This workflow follows the Chainllm → 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "2a5a96c9-926c-447d-8244-db760e48a45f",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-140
],
"parameters": {
"content": "## Edit your own prompt \u2b07\ufe0f\n"
},
"typeVersion": 1
},
{
"id": "4c3a6b0b-2771-441d-8cb2-e17c07a92156",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1440,
-100
],
"parameters": {
"content": "## Filter comments and customize your trigger words \u2b07\ufe0f"
},
"typeVersion": 1
},
{
"id": "4f42b776-cc24-486c-889f-7c09522503ed",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1180,
-120
],
"parameters": {
"content": "## Replace your gitlab URL and token \u2b07\ufe0f"
},
"typeVersion": 1
},
{
"id": "b8859219-ce90-4940-8d9e-338c742def5e",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
140,
-140
],
"parameters": {
"content": "## Replace your gitlab URL and token \u2b07\ufe0f"
},
"typeVersion": 1
},
{
"id": "6be296f3-bd61-4644-825f-d96d591f229e",
"name": "Need Review",
"type": "n8n-nodes-base.if",
"position": [
-1440,
100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "617eb2c5-dd4b-4e28-b533-0c32ea6ca961",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.body.object_attributes.note }}",
"rightValue": "+0"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "fe59eeab-03a1-4b36-97f2-bf04bf6e4b8d",
"name": "Get Changes",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1180,
80
],
"parameters": {
"url": "=https://gitlab.com/api/v4/projects/{{ $json[\"body\"][\"project_id\"] }}/merge_requests/{{ $json[\"body\"][\"merge_request\"][\"iid\"] }}/changes",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "PRIVATE-TOKEN"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "4fe2800c-1eb5-44c6-93bb-25285a015b1d",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
-1000,
80
],
"parameters": {
"options": {},
"fieldToSplitOut": "changes"
},
"typeVersion": 1
},
{
"id": "1838ffe7-a846-473b-9716-2714d527c727",
"name": "Skip File Changes",
"type": "n8n-nodes-base.if",
"position": [
-820,
80
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "c6e1430b-84a7-47ce-8fe9-7b94da0f2d31",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
},
"leftValue": "={{ $json.renamed_file }}",
"rightValue": ""
},
{
"id": "bf6e9eb9-d72d-459c-a722-9614bab8842c",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
},
"leftValue": "={{ $json.deleted_file }}",
"rightValue": ""
},
{
"id": "501623a9-9515-4034-bb13-a5a6a4f924eb",
"operator": {
"type": "string",
"operation": "startsWith"
},
"leftValue": "={{ $json.diff }}",
"rightValue": "@@"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "6215ecd2-55ad-4652-8c1f-f08713fdc237",
"name": "Parse Last Diff Line",
"type": "n8n-nodes-base.code",
"position": [
-560,
-120
],
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const parseLastDiff = (gitDiff) => {\n gitDiff = gitDiff.replace(/\\n\\\\ No newline at end of file/, '')\n \n const diffList = gitDiff.trimEnd().split('\\n').reverse();\n const lastLineFirstChar = diffList?.[0]?.[0];\n const lastDiff =\n diffList.find((item) => {\n return /^@@ \\-\\d+,\\d+ \\+\\d+,\\d+ @@/g.test(item);\n }) || '';\n\n const [lastOldLineCount, lastNewLineCount] = lastDiff\n .replace(/@@ \\-(\\d+),(\\d+) \\+(\\d+),(\\d+) @@.*/g, ($0, $1, $2, $3, $4) => {\n return `${+$1 + +$2},${+$3 + +$4}`;\n })\n .split(',');\n \n if (!/^\\d+$/.test(lastOldLineCount) || !/^\\d+$/.test(lastNewLineCount)) {\n return {\n lastOldLine: -1,\n lastNewLine: -1,\n gitDiff,\n };\n }\n\n\n const lastOldLine = lastLineFirstChar === '+' ? null : (parseInt(lastOldLineCount) || 0) - 1;\n const lastNewLine = lastLineFirstChar === '-' ? null : (parseInt(lastNewLineCount) || 0) - 1;\n\n return {\n lastOldLine,\n lastNewLine,\n gitDiff,\n };\n};\n\nreturn parseLastDiff($input.item.json.diff)\n"
},
"typeVersion": 2
},
{
"id": "bb3d6be0-7e85-4c2e-840a-090a36b48236",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-180,
60
],
"parameters": {
"text": "=File path\uff1a{{ $('Skip File Changes').item.json.new_path }}\n\n```Original code\n {{ $json.originalCode }}\n```\nchange to\n```New code\n {{ $json.newCode }}\n```\nPlease review the code changes in this section:",
"messages": {
"messageValues": [
{
"message": "# Overview:| You are a senior programming expert Bot, responsible for reviewing code changes and providing review recommendations. At the beginning of the suggestion, it is necessary to clearly make a decision to \"reject\" or \"accept\" the code change, and rate the change in the format \"Change Score: Actual Score\", with a score range of 0-100 points. Then, point out the existing problems in concise language and a stern tone. If you feel it is necessary, you can directly provide the modified content. Your review proposal must use rigorous Markdown format."
}
]
},
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "f3a6e8c6-eda1-4af1-bdd5-f3b56ef8c23b",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-180,
220
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "796b0d0f-320f-43ff-943a-0d15b73878c7",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
-1680,
100
],
"parameters": {
"path": "e21095c0-1876-4cd9-9e92-a2eac737f03e",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 2
},
{
"id": "74a7dd0c-fc01-411c-8ea9-e43b45c376c2",
"name": "Code",
"type": "n8n-nodes-base.code",
"position": [
-360,
-120
],
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nvar diff = $input.item.json.gitDiff\n\nlet lines = diff.trimEnd().split('\\n');\n\nlet originalCode = '';\nlet newCode = '';\n\nlines.forEach(line => {\n console.log(line)\n if (line.startsWith('-')) {\n originalCode += line + \"\\n\";\n } else if (line.startsWith('+')) {\n newCode += line + \"\\n\";\n } else {\n originalCode += line + \"\\n\";\n newCode += line + \"\\n\";\n }\n});\n\nreturn {\n originalCode:originalCode,\n newCode:newCode\n};\n\n"
},
"typeVersion": 2
},
{
"id": "d55f0b8f-aac5-49e3-a5f1-9dd1a7c46254",
"name": "Post Discussions",
"type": "n8n-nodes-base.httpRequest",
"position": [
240,
60
],
"parameters": {
"url": "=https://gitlab.com/api/v4/projects/{{ $('Webhook').item.json[\"body\"][\"project_id\"] }}/merge_requests/{{ $('Webhook').item.json[\"body\"][\"merge_request\"][\"iid\"] }}/discussions",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "body",
"value": "={{ $('Basic LLM Chain').item.json[\"text\"] }}"
},
{
"name": "position[position_type]",
"value": "text"
},
{
"name": "position[old_path]",
"value": "={{ $('Split Out').item.json.old_path }}"
},
{
"name": "position[new_path]",
"value": "={{ $('Split Out').item.json.new_path }}"
},
{
"name": "position[start_sha]",
"value": "={{ $('Get Changes').item.json.diff_refs.start_sha }}"
},
{
"name": "position[head_sha]",
"value": "={{ $('Get Changes').item.json.diff_refs.head_sha }}"
},
{
"name": "position[base_sha]",
"value": "={{ $('Get Changes').item.json.diff_refs.base_sha }}"
},
{
"name": "position[new_line]",
"value": "={{ $('Parse Last Diff Line').item.json.lastNewLine || '' }}"
},
{
"name": "position[old_line]",
"value": "={{ $('Parse Last Diff Line').item.json.lastOldLine || '' }}"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "PRIVATE-TOKEN"
}
]
}
},
"typeVersion": 4.2
}
],
"connections": {
"Code": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Need Review",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Skip File Changes",
"type": "main",
"index": 0
}
]
]
},
"Get Changes": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Need Review": {
"main": [
[
{
"node": "Get Changes",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Post Discussions",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Skip File Changes": {
"main": [
[
{
"node": "Parse Last Diff Line",
"type": "main",
"index": 0
}
]
]
},
"Parse Last Diff Line": {
"main": [
[
{
"node": "Code",
"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
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow streamlines the extraction of specific details from incoming webhooks, delivering targeted outputs without manual sifting through complex data streams. It's ideal for developers and automation enthusiasts handling API responses or form submissions that require parsing into usable segments, saving hours of repetitive coding. The key step involves the splitOut node, which intelligently divides the payload after an initial HTTP request fetches changes, often enhanced by ChainLLM for AI-driven refinement using OpenAI integration.
Use this workflow when processing dynamic web data like user submissions or API updates demands precise splitting to trigger downstream actions, such as notifications or database entries. Avoid it for static files or simple boolean checks, where basic if nodes suffice without the overhead of 14 nodes. Common variations include swapping HTTP Request for direct database pulls or adding LM Chat OpenAI for natural language queries on the split data.
About this workflow
Splitout. Uses stickyNote, httpRequest, splitOut, chainLlm. Webhook trigger; 14 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.
Code. Uses httpRequest, extractFromFile, splitInBatches, noOp. Webhook trigger; 51 nodes.
HTTP Request, Chain Llm, OpenAI Chat +1
Splitout Code. Uses httpRequest, extractFromFile, splitInBatches, noOp. Webhook trigger; 45 nodes.
HTTP Request, Chain Llm, OpenAI Chat
Stopanderror Splitout. Uses outputParserStructured, lmChatOpenAi, formTrigger, chainLlm. Event-driven trigger; 85 nodes.
Output Parser Structured, OpenAI Chat, Form Trigger +8
Splitout Schedule. Uses scheduleTrigger, microsoftExcel, lmChatOpenAi, splitOut. Scheduled trigger; 33 nodes.
Microsoft Excel, OpenAI Chat, Chain Llm +2
Extractfromfile Form Export. Uses extractFromFile, lmChatOpenAi, outputParserStructured, formTrigger. Event-driven trigger; 23 nodes.
OpenAI Chat, Output Parser Structured, Form Trigger +5