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": "W13 - Academic Paper Finder & Citation Generator",
"nodes": [
{
"parameters": {
"content": "## \ud83c\udf93 Academic Paper Finder & Citation Generator\n\n### What this workflow does\n1. Checks Google Sheet for queries with Status = \"Pending\"\n2. Searches Semantic Scholar, PubMed, and ArXiv\n3. Ranks results by citation count\n4. Generates APA and BibTeX citations\n5. Updates row with results and Status = \"Completed\"\n\n### Setup steps\n1. Get PDF Vector API key from pdfvector.com/api-keys\n2. Create Google Sheet with columns:\n Search Query, Status, Results Found, Top Papers, Total Citations, Most Cited, APA Citations, BibTeX Citations, Search Date\n3. Connect Google Sheets credential in both Read Queries and Update Results nodes\n4. Update your Spreadsheet ID in both nodes\n5. Connect PDF Vector credential in the Search Papers node\n\n### How to use\n1. Add your search topic to column A (Search Query)\n2. Type **Pending** in column B (Status)\n3. The workflow runs every minute automatically\n4. Status changes to **Completed** when results are ready\n5. To re-search the same query: change Status back to **Pending**\n\n### \u26a0\ufe0f Important Note\nThe workflow automatically filters for Status = \"Pending\" rows via the **Status = Pending?** filter node \u2014 you do NOT need to configure any filter in the Read Queries Sheets node. It works out of the box.\n\n### Perfect for\n- Researchers doing literature reviews\n- PhD students finding related work\n- Academic writers needing citations",
"height": 580,
"width": 360,
"color": 5
},
"id": "e4605613-39cf-43e9-9093-0b4f40d11cc7",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2160,
976
]
},
{
"parameters": {
"content": "## \ud83d\udcda Databases Searched\n\n- Semantic Scholar\n- PubMed (medical/life sciences)\n- ArXiv (physics, math, CS)\n\nTop 10 most-cited papers returned",
"height": 180,
"width": 220
},
"id": "d6036ed2-d607-421c-b6c0-97ef0230f93d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2768,
976
]
},
{
"parameters": {
"content": "## \ud83d\udcdd Status Values\n\n- Pending = Will be searched\n- Completed = Done\n- (empty) = Ignored\n\nChange to \"Pending\" to re-run",
"height": 180,
"width": 220
},
"id": "cc9ebec3-861b-45a4-9cee-317a72c0a90f",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
3008,
976
]
},
{
"parameters": {
"rule": {
"interval": [
{
"field": "minutes",
"minutesInterval": 1
}
]
}
},
"id": "faa1092c-f6aa-4e0c-b9e1-7e7db5bbd0ac",
"name": "Every Minute",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
2512,
1264
]
},
{
"parameters": {
"documentId": {
"__rl": true,
"value": "YOUR_SPREADSHEET_ID",
"mode": "list"
},
"sheetName": {
"__rl": true,
"value": "gid=0",
"mode": "list"
},
"options": {},
"filtersUI": {
"values": [
{
"lookupColumn": "Status",
"lookupValue": "Pending"
}
]
}
},
"id": "de349380-5ee3-49fc-9754-fa77a702230f",
"name": "Read Queries",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
2704,
1264
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 1
},
"conditions": [
{
"id": "condition-pending",
"leftValue": "={{ $json.Status }}",
"rightValue": "Pending",
"operator": {
"type": "string",
"operation": "equals"
}
},
{
"id": "condition-query",
"leftValue": "={{ $json['Search Query'] }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "notEmpty"
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "90f46c8e-e291-475d-ad26-47bd2571e2b9",
"name": "Status = Pending?",
"type": "n8n-nodes-base.filter",
"typeVersion": 2,
"position": [
2912,
1264
]
},
{
"parameters": {
"resource": "academic",
"query": "={{ $json['Search Query'] }}",
"providers": [
"semantic-scholar",
"pubmed",
"arxiv"
],
"limit": 20,
"yearFrom": 1900,
"yearTo": 2050
},
"id": "79e06e72-e80f-4bf7-a6b5-ec2a313b5149",
"name": "PDF Vector - Search Papers",
"type": "n8n-nodes-pdfvector.pdfVector",
"typeVersion": 2,
"position": [
3104,
1264
],
"credentials": {
"pdfVectorApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const results = $input.item.json.results || [];\nconst query = $('Status = Pending?').item.json['Search Query'] || 'Unknown';\n\n// Sort by citations (descending)\nconst sortedResults = results.sort((a, b) => (b.citationCount || 0) - (a.citationCount || 0));\n\n// Take top 10 most cited\nconst topPapers = sortedResults.slice(0, 10);\n\n// Generate formatted lists\nconst apaCitations = [];\nconst bibtexCitations = [];\nconst paperList = [];\n\ntopPapers.forEach((paper, index) => {\n const authors = paper.authors ? paper.authors.map(a => a.name).join(', ') : 'Unknown';\n const firstAuthor = paper.authors && paper.authors[0] ? paper.authors[0].name.split(' ').pop() : 'Unknown';\n const year = paper.year || 'n.d.';\n const title = paper.title || 'Untitled';\n const venue = paper.venue || paper.journal || 'N/A';\n const citations = paper.citationCount || 0;\n \n // Paper list entry\n paperList.push(`${index + 1}. ${title} (${year}) - ${citations} citations`);\n \n // APA format\n const apa = `${authors} (${year}). ${title}. ${venue}${paper.doi ? `. https://doi.org/${paper.doi}` : ''}`;\n apaCitations.push(apa);\n \n // BibTeX format\n const bibtexKey = `${firstAuthor.toLowerCase().replace(/[^a-z]/g, '')}${year}${title.split(' ')[0].toLowerCase().replace(/[^a-z]/g, '')}`;\n const bibtex = `@article{${bibtexKey},\\n title={${title}},\\n author={${authors}},\\n year={${year}},\\n journal={${venue}}${paper.doi ? `,\\n doi={${paper.doi}}` : ''}\\n}`;\n bibtexCitations.push(bibtex);\n});\n\n// Summary stats\nconst totalCitations = topPapers.reduce((sum, p) => sum + (p.citationCount || 0), 0);\n\nreturn {\n json: {\n query: query,\n totalResults: results.length,\n topPapersList: paperList.join('\\n'),\n totalCitations: totalCitations,\n mostCited: topPapers[0] ? `${topPapers[0].title} (${topPapers[0].citationCount} citations)` : 'N/A',\n apaCitations: apaCitations.join('\\n\\n'),\n bibtexCitations: bibtexCitations.join('\\n\\n'),\n searchDate: new Date().toISOString().split('T')[0]\n }\n};"
},
"id": "e69ff6f1-9595-4da0-93e0-e795d89118c7",
"name": "Process & Format Results",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
3312,
1264
]
},
{
"parameters": {
"operation": "update",
"documentId": {
"__rl": true,
"value": "YOUR_SPREADSHEET_ID",
"mode": "list"
},
"sheetName": {
"__rl": true,
"value": "gid=0",
"mode": "list"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"Search Query": "={{ $json.query }}",
"Status": "=Completed",
"Results Found": "={{ $json.totalResults }}",
"Top Papers": "={{ $json.topPapersList }}",
"Total Citations": "={{ $json.totalCitations }}",
"Most Cited": "={{ $json.mostCited }}",
"APA Citations": "={{ $json.apaCitations }}",
"BibTeX Citations": "={{ $json.bibtexCitations }}",
"Search Date": "={{ $json.searchDate }}",
"row_number": 0
},
"matchingColumns": [
"Search Query"
],
"schema": [
{
"id": "Search Query",
"displayName": "Search Query",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Status",
"displayName": "Status",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Results Found",
"displayName": "Results Found",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Top Papers",
"displayName": "Top Papers",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Total Citations",
"displayName": "Total Citations",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Most Cited",
"displayName": "Most Cited",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "APA Citations",
"displayName": "APA Citations",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "BibTeX Citations",
"displayName": "BibTeX Citations",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Search Date",
"displayName": "Search Date",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "row_number",
"displayName": "row_number",
"required": false,
"defaultMatch": false,
"display": true,
"type": "number",
"canBeUsedToMatch": true,
"readOnly": true,
"removed": false
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"id": "ff0b5982-f5c8-4870-8ebd-16c20ced93e6",
"name": "Update Results",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
3504,
1264
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Every Minute": {
"main": [
[
{
"node": "Read Queries",
"type": "main",
"index": 0
}
]
]
},
"Read Queries": {
"main": [
[
{
"node": "Status = Pending?",
"type": "main",
"index": 0
}
]
]
},
"Status = Pending?": {
"main": [
[
{
"node": "PDF Vector - Search Papers",
"type": "main",
"index": 0
}
]
]
},
"PDF Vector - Search Papers": {
"main": [
[
{
"node": "Process & Format Results",
"type": "main",
"index": 0
}
]
]
},
"Process & Format Results": {
"main": [
[
{
"node": "Update Results",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate"
},
"meta": {
"templateCredsSetupCompleted": false
},
"tags": [
{
"name": "PDF Vector"
},
{
"name": "Academic"
},
{
"name": "Research"
},
{
"name": "Citations"
}
]
}
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.
googleSheetsOAuth2ApipdfVectorApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
W13 - Academic Paper Finder & Citation Generator. Uses googleSheets, n8n-nodes-pdfvector. Scheduled trigger; 9 nodes.
Source: https://github.com/khanhduyvt0101/workflows/blob/0153ee2efc0f692c931b9bb4c2a04abf11756822/n8n-workflows/academic-paper-finder.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.
Free Support: Setting up and getting the workflow tailord to your needs. One small free adjustment included.
HTTP Request, Google Cloud Storage, YouTube +2
This workflow aims to help you and your team track your expenses with OpenAI It automatically collects your OpenAI organization’s API usage and cost data every few days and saves it to a ready-to-use
HTTP Request, Google Sheets
Automatically fetch, rank, and summarize the top financial stories from curated RSS feeds each day, then deliver a concise AI-written digest to Telegram and log the run to Google Sheets. Runs on a dai
Google Sheets, HTTP Request, RSS Feed Read
Founder's Discovery Engine. Uses googleSheets, googleDrive, httpRequest, gmail. Scheduled trigger; 18 nodes.
Google Sheets, Google Drive, HTTP Request +1
Sales managers and team leads who use Zoom Phone for outbound calls and want automated performance tracking without manually reviewing every recording. A schedule trigger runs periodically and fetches
HTTP Request, Google Drive, Google Sheets