Workflow de données analytiques pour boulangerie 4
Ceci est unMiscellaneous, AI RAG, Multimodal AIworkflow d'automatisation du domainecontenant 10 nœuds.Utilise principalement des nœuds comme Agent, GoogleSheetsTool, ChatTrigger, LmChatAzureOpenAi, MemoryBufferWindow. Analyser les ventes et l'inventaire d'une boulangerie avec Google Sheets et l'assistant de discussion Azure GPT
- •Informations d'identification Google Sheets API
- •Clé API OpenAI
Catégorie
{
"id": "3v8t7FV5f5vkU9LM",
"meta": {
"instanceId": "3caab7a077d6a24bf913833250143556c3033c05ff2ea30885e13d0164c0cec2",
"templateCredsSetupCompleted": true
},
"name": "Data analytics Workflow 4 bakery.",
"tags": [],
"nodes": [
{
"id": "e559ce26-07d1-4bca-aa53-082ff8480e63",
"name": "À la réception du message",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-384,
-192
],
"webhookId": "1d429d6b-8816-4023-88da-af4cc93a4f81",
"parameters": {
"options": {}
},
"typeVersion": 1.3
},
{
"id": "517129d9-18fc-4bf3-8193-8d8ed8fb8b1f",
"name": "Agent IA",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-112,
-192
],
"parameters": {
"options": {
"systemMessage": "You are a professional Data Analysis Assistant specialized in Excel datasets. \nYou never assume what the user wants — you only respond based on their exact question. \n\nBehavior & Tone:\n- Clear, concise, and professional.\n- Always answer in plain English, avoiding unnecessary jargon.\n- Use short, structured insights (bullets, small tables, or compact summaries).\n- Keep responses brief but meaningful — no long reports unless explicitly requested.\n- Provide actionable insights when appropriate, but do not invent analysis that was not asked.\n\nInstructions:\n1. Only analyze the Excel data when the user asks a specific question.\n2. Never output full raw data unless explicitly requested.\n3. Present results in a compact format (e.g., weekly breakdown, totals, highlights) if the question relates to time or quantities.\n4. If the data is insufficient, state the limitation clearly.\n5. Keep a balanced tone: informative, decision-oriented, and easy to understand.\n6. Never assume tasks — wait for user instructions before analyzing. \n7. If a recommendation is reasonable (like stocking, trends, or anomalies), keep it short and relevant to the user’s query.\n"
}
},
"typeVersion": 2.2
},
{
"id": "ed8f4fe1-272f-4657-ac41-36ffb7456bb1",
"name": "Simple Mémoire",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-16,
32
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "d1a293d6-7e5b-4543-9107-9caf45b4051a",
"name": "Retrieve bakery data",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
320,
-80
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 764145761,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1dCCQzjoDZak-mQD1iyGd5aHKGFeh15fsBPUIoTgAYGw/edit#gid=764145761",
"cachedResultName": "Full Month"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1dCCQzjoDZak-mQD1iyGd5aHKGFeh15fsBPUIoTgAYGw",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1dCCQzjoDZak-mQD1iyGd5aHKGFeh15fsBPUIoTgAYGw/edit?usp=drivesdk",
"cachedResultName": "Bakery data 1 month"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "2cLBwxQBfcaJ1DCN",
"name": "Google Sheets account"
}
},
"typeVersion": 4.7
},
{
"id": "1106cbea-591d-4dd4-88dd-03ad52052e38",
"name": "Azure Modèle de chat OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
"position": [
-400,
32
],
"parameters": {
"model": "gpt-5-mini",
"options": {}
},
"credentials": {
"azureOpenAiApi": {
"id": "eyXr9TTWzqXoS9oD",
"name": "Azure Open AI account"
}
},
"typeVersion": 1
},
{
"id": "dc450b50-9326-40a1-a25a-c044c459a1ff",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-464,
-512
],
"parameters": {
"width": 256,
"height": 496,
"content": "## Workflow: **Data Analytics for Bakery**\n\n### Node 1: **When chat message received**\n\n*Purpose:*\nThis node acts as the **entry point** of the workflow. It triggers the process whenever a user sends a **chat message**.\n\n"
},
"typeVersion": 1
},
{
"id": "982b0dd2-ac23-47d6-a91b-5df8d2d42527",
"name": "Note adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-192,
-512
],
"parameters": {
"color": 3,
"width": 336,
"height": 496,
"content": "### Node 2: **AI Agent**\n\n*Purpose:*\nThis is the **central AI reasoning engine**. It processes the user’s request, interprets the context, and decides how to handle it.\n\n*Key roles:*\n\n* Ensures **professional and concise** responses\n* Analyzes bakery Excel data only when asked\n* Provides insights in **plain English** with short, actionable summaries\n"
},
"typeVersion": 1
},
{
"id": "4fa77358-11a8-4c21-bdb2-c1f606773d17",
"name": "Note adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-128,
144
],
"parameters": {
"color": 2,
"width": 320,
"height": 272,
"content": "### Node 3: **Simple Memory**\n\n*Purpose:*\nThis node stores **short-term conversational memory**.\n\n*Key roles:*\n\n* Keeps track of the **previous chat context**\n* Allows the AI to maintain continuity during ongoing discussions\n"
},
"typeVersion": 1
},
{
"id": "3e234b21-725b-4aaa-a767-a2a05e744a55",
"name": "Note adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
208,
-384
],
"parameters": {
"color": 4,
"width": 320,
"height": 432,
"content": "### Node 4: **Retrieve bakery data**\n\n*Purpose:*\nThis node connects to the **Google Sheets bakery dataset**.\n\n*Key roles:*\n\n* Retrieves sales and stock data from the linked **spreadsheet**\n* Provides structured data for the AI Agent to analyze\n* Dataset: [Bakery Data Sheet](https://docs.google.com/spreadsheets/d/1dCCQzjoDZak-mQD1iyGd5aHKGFeh15fsBPUIoTgAYGw/edit?usp=drivesdk)\n"
},
"typeVersion": 1
},
{
"id": "4b5eb0ce-e311-4bed-821b-fcf7e5cf74ba",
"name": "Note adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-528,
176
],
"parameters": {
"color": 6,
"width": 352,
"height": 336,
"content": "### Node 5: **Azure OpenAI Chat Model**\n\n*Purpose:*\nThis node provides the **language model backend** for the AI Agent.\n\n*Key roles:*\n\n* Uses **GPT-based reasoning** for natural conversation\n* Handles query understanding and response generation\n* Ensures responses follow the defined **tone and style**\n"
},
"typeVersion": 1
}
],
"active": true,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "fe8411cd-b13e-40b3-beca-c579c00be0fc",
"connections": {
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"d1a293d6-7e5b-4543-9107-9caf45b4051a": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Azure OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Divers, RAG IA, IA Multimodale
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Partager ce workflow