This workflow follows the HTTP Request → Postgres 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": "Research Pipeline Workflow",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "research/start",
"responseMode": "responseNode",
"options": {}
},
"id": "webhook-research-start",
"name": "Webhook - Start Research",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1,
"position": [
250,
300
]
},
{
"parameters": {
"mode": "multiplex"
},
"id": "split-topics",
"name": "Split Research Topics",
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
450,
300
]
},
{
"parameters": {
"url": "http://langchain_service:8001/agents/research",
"method": "POST",
"bodyParametersJson": "={\n \"query\": \"{{ $json.topic }}\",\n \"max_results\": 10,\n \"include_sentiment\": true\n}",
"options": {
"timeout": 90000
}
},
"id": "run-research-agent",
"name": "Run Research Agent",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
650,
300
]
},
{
"parameters": {
"url": "http://scrapy-service:8003/scrape/competitor",
"method": "POST",
"bodyParametersJson": "={\n \"competitor_id\": {{ $json.competitor_id }},\n \"start_url\": \"{{ $json.url }}\",\n \"max_depth\": 2,\n \"max_pages\": 50,\n \"content_types\": [\"blog_post\", \"pricing\", \"product\", \"page\"]\n}",
"options": {
"timeout": 120000
}
},
"id": "scrape-competitor",
"name": "Scrape Competitor Content",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
650,
450
]
},
{
"parameters": {
"url": "http://langchain_service:8001/tools/sentiment-analysis",
"method": "POST",
"bodyParametersJson": "={\n \"text\": \"{{ $json.content }}\",\n \"batch\": false\n}",
"options": {}
},
"id": "analyze-sentiment",
"name": "Analyze Sentiment",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
850,
300
]
},
{
"parameters": {
"url": "http://langchain_service:8001/tools/extract-entities",
"method": "POST",
"bodyParametersJson": "={\n \"text\": \"{{ $json.content }}\"\n}",
"options": {}
},
"id": "extract-entities",
"name": "Extract Named Entities",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
850,
450
]
},
{
"parameters": {
"url": "http://langchain_service:8001/tools/extract-topics",
"method": "POST",
"bodyParametersJson": "={\n \"text\": \"{{ $json.content }}\"\n}",
"options": {}
},
"id": "extract-topics",
"name": "Extract Topics",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
850,
600
]
},
{
"parameters": {
"jsCode": "// Aggregate all analysis results\nconst items = $input.all();\nconst researchData = items[0].json;\nconst sentimentData = items[1]?.json || {};\nconst entitiesData = items[2]?.json || {};\nconst topicsData = items[3]?.json || {};\n\nconst aggregated = {\n campaign_id: researchData.campaign_id,\n topic: researchData.topic,\n research_results: researchData.results,\n sentiment: {\n label: sentimentData.sentiment,\n confidence: sentimentData.confidence\n },\n entities: entitiesData.entities || {},\n topics: topicsData.topics || [],\n metadata: {\n researched_at: new Date().toISOString(),\n sources: researchData.sources || [],\n total_results: researchData.results?.length || 0\n }\n};\n\nreturn aggregated;"
},
"id": "aggregate-results",
"name": "Aggregate Research Results",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1050,
400
]
},
{
"parameters": {
"operation": "insert",
"table": "research_results",
"columns": "campaign_id, query, source, results, created_at",
"additionalFields": {}
},
"id": "store-research",
"name": "Store Research Results",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2,
"position": [
1250,
400
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "insert",
"table": "content_analysis",
"columns": "content_id, analysis_type, results, sentiment_score, topics, entities, created_at",
"additionalFields": {}
},
"id": "store-analysis",
"name": "Store Content Analysis",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2,
"position": [
1250,
550
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"url": "http://langchain_service:8001/storage/vector-embeddings/add",
"method": "POST",
"bodyParametersJson": "={\n \"collection_name\": \"research_content\",\n \"texts\": [\"{{ $json.content }}\"],\n \"metadatas\": [{\n \"campaign_id\": {{ $json.campaign_id }},\n \"topic\": \"{{ $json.topic }}\",\n \"sentiment\": \"{{ $json.sentiment.label }}\",\n \"source\": \"{{ $json.source }}\",\n \"created_at\": \"{{ $json.metadata.researched_at }}\"\n }]\n}",
"options": {}
},
"id": "store-embeddings",
"name": "Store Vector Embeddings",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
1450,
400
]
},
{
"parameters": {
"mode": "combine",
"combinationMode": "mergeByPosition",
"options": {}
},
"id": "merge-results",
"name": "Merge All Results",
"type": "n8n-nodes-base.merge",
"typeVersion": 2,
"position": [
1650,
400
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={\n \"success\": true,\n \"message\": \"Research pipeline completed\",\n \"campaign_id\": {{ $json.campaign_id }},\n \"topics_researched\": {{ $json.topics_count }},\n \"total_results\": {{ $json.total_results }},\n \"sentiment_analysis_completed\": true,\n \"entities_extracted\": true,\n \"topics_extracted\": true,\n \"embeddings_stored\": true,\n \"results_summary\": {\n \"positive_sentiment\": {{ $json.positive_count }},\n \"negative_sentiment\": {{ $json.negative_count }},\n \"neutral_sentiment\": {{ $json.neutral_count }},\n \"top_entities\": {{ $json.top_entities }},\n \"trending_topics\": {{ $json.trending_topics }}\n }\n}",
"options": {}
},
"id": "response-complete",
"name": "Respond Research Complete",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1850,
400
]
},
{
"parameters": {
"url": "http://langchain_service:8001/agents/trend",
"method": "POST",
"bodyParametersJson": "={\n \"topics\": {{ $json.all_topics }},\n \"time_range\": \"week\",\n \"min_score\": 0.5\n}",
"options": {
"timeout": 60000
}
},
"id": "detect-trends",
"name": "Detect Trending Topics",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
1450,
600
]
},
{
"parameters": {
"operation": "insert",
"table": "trends",
"columns": "topic, score, source, metadata, detected_at",
"mode": "insert",
"additionalFields": {}
},
"id": "store-trends",
"name": "Store Detected Trends",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2,
"position": [
1650,
600
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Webhook - Start Research": {
"main": [
[
{
"node": "Split Research Topics",
"type": "main",
"index": 0
}
]
]
},
"Split Research Topics": {
"main": [
[
{
"node": "Run Research Agent",
"type": "main",
"index": 0
},
{
"node": "Scrape Competitor Content",
"type": "main",
"index": 0
}
]
]
},
"Run Research Agent": {
"main": [
[
{
"node": "Analyze Sentiment",
"type": "main",
"index": 0
},
{
"node": "Extract Named Entities",
"type": "main",
"index": 0
},
{
"node": "Extract Topics",
"type": "main",
"index": 0
}
]
]
},
"Analyze Sentiment": {
"main": [
[
{
"node": "Aggregate Research Results",
"type": "main",
"index": 0
}
]
]
},
"Extract Named Entities": {
"main": [
[
{
"node": "Aggregate Research Results",
"type": "main",
"index": 0
}
]
]
},
"Extract Topics": {
"main": [
[
{
"node": "Aggregate Research Results",
"type": "main",
"index": 0
}
]
]
},
"Aggregate Research Results": {
"main": [
[
{
"node": "Store Research Results",
"type": "main",
"index": 0
},
{
"node": "Store Content Analysis",
"type": "main",
"index": 0
}
]
]
},
"Store Research Results": {
"main": [
[
{
"node": "Store Vector Embeddings",
"type": "main",
"index": 0
}
]
]
},
"Store Content Analysis": {
"main": [
[
{
"node": "Merge All Results",
"type": "main",
"index": 0
}
]
]
},
"Store Vector Embeddings": {
"main": [
[
{
"node": "Merge All Results",
"type": "main",
"index": 1
}
]
]
},
"Merge All Results": {
"main": [
[
{
"node": "Detect Trending Topics",
"type": "main",
"index": 0
},
{
"node": "Respond Research Complete",
"type": "main",
"index": 0
}
]
]
},
"Detect Trending Topics": {
"main": [
[
{
"node": "Store Detected Trends",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"staticData": null,
"tags": [],
"triggerCount": 1,
"updatedAt": "2024-01-15T00:00:00.000Z",
"versionId": "1"
}
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.
postgres
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Research Pipeline Workflow. Uses httpRequest, postgres. Webhook trigger; 15 nodes.
Source: https://github.com/Yaakovyitzchak1231/CLAUDE-CODE_Marketing-Agent/blob/a9f11690dfb44a4e0f520ab2cd1436f06b18c442/n8n-workflows/research_pipeline.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.
Jigsaw API key for image processing, I use this as a gatekeeper/second pair of eyes. LINK to their website https://jigsawstack.com/ SECOND A postgress DATABASE (I use Supabase) LlamaCloud for the pars
HTTP Request, Postgres, Stop And Error +2
W1 - IN WhatsApp Adapter (Secure + Fast ACK). Uses postgres, redis, httpRequest. Webhook trigger; 48 nodes.
Postgres, Redis, HTTP Request
W2 - IN Instagram Adapter (Secure). Uses postgres, httpRequest. Webhook trigger; 28 nodes.
Postgres, HTTP Request
W3 - IN Messenger Adapter (Secure). Uses postgres, httpRequest. Webhook trigger; 28 nodes.
Postgres, HTTP Request
Engagement Tracking Workflow. Uses postgres, httpRequest. Webhook trigger; 22 nodes.
Postgres, HTTP Request