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": "Chimera: AI Pipeline",
"nodes": [
{
"parameters": {
"context": "={{ $json.message }}",
"systemInstruction": "You are an intent classification and entity extraction system for a WhatsApp business bot.\n\nTASK: Analyze the user's message and return a structured JSON object.\n\nINTENT CATEGORIES:\n- greeting, order_status, product_inquiry, booking_request, support_request, payment_question, human_handoff, feedback, unsubscribe, unknown\n\nOUTPUT FORMAT:\n{\n \"intent\": \"string\",\n \"confidence\": 0.95,\n \"entities\": {\n \"order_id\": \"string|null\",\n \"product_name\": \"string|null\"\n },\n \"sentiment\": \"positive|neutral|negative\",\n \"urgency\": \"low|normal|high\"\n}",
"options": {
"responseMimeType": "application/json"
}
},
"id": "gemini-flash-node",
"name": "Gemini 2.0 Flash: Extraction",
"type": "n8n-nodes-base.googleGeminiChat",
"typeVersion": 1,
"position": [
400,
200
]
},
{
"parameters": {
"url": "https://api.x.ai/v1/chat/completions",
"method": "POST",
"authentication": "headerAuth",
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "grok-beta"
},
{
"name": "messages",
"value": "=[{\"role\": \"system\", \"content\": \"{{ $parameter.systemPrompt }}\"}, {\"role\": \"user\", \"content\": \"{{ $parameter.prompt }}\"}]"
}
]
}
},
"id": "grok-node",
"name": "Grok: Reasoning & Response",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4,
"position": [
650,
400
]
},
{
"parameters": {
"operation": "insert",
"table": "intent_log",
"columns": "message_id, primary_intent, confidence, entities, grok_response, gemini_response",
"values": "={{ $node[\"Execute AI Pipeline\"].json.messageId }}, {{ $node[\"Gemini 2.0 Flash: Extraction\"].json.intent }}, {{ $node[\"Gemini 2.0 Flash: Extraction\"].json.confidence }}, {{ JSON.stringify($node[\"Gemini 2.0 Flash: Extraction\"].json.entities) }}, {{ JSON.stringify($node[\"Grok: Reasoning & Response\"].json) }}, {{ JSON.stringify($node[\"Gemini 2.0 Flash: Extraction\"].json) }}"
},
"id": "db-log-node",
"name": "Postgres: Log Intent",
"type": "n8n-nodes-base.postgres",
"typeVersion": 1,
"position": [
900,
300
]
}
],
"connections": {
"Gemini 2.0 Flash: Extraction": {
"main": [
[
{
"node": "Grok: Reasoning & Response",
"type": "main",
"index": 0
}
]
]
},
"Grok: Reasoning & Response": {
"main": [
[
{
"node": "Postgres: Log Intent",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Chimera: AI Pipeline. Uses googleGeminiChat, httpRequest, postgres. Manual trigger; 3 nodes.
Source: https://github.com/Oracle69digitalmarketing/Chimera/blob/3e240c9bf4c1adbd299a205be7c3d4bd7cdf8a19/n8n-workflows/02-ai-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.
n8n Demo Workflow. Uses httpRequest, chatOpenAi. Manual trigger; 2 nodes.
Eu Clara – Funil Kiwify Completo. Uses postgres, openAi, httpRequest, gmail. Webhook trigger; 70 nodes.
Lua Nova - Sistema Completo. Uses postgres, httpRequest, openAi. Webhook trigger; 55 nodes.
User Signup & Verification: The workflow starts when a user signs up. It generates a verification code and sends it via SMS using Twilio. Code Validation: The user replies with the code. The workflow
A scheduled process aggregates content from eight distinct data sources and standardizes all inputs into a unified format. AI models perform sentiment scoring, detect conspiracy or misinformation sign