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": "Chatbot-Query-Qdrant",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "chatbot-rag",
"options": {}
},
"id": "webhook-trigger",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 1,
"position": [
200,
300
]
},
{
"parameters": {
"method": "POST",
"url": "=http://ollama:11434/api/embeddings",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "nomic-embed-text"
},
{
"name": "prompt",
"value": "={{ $json.body.pregunta || $json.body.question }}"
}
]
},
"options": {}
},
"id": "query-embedding",
"name": "Query Embedding",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
450,
300
]
},
{
"parameters": {
"method": "POST",
"url": "http://qdrant:6333/collections/reglamento_taekwondo/points/search",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"vector\": {{ JSON.stringify($json.embedding) }},\n \"limit\": 3,\n \"with_payload\": true\n}",
"options": {}
},
"id": "qdrant-search",
"name": "Qdrant Search",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
700,
300
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "context-val",
"name": "context",
"value": "={{ $json.result.map(r => r.payload.text).join('\\n---\\n') }}",
"type": "string"
},
{
"id": "question-val",
"name": "question",
"value": "={{ $('Webhook').item.json.body.pregunta || $('Webhook').item.json.body.question }}",
"type": "string"
}
]
},
"options": {}
},
"id": "format-context",
"name": "Format Context",
"type": "n8n-nodes-base.set",
"typeVersion": 3.2,
"position": [
950,
300
]
},
{
"parameters": {
"method": "POST",
"url": "http://ollama:11434/api/generate",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "smollm2:1.7b"
},
{
"name": "prompt",
"value": "=Eres un asistente experto en el reglamento de Taekwondo. Responde a la pregunta bas\u00e1ndote \u00fanicamente en el contexto proporcionado.\n\nContexto:\n{{ $json.context }}\n\nPregunta: {{ $json.question }}\n\nRespuesta corta y precisa:"
},
{
"name": "stream",
"value": "false"
}
]
},
"options": {}
},
"id": "ollama-generate",
"name": "Ollama Generate",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
1200,
300
]
},
{
"parameters": {
"operation": "executeQuery",
"query": "=INSERT INTO consultas_rag (pregunta, respuesta, documentos_usados) VALUES ('{{ $('Webhook').item.json.body.pregunta || $('Webhook').item.json.body.question }}', '{{ $json.response }}', ARRAY['reglamento_taekwondo']);",
"options": {}
},
"id": "postgres-save",
"name": "PostgreSQL Save",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.2,
"position": [
1450,
300
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"id": "respond-to-webhook",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1700,
300
]
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "Query Embedding",
"type": "main",
"index": 0
}
]
]
},
"Query Embedding": {
"main": [
[
{
"node": "Qdrant Search",
"type": "main",
"index": 0
}
]
]
},
"Qdrant Search": {
"main": [
[
{
"node": "Format Context",
"type": "main",
"index": 0
}
]
]
},
"Format Context": {
"main": [
[
{
"node": "Ollama Generate",
"type": "main",
"index": 0
}
]
]
},
"Ollama Generate": {
"main": [
[
{
"node": "PostgreSQL Save",
"type": "main",
"index": 0
}
]
]
},
"PostgreSQL Save": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
}
}
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
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Chatbot-Query-Qdrant. Uses httpRequest, postgres. Webhook trigger; 7 nodes.
Source: https://github.com/Diana27106/tfg-taekwondo/blob/68e897cda1e408b67ddc4261ce4854b6e9229820/n8n-workflows/query-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.
Camila IA. Uses postgres, crypto, redis, agent. Webhook trigger; 92 nodes.
This workflow automates business intelligence reporting by aggregating data from multiple sources, processing it through AI models, and delivering formatted dashboards via email. Designed for business
RAG Ingestion Pipeline. Uses textSplitterRecursiveCharacterTextSplitter, httpRequest, postgres. Webhook trigger; 5 nodes.
Hi! I’m Amanda, a creator of intelligent automations using n8n and Make. I’ve been building AI-powered workflows for over 2 years, always focused on usability and innovation. This one here is very spe
This simple philosophy changes the way we think about automated sales agents. Context changes everything. In this 4-part workflow, we start by creating a knowledge base that will act as context across