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": "SearxNG Research Workflow",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "research",
"responseMode": "responseNode",
"options": {}
},
"id": "a1a1a1a1-1111-1111-1111-111111111111",
"name": "Research Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1,
"position": [
240,
300
]
},
{
"parameters": {
"url": "http://searxng:8080/search",
"authentication": "none",
"httpMethod": "GET",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "q",
"value": "={{ $json.query || $json.search || 'artificial intelligence' }}"
},
{
"name": "format",
"value": "json"
},
{
"name": "categories",
"value": "={{ $json.categories || 'general' }}"
},
{
"name": "engines",
"value": "={{ $json.engines || '' }}"
},
{
"name": "pageno",
"value": "={{ $json.page || '1' }}"
},
{
"name": "time_range",
"value": "={{ $json.time_range || '' }}"
}
]
},
"options": {
"timeout": 15000
}
},
"id": "a1a1a1a1-2222-2222-2222-222222222222",
"name": "Search SearxNG",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
460,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "SELECT name FROM public.llms WHERE provider = 'ollama' AND active = true AND content > 0 ORDER BY created_at DESC LIMIT 1",
"options": {}
},
"id": "a1a1a1a1-3333-3333-3333-333333333333",
"name": "Get AI Model for Summary",
"type": "n8n-nodes-base.postgres",
"typeVersion": 1,
"position": [
680,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Extract and format search results for AI summarization\nconst searchData = $input.first().json;\nconst results = searchData.results || [];\n\n// Format results for AI processing\nconst formattedResults = results.slice(0, 5).map((result, index) => {\n return `${index + 1}. **${result.title}**\\n URL: ${result.url}\\n Content: ${result.content || result.description || 'No description available'}\\n`;\n}).join('\\n');\n\nconst searchQuery = $('Research Webhook').first().json.query || $('Research Webhook').first().json.search;\n\nconst promptText = `Please analyze and summarize these search results for the query: \"${searchQuery}\"\\n\\nSearch Results:\\n${formattedResults}\\n\\nPlease provide:\\n1. A concise summary of the key findings\\n2. The most relevant insights\\n3. Any notable trends or patterns\\n4. Credible sources mentioned`;\n\nreturn {\n search_query: searchQuery,\n total_results: searchData.number_of_results || results.length,\n results_count: results.length,\n raw_results: results,\n formatted_prompt: promptText\n};"
},
"id": "a1a1a1a1-4444-4444-4444-444444444444",
"name": "Format Results for AI",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
300
]
},
{
"parameters": {
"url": "={{ $env.LITELLM_BASE_URL }}/v1/chat/completions",
"authentication": "none",
"httpMethod": "POST",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "Authorization",
"value": "=Bearer {{ $env.LITELLM_API_KEY }}"
}
]
},
"sendBody": true,
"bodyContentType": "json",
"jsonParameters": true,
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "=ollama/{{ $node['Get AI Model for Summary'].json[0].name }}"
},
{
"name": "messages",
"value": "=[{\"role\":\"user\",\"content\": {{ JSON.stringify($json.formatted_prompt) }} }]"
},
{
"name": "stream",
"value": false
},
{
"name": "temperature",
"value": 0.3
},
{
"name": "max_tokens",
"value": 1000
}
]
},
"options": {
"timeout": 90000
}
},
"id": "a1a1a1a1-5555-5555-5555-555555555555",
"name": "Generate AI Summary",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
1120,
300
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ {\n \"search_query\": $node['Format Results for AI'].json.search_query,\n \"total_results_found\": $node['Format Results for AI'].json.total_results,\n \"results_analyzed\": $node['Format Results for AI'].json.results_count,\n \"ai_summary\": ($json.choices && $json.choices[0] && $json.choices[0].message && $json.choices[0].message.content) || $json.response,\n \"model_used\": $node['Get AI Model for Summary'].json[0].name,\n \"raw_search_results\": $node['Format Results for AI'].json.raw_results.slice(0, 3),\n \"success\": true,\n \"timestamp\": new Date().toISOString()\n} }}"
},
"id": "a1a1a1a1-6666-6666-6666-666666666666",
"name": "Return Research Summary",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1340,
300
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ {\n \"error\": \"Research workflow failed\",\n \"details\": $json.error || \"Unknown error\",\n \"success\": false,\n \"timestamp\": new Date().toISOString()\n} }}"
},
"id": "a1a1a1a1-7777-7777-7777-777777777777",
"name": "Error Response",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1340,
480
]
}
],
"connections": {
"Research Webhook": {
"main": [
[
{
"node": "Search SearxNG",
"type": "main",
"index": 0
}
]
]
},
"Search SearxNG": {
"main": [
[
{
"node": "Get AI Model for Summary",
"type": "main",
"index": 0
}
]
]
},
"Get AI Model for Summary": {
"main": [
[
{
"node": "Format Results for AI",
"type": "main",
"index": 0
}
]
]
},
"Format Results for AI": {
"main": [
[
{
"node": "Generate AI Summary",
"type": "main",
"index": 0
}
]
]
},
"Generate AI Summary": {
"main": [
[
{
"node": "Return Research Summary",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {},
"versionId": "1",
"id": "searxng-research-workflow",
"meta": {
"templateCredsSetupCompleted": true
},
"tags": [
"searxng",
"research",
"ai",
"ollama",
"automation"
]
}
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
SearxNG Research Workflow. Uses httpRequest, postgres. Webhook trigger; 7 nodes.
Source: https://github.com/thekaveh/genai-vanilla/blob/main/services/n8n/init/config/searxng-research-workflow.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.
CMM. Uses httpRequest, postgres, redis. Webhook trigger; 90 nodes.
HTTP Request, Postgres, Redis
Scraping. Uses httpRequest, postgres, @apify/n8n-nodes-apify, respondToWebhook. Webhook trigger; 61 nodes.
HTTP Request, Postgres, @Apify/N8N Nodes Apify
Workflow B — AI Listing Engine. Uses httpRequest, postgres, errorTrigger. Webhook trigger; 47 nodes.
HTTP Request, Postgres, Error Trigger
LogSentinel Workflow. Uses postgres, emailSend, httpRequest. Webhook trigger; 44 nodes.
Postgres, Email Send, HTTP Request
Pawa VAPI Tools v2 (live-schema). Uses postgres, httpRequest. Webhook trigger; 36 nodes.
Postgres, HTTP Request