This workflow follows the Chainllm → HTTP Request 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": "ShopAnalyticsVersionFinal",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 6 * * *"
}
]
}
},
"id": "46733ac4-4db2-445e-aa87-f2110e704624",
"name": "D\u00e9clencheur 6h00",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.1,
"position": [
-1328,
144
]
},
{
"parameters": {
"jsCode": "await new Promise(r => setTimeout(r, 500));\nreturn [{\n json: {\n status: 'trained',\n model_version: '1.0.0',\n trained_at: new Date().toISOString(),\n samples_used: 142\n }\n}];"
},
"id": "37109df6-9a9d-4d4a-8d93-e36663a8de61",
"name": "R\u00e9entra\u00eenement Mod\u00e8le ML",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-1104,
144
],
"notes": "\u26a0\ufe0f MOCK \u2014 Remplacer par HTTP Request POST /api/train"
},
{
"parameters": {
"jsCode": "const profiles = ['Familles', 'Jeunes adultes', 'Seniors', 'Professionnels'];\nconst niveaux = ['Faible', 'Mod\u00e9r\u00e9', '\u00c9lev\u00e9', 'Tr\u00e8s \u00e9lev\u00e9'];\nconst visiteurs = Math.floor(Math.random() * 300) + 350;\n\nreturn [{\n json: {\n visiteurs_prevus: visiteurs,\n profil_dominant: profiles[Math.floor(Math.random() * profiles.length)],\n niveau_affluence: niveaux[Math.floor(Math.random() * niveaux.length)],\n heure_pointe_debut: '14:00',\n heure_pointe_fin: '18:00',\n date_prevision: new Date().toISOString().split('T')[0]\n }\n}];"
},
"id": "6065d42e-a37c-4c97-a035-004dc66eed62",
"name": "Pr\u00e9diction Visiteurs",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-880,
144
],
"notes": "\u26a0\ufe0f MOCK \u2014 Remplacer par HTTP Request POST /api/predict"
},
{
"parameters": {
"jsCode": "const data = $input.first().json;\n\nconst prompt = `Tu es l assistant analytique de ShopAnalytics pour Anavid Store 360. Voici les predictions de frequentation pour aujourd hui (${data.date_prevision}) : Visiteurs prevus : ${data.visiteurs_prevus}. Profil dominant : ${data.profil_dominant}. Niveau d affluence : ${data.niveau_affluence}. Heure de pointe : ${data.heure_pointe_debut} a ${data.heure_pointe_fin}. Redige un message professionnel et concis de 4 a 5 phrases en francais a destination de l equipe du magasin. Mentionne le nombre de visiteurs, le profil dominant, le niveau d affluence et donne 1 a 2 recommandations concretes sur la gestion du personnel ou des caisses.`;\n\nreturn [{\n json: {\n prompt: prompt,\n prediction: data\n }\n}];"
},
"id": "fc7c823d-2696-45f3-a1be-5854df761833",
"name": "Pr\u00e9parer Prompt Ollama",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-656,
144
]
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('Pr\u00e9parer Prompt Ollama').item.json.prompt }}"
},
"id": "5c36f2f4-3aa3-46bb-9eab-71f015d03fa2",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.4,
"position": [
-432,
144
]
},
{
"parameters": {
"model": "=llama3.2:3b-instruct-q4_K_M",
"options": {
"temperature": 0.1,
"numCtx": 4096,
"numPredict": 300
}
},
"id": "41ebc6ab-d1fc-4907-8965-6e56cc2a83d7",
"name": "Ollama Model",
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"typeVersion": 1,
"position": [
-352,
368
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Formate le payload attendu par Django SSE (receive_daily_report)\n// et par le Dashboard.tsx (PredictionData interface)\nconst llmText = $input.first().json.text?.trim();\nconst pred = $('Pr\u00e9parer Prompt Ollama').first().json.prediction;\n\nconst payload = {\n type: 'llm_report',\n date: pred.date_prevision,\n generated_at: new Date().toISOString(),\n message: llmText,\n prediction: {\n visiteurs_prevus: pred.visiteurs_prevus,\n profil_dominant: pred.profil_dominant,\n niveau_affluence: pred.niveau_affluence,\n heure_pointe: `${pred.heure_pointe_debut} - ${pred.heure_pointe_fin}`\n }\n};\n\nreturn [{ json: payload }];"
},
"id": "08b12b16-2b6b-42b5-a2af-4e32a65ef770",
"name": "Formater Payload SSE",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-80,
144
],
"notes": "Formate exactement le PredictionData attendu par Dashboard.tsx et Django SSE"
},
{
"parameters": {
"method": "POST",
"url": "http://shopanalytics-django-api:8000/api/daily-report/",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify($json) }}",
"options": {
"timeout": 10000
}
},
"id": "c28cff01-6ec5-4a9e-b5dc-088d20cf6e5c",
"name": "Push SSE \u2192 Django",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
144,
-48
],
"notes": "POST /api/daily-report/ \u2192 Django notifie tous les clients SSE connect\u00e9s (Dashboard + ChatIA)"
},
{
"parameters": {
"jsCode": "// Appel HTTP via $http natif de N8N (fetch et http sont bloqu\u00e9s)\nconst llmText = $input.first().json.text?.trim();\nconst prediction = $('Pr\u00e9parer Prompt Ollama').first().json.prediction;\n\nlet chatAnswer = llmText;\n\ntry {\n const response = await $http.request({\n method: 'POST',\n url: 'http://django_api:8000/api/chat/',\n headers: { 'Content-Type': 'application/json' },\n body: {\n question: `Rapport quotidien automatique du ${prediction.date_prevision} : ${llmText}`\n },\n json: true\n });\n chatAnswer = response.answer || llmText;\n} catch (err) {\n console.log('Django indisponible, fallback LLM : ' + err.message);\n}\n\nconst notification = {\n id: Date.now(),\n date: prediction.date_prevision,\n generated_at: new Date().toISOString(),\n visiteurs_prevus: prediction.visiteurs_prevus,\n profil_dominant: prediction.profil_dominant,\n niveau_affluence: prediction.niveau_affluence,\n heure_pointe: `${prediction.heure_pointe_debut} - ${prediction.heure_pointe_fin}`,\n message: chatAnswer,\n model: 'llama3.2:3b-instruct-q4_K_M',\n type: 'daily_report'\n};\n\nreturn [{ json: notification }];"
},
"id": "6835e565-0baa-423b-828b-aa34e521f783",
"name": "Envoyer au Chatbot",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
144,
336
],
"notes": "Envoie le message LLM au RAG Django \u2192 chatbot Ionic"
},
{
"parameters": {
"method": "POST",
"url": "http://shopanalytics-django-api:8000/api/send-fcm/",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "=json",
"bodyParameters": {
"parameters": [
{}
]
},
"jsonBody": "={{\n{\n title: \"\ud83d\udcca Rapport Quotidien - \" + $json.date,\n body: $json.message,\n data: {\n type: $json.type,\n date: $json.date,\n visiteurs_prevus: $json.prediction.visiteurs_prevus,\n profil_dominant: $json.prediction.profil_dominant,\n niveau_affluence: $json.prediction.niveau_affluence,\n heure_pointe: $json.prediction.heure_pointe\n }\n}\n}}",
"options": {
"timeout": 10000
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
144,
144
],
"id": "ae892a54-366b-44ed-806c-4b59a9330412",
"name": "Envoyer FCM"
}
],
"connections": {
"D\u00e9clencheur 6h00": {
"main": [
[
{
"node": "R\u00e9entra\u00eenement Mod\u00e8le ML",
"type": "main",
"index": 0
}
]
]
},
"R\u00e9entra\u00eenement Mod\u00e8le ML": {
"main": [
[
{
"node": "Pr\u00e9diction Visiteurs",
"type": "main",
"index": 0
}
]
]
},
"Pr\u00e9diction Visiteurs": {
"main": [
[
{
"node": "Pr\u00e9parer Prompt Ollama",
"type": "main",
"index": 0
}
]
]
},
"Pr\u00e9parer Prompt Ollama": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Ollama Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Formater Payload SSE",
"type": "main",
"index": 0
}
]
]
},
"Formater Payload SSE": {
"main": [
[
{
"node": "Envoyer au Chatbot",
"type": "main",
"index": 0
},
{
"node": "Envoyer FCM",
"type": "main",
"index": 0
},
{
"node": "Push SSE \u2192 Django",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "6a1669e0-7e1c-4cd9-a2ab-a0bcbe209008",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "haD6hCVYA8oVdIAB",
"tags": [
{
"updatedAt": "2026-06-17T22:52:38.300Z",
"createdAt": "2026-06-17T22:52:38.300Z",
"id": "8mEYfMeCjGpMZEBP",
"name": "ShopAnalytics"
},
{
"updatedAt": "2026-06-17T22:52:38.337Z",
"createdAt": "2026-06-17T22:52:38.337Z",
"id": "S9YsIgrS8BAcLO13",
"name": "Sprint1"
}
]
}
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.
ollamaApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
ShopAnalyticsVersionFinal. Uses chainLlm, lmOllama, httpRequest. Scheduled trigger; 10 nodes.
Source: https://github.com/ZeinebGhrab/smart-retail-platform/blob/384f03b09f45313338c2052f11454714f0430b96/backend/n8n/workflows/ShopAnalyticsVersionFinal.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.
This workflow automates fetching the latest post from a Blogspot RSS feed, summarizes it with an LLM (e.g., Gemma via Ollama), extracts and uploads an image, generates three relevant hashtags, and pos
N8N Nodes Postiz, RSS Feed Read, Chain Llm +3
Complete PostgreSQL-backed system: Keyword scoring → AI research → Multi-part content generation → fal.ai Nano Banana image generation → WordPress publishing
WordPress, OpenAI, Perplexity +8
Chanchito_PROD. Uses googleGemini, postgres, telegram, httpRequest. Scheduled trigger; 94 nodes.
Google Gemini, Postgres, Telegram +4
Automatically scan major financial newswires for biotech catalyst events, score them with AI sentiment analysis, and surface ranked trade candidates — all without manual monitoring.
RSS Feed Read, Data Table, HTTP Request +4
Cyber Zap Public. Uses httpRequest, chainLlm, outputParserStructured, telegram. Scheduled trigger; 69 nodes.
HTTP Request, Chain Llm, Output Parser Structured +6