Warren Gates 
This workflow corresponds to n8n.io template #14381 — we link there as the canonical source.
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 →
{
"id": "ica4EwxtFqquNriy",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Set Paperless Document Title w/Tag Removal",
"tags": [],
"nodes": [
{
"id": "dac1caa7-ca26-4712-bbcf-f26f04b2cd52",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
832
],
"parameters": {
"width": 480,
"height": 656,
"content": "## Set Paperless Document Title w/Tag Removal\n\n### How it works\n\n1. The workflow is triggered by a webhook when a title needs updating.\n2. Validates the incoming URL provided in the webhook.\n3. Fetches document content based on the valid URL.\n4. Uses AI to generate a new document name.\n5. Removes unnecessary tags and updates the document title.\n\n### Setup steps\n\n- [ ] Configure the Webhook node to receive update requests.\n- [ ] Set up the API authentication details for all HTTP Request nodes.\n- [ ] Ensure the AI Agent has access to required models like OpenAI Chat.\n\n### Customization\n\nAdjustment of tags to remove can be customized in the \"Filter Out Tag to Remove\" code node."
},
"typeVersion": 1
},
{
"id": "41e686d7-717f-4e22-a0bd-bbb2738aedf0",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
928
],
"parameters": {
"color": 7,
"width": 640,
"height": 464,
"content": "## Trigger and validation\n\nStarts workflow on webhook and validates the URL."
},
"typeVersion": 1
},
{
"id": "03ff65d0-e543-4ab2-9abd-848f2508cbcb",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1152,
928
],
"parameters": {
"color": 7,
"width": 640,
"height": 368,
"content": "## Fetch and evaluate document\n\nFetches document content and checks if it needs processing."
},
"typeVersion": 1
},
{
"id": "e377cc84-6766-4b24-8db5-f59dfef5f4b2",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1584,
832
],
"parameters": {
"color": 7,
"width": 576,
"height": 480,
"content": "## AI document name generation\n\nGenerates a new document name using AI."
},
"typeVersion": 1
},
{
"id": "fb80dceb-53f1-4aa9-9d12-9cb1bd539856",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
2176,
832
],
"parameters": {
"color": 7,
"width": 640,
"height": 272,
"content": "## Tag removal and update\n\nIdentifies and removes unnecessary tags, then updates the document."
},
"typeVersion": 1
},
{
"id": "7501a8b0-010d-4f12-a938-c35bce1553a3",
"name": "Fetch Document Content",
"type": "n8n-nodes-base.httpRequest",
"position": [
1200,
1040
],
"parameters": {
"url": "={{ $json.scheme }}://{{ $json.server }}/api/documents/{{ $json.documentId }}/",
"options": {
"response": {
"response": {
"fullResponse": true
}
}
},
"authentication": "genericCredentialType",
"genericAuthType": "httpBasicAuth"
},
"credentials": {
"httpBasicAuth": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"typeVersion": 4.3
},
{
"id": "eae50ac5-0899-497c-88ee-3c9c1b5ada13",
"name": "Apply Document Guardrails",
"type": "@n8n/n8n-nodes-langchain.guardrails",
"position": [
1648,
944
],
"parameters": {
"text": "={{ $json.body.content }}",
"operation": "sanitize",
"guardrails": {
"pii": {
"value": {
"type": "all"
}
}
}
},
"typeVersion": 2
},
{
"id": "29811062-625a-4362-a0f4-001a80d4d5ba",
"name": "Generate Title AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1872,
944
],
"parameters": {
"text": "={{ $json.guardrailsInput.substring(0, 10000) }}",
"options": {
"systemMessage": "Role: You are an expert Document Archivist and Information Architect. Your task is to analyze the text provided, which has been generated via OCR (Optical Character Recognition) from scanned documents.\n\nTask: Generate a concise, descriptive, and professional title for the document based on its primary subject matter, intent, and key entities (e.g., companies, dates, or specific project names).\n\nGuidelines:\n\n Contextual Accuracy: Prioritize formal headers, dates, and recurring keywords to determine the document type (e.g., Invoice, Technical Specification, Meeting Minutes, Contract).\n\n OCR Resilience: Ignore \"noise\" typical of OCR, such as garbled characters, misread page numbers, or fragmented headers.\n\n Format: Output only the suggested title. Limit the length to no more than 60 characters. Do not include introductory text like \"The title is...\" or \"I suggest...\"\n\n Naming Convention: Use a standard format: [YYYY-MM-DD] - [Document Type] - [Main Subject/Entity]. If a date is not found, omit it.\n\nTone: Professional and objective."
},
"promptType": "define"
},
"notesInFlow": false,
"typeVersion": 3.1,
"alwaysOutputData": false
},
{
"id": "c4e951f8-75b7-4c35-8663-2ec94dfd1f87",
"name": "OpenAI GPT-4 Mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1944,
1168
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4o Mini"
},
"options": {
"maxTokens": 4096
},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "be586407-249a-4843-a02b-aa7e120010d9",
"name": "Interrupt on Invalid URL",
"type": "n8n-nodes-base.stopAndError",
"position": [
976,
1232
],
"parameters": {
"errorMessage": "Input value for doc_url is not a url."
},
"typeVersion": 1
},
{
"id": "c81573f7-2c8c-4f90-b440-bed570249b73",
"name": "Set URL Components",
"type": "n8n-nodes-base.set",
"position": [
976,
1040
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a734fa97-0bca-485b-8ce3-ae328c3d0e8d",
"name": "server",
"type": "string",
"value": "={{ $json.body['x-doc-url'].extractDomain() }}"
},
{
"id": "b2d29825-7452-4657-aed2-da4413f72cb7",
"name": "scheme",
"type": "string",
"value": "={{ $json.body['x-doc-url'].split(':')[0] }}"
},
{
"id": "853b2b68-2389-4a31-82c9-a95ad9a51f4e",
"name": "documentId",
"type": "string",
"value": "={{ (() => {\nconst path = $json.body['x-doc-url'].extractUrlPath().split('/');\nconst id = path[path.length - 2];\nreturn id;\n})() }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "9890ada3-e94a-462a-bead-4a9639b61701",
"name": "Check URL Validity",
"type": "n8n-nodes-base.if",
"position": [
752,
1136
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "187466b4-2c51-40ca-bb84-b53209fa24a8",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.body['x-doc-url'].isUrl() }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.3
},
{
"id": "07ecb804-889a-4f81-b687-048a4a5e0c29",
"name": "Fetch Removal Tag ID",
"type": "n8n-nodes-base.httpRequest",
"position": [
2224,
944
],
"parameters": {
"url": "={{ $('Set URL Components').first().json.scheme }}://{{ $('Set URL Components').first().json.server }}/api/tags/?name__iexact={{ $('When Title Update Requested').item.json.body['x-tag-to-remove'] }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpBasicAuth"
},
"credentials": {
"httpBasicAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.4
},
{
"id": "5b685cba-fc5a-4d95-8a86-c39f9806f4a1",
"name": "Execute Tag Removal",
"type": "n8n-nodes-base.code",
"position": [
2448,
944
],
"parameters": {
"jsCode": "// Using ?. to safely navigate and ?? to provide a default empty array\nconst tagIdToRemove = $('Fetch Removal Tag ID').first()?.json?.results?.[0]?.id;\nconst currentTags = $('Fetch Document Content').first()?.json?.body?.tags ?? [];\n\n// If tagIdToRemove is undefined, the filter simply returns the full currentTags array\nconst updatedTags = currentTags.filter(id => id !== tagIdToRemove);\n\nreturn {\n updatedTags: updatedTags\n};"
},
"typeVersion": 2
},
{
"id": "4b6ca323-c425-4f11-8cc9-17b67c26bb8e",
"name": "Terminate Process",
"type": "n8n-nodes-base.noOp",
"position": [
1648,
1136
],
"parameters": {},
"typeVersion": 1
},
{
"id": "4001cfee-0f64-4485-9482-b3676d6e31ab",
"name": "Apply Document Updates",
"type": "n8n-nodes-base.httpRequest",
"position": [
2672,
944
],
"parameters": {
"url": "={{ $('Set URL Components').first().json.scheme }}://{{ $('Set URL Components').first().json.server }}/api/documents/{{ $('Set URL Components').last().json.documentId }}/",
"method": "PATCH",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "title",
"value": "={{ $('Generate Title AI Agent').first().json.output }}"
},
{
"name": "tags",
"value": "={{ $json.updatedTags }}"
}
]
},
"genericAuthType": "httpBasicAuth"
},
"credentials": {
"httpBasicAuth": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"typeVersion": 4.3
},
{
"id": "a5c92cd2-7a5f-43c0-a7eb-dc3361fa2726",
"name": "If Document Content Exists",
"type": "n8n-nodes-base.if",
"position": [
1424,
1040
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "5fbec441-1f29-4e12-8cc1-c2a48e814e2c",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.body.content }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.3
},
{
"id": "ce5ef9c8-ae58-478b-8e8d-9905321ad780",
"name": "When Title Update Requested",
"type": "n8n-nodes-base.webhook",
"position": [
528,
1136
],
"parameters": {
"path": "update-document-title",
"options": {},
"httpMethod": "POST",
"authentication": "headerAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
}
],
"active": true,
"settings": {
"binaryMode": "separate",
"callerPolicy": "workflowsFromSameOwner",
"availableInMCP": false,
"executionOrder": "v1"
},
"versionId": "aea605f3-fc39-48ca-948d-159ec0695e03",
"connections": {
"OpenAI GPT-4 Mini": {
"ai_languageModel": [
[
{
"node": "Generate Title AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Check URL Validity": {
"main": [
[
{
"node": "Set URL Components",
"type": "main",
"index": 0
}
],
[
{
"node": "Interrupt on Invalid URL",
"type": "main",
"index": 0
}
]
]
},
"Set URL Components": {
"main": [
[
{
"node": "Fetch Document Content",
"type": "main",
"index": 0
}
]
]
},
"Execute Tag Removal": {
"main": [
[
{
"node": "Apply Document Updates",
"type": "main",
"index": 0
}
]
]
},
"Fetch Removal Tag ID": {
"main": [
[
{
"node": "Execute Tag Removal",
"type": "main",
"index": 0
}
]
]
},
"Fetch Document Content": {
"main": [
[
{
"node": "If Document Content Exists",
"type": "main",
"index": 0
}
]
]
},
"Generate Title AI Agent": {
"main": [
[
{
"node": "Fetch Removal Tag ID",
"type": "main",
"index": 0
}
]
]
},
"Apply Document Guardrails": {
"main": [
[
{
"node": "Generate Title AI Agent",
"type": "main",
"index": 0
}
]
]
},
"If Document Content Exists": {
"main": [
[
{
"node": "Apply Document Guardrails",
"type": "main",
"index": 0
}
],
[
{
"node": "Terminate Process",
"type": "main",
"index": 0
}
]
]
},
"When Title Update Requested": {
"main": [
[
{
"node": "Check URL Validity",
"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.
httpBasicAuthhttpHeaderAuthopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This template automatically generates a professional, structured title for newly-ingested Paperless-ngx documents using AI (OpenAI GPT), then removes a processing tag to mark the document as handled. A webhook fires when a document needs titling (e.g., from a Paperless…
Source: https://n8n.io/workflows/14381/ — 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.
|Overview |Sample| |-|-| |This template is the first of its kind: it automatically generates both the caption and the image for your Instagram posts by analysing your existing feed, with zero spreadsh
Airtable, HTTP Request, Agent +4
Recup_CV. Uses httpRequest, agent, lmChatOpenAi, stopAndError. Webhook trigger; 43 nodes.
HTTP Request, Agent, OpenAI Chat +3
This workflow is designed for professionals, companies, and agencies that want to automate competitive analysis based on public reviews and opinions found on the Internet. It is especially useful for:
Agent, OpenAI Chat, OpenAI +4
f1_bot_zoom. Uses stopAndError, httpRequest, emailSend, agent. Webhook trigger; 39 nodes.
Stop And Error, HTTP Request, Email Send +3
This workflow receives inbound WhatsApp messages via Whapi, screens them with OpenAI-powered guardrails, and replies using an OpenAI support agent that can search a Notion knowledge base, look up live
Guardrails, OpenAI Chat, Agent +6