980,
540
],
"parameters": {
"options": {
"temperature": 0
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "7f666edb-ecb7-4a6d-9dc7-ba67ef41d71f",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1140,
900
],
"parameters": {
"options": {
"temperature": 0
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "976446d0-eb9d-478e-8178-69017329d736",
"connections": {
"Prompt": {
"main": [
[
{
"node": "LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Auto-fixing Output Parser",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Auto-fixing Output Parser",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Auto-fixing Output Parser": {
"ai_outputParser": [
[
{
"node": "LLM Chain",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "Prompt",
"type": "main",
"index": 0
}
]
]
}
}
}
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.
openAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
[AI/LangChain] Output Parser 4. Uses manualTrigger, chainLlm, outputParserStructured, outputParserAutofixing. Event-driven trigger; 11 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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.
Turns a plain name + email into a fully-enriched HubSpot contact by matching the person in Apollo, pulling their latest LinkedIn activity, summarising the findings with GPT-4o, and upserting the clean
This workflow is designed for content creators, prompt engineers, AI developers, and anyone who needs to create effective, structured prompts for AI agents. It helps transform vague ideas into detaile
This workflow is for anyone looking to automatically fetch, validate, and parse complex language-based queries into a structured format. Its unique capability lies in not only processing language but
Agent Nodes. Uses lmChatOpenAi, slack, stopAndError, errorTrigger. Event-driven trigger; 72 nodes.
Many new n8n users struggle with testing webhooks when running n8n on localhost, as external services cannot reach . This workflow introduces a technique using PostBin, which provides a temporary, pub