Davide Boizza This workflow corresponds to n8n.io template #8488 — we link there as the canonical source.
This workflow follows the Agent → OpenAI Embeddings 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 →
{
"id": "EMOh4weW7QKklbyb",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Build AI Voice Assistent with VAPI",
"tags": [],
"nodes": [
{
"id": "784ae812-b3e9-4768-a108-ac3f5fd0e965",
"name": "Question and Answer Chain",
"type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
"position": [
736,
3728
],
"parameters": {
"text": "={{ $json.body.search }}",
"options": {
"systemPromptTemplate": "=You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question.\nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n\nToday is {{ $now }}\n\n----------------\nContext: {context}"
},
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "1a051d79-3738-4e64-b97f-ac581e724d95",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
624,
3952
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "31c0a7f1-45a2-4ed2-adbd-423f1fcc7bb7",
"name": "Vector Store Retriever",
"type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
"position": [
832,
3936
],
"parameters": {
"topK": 5
},
"typeVersion": 1
},
{
"id": "bb55684d-6c5b-4518-ae49-206f5f163c3c",
"name": "Qdrant Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
752,
4128
],
"parameters": {
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "list",
"value": "negozio-emporio-verde",
"cachedResultName": "negozio-emporio-verde"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "f530e2ad-645d-4b89-94f0-44f62522917a",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
736,
4304
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "5b11f5d5-78f6-4095-b5a8-88630fce649e",
"name": "rag",
"type": "n8n-nodes-base.webhook",
"position": [
352,
3728
],
"parameters": {
"path": "5ca93cd6-7f7b-4c91-acff-c324e594cca7",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2.1
},
{
"id": "07ab5e01-4fff-414e-9843-cf9382aac4df",
"name": "get_order",
"type": "n8n-nodes-base.wooCommerceTool",
"position": [
1072,
3408
],
"parameters": {
"orderId": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Order_ID', `Order Details Retrieval Process:\n1. Request Order Number\n - Explicitly ask customer for the complete order number\n\n2. Identity Verification\n - Ask for the email address associated with the order\n - Strictly verify that the provided email matches the order record\n - If email does NOT match the order:\n * Immediately halt the process\n * Inform customer that the email is incorrect\n * Do NOT provide the correct email\n * Prevent access to order details\n\n3. Verification Criteria\n - Exact match of email to order record is mandatory\n - No exceptions or workarounds\n - Customer must provide the precise, correct email`, 'string') }}",
"resource": "order",
"operation": "get"
},
"credentials": {
"wooCommerceApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "b83afd81-7e3e-43bb-8581-ee82d76b9330",
"name": "get_orders",
"type": "n8n-nodes-base.wooCommerceTool",
"position": [
1184,
3408
],
"parameters": {
"options": {
"search": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Search', ``, 'string') }}"
},
"resource": "order",
"operation": "getAll",
"returnAll": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Return_All', ``, 'boolean') }}"
},
"credentials": {
"wooCommerceApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "22d61db2-97b4-40da-852d-676b50ef7d26",
"name": "get_user",
"type": "n8n-nodes-base.wooCommerceTool",
"position": [
1280,
3408
],
"parameters": {
"filters": {
"email": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Email', ``, 'string') }}"
},
"resource": "customer",
"operation": "getAll",
"returnAll": true
},
"credentials": {
"wooCommerceApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "7026a8d5-43a7-48db-a337-1b3a9f457ddb",
"name": "Calculator",
"type": "@n8n/n8n-nodes-langchain.toolCalculator",
"position": [
768,
3408
],
"parameters": {},
"typeVersion": 1
},
{
"id": "fb4d1894-4d09-4f3c-af85-de2fe67d5967",
"name": "get_tracking",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
928,
3408
],
"parameters": {
"name": "get_tracking",
"workflowId": {
"__rl": true,
"mode": "id",
"value": "EMOh4weW7QKklbyb"
},
"description": "Get tracking number for a specific order by providing the order number. The tool retrieves the unique tracking code that allows customers to monitor their shipment's current status and location.",
"workflowInputs": {
"value": {
"order_number": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('order_number', ``, 'string') }}"
},
"schema": [
{
"id": "order_number",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "order_number",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"order_number"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.1
},
{
"id": "caacd925-11eb-4f11-a3bb-6381f74b5fc8",
"name": "When Executed by Another Workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
1472,
3392
],
"parameters": {
"inputSource": "jsonExample",
"jsonExample": "{\n \"order_number\": \"order number\"\n}"
},
"typeVersion": 1.1
},
{
"id": "11504f43-0dce-4eef-a461-a0fd080b94e3",
"name": "Post-Sales Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
624,
3120
],
"parameters": {
"text": "=Order Information:\nEmail: {{ $json.body.email }}\nOrder number: {{ $json.body.n_order }}",
"options": {
"systemMessage": "=## Role and Primary Objective\nYou are a customer support AI agent for an online clothing store, specializing in post-sales assistance. Your primary goals are to:\n- Help customers track their orders\n- Provide information about past and current orders\n- Offer clear and concise support\n\n## Communication Guidelines\n1. Always be professional, helpful, and precise\n2. Use available tools to retrieve accurate information\n3. Verify customer identity before sharing order details\n4. Protect customer privacy and data confidentiality\n\n## Tool Usage Instructions\n\n### Order Information Retrieval\n- Use `get_order` to fetch details for a single order\n - REQUIRED: Complete user information including request, email, and order number\n- Use `get_orders` to retrieve multiple orders for a single customer\n- Use `get_user` to obtain customer profile information\n\n### Tracking and Support\n- Use `get_tracking` to obtain tracking information for an order using the order number\n- If a customer cannot find what they need, use `human*assistance`\n - Synthesize the request clearly\n - Include associated user email\n - Provide concise, relevant details\n\n### General Information\n- Use `ToS` tool to answer questions about:\n - Terms and Conditions\n - Shipping information\n - General store policies\n\n## Critical Verification Rules\n- ALWAYS verify that the email provided matches the order number\n- If the email does not match the order:\n - DO NOT provide the correct email\n - Inform the customer that the email address is incorrect\n - Request the correct email associated with the order\n\n## Prohibited Actions\n- Never disclose sensitive customer information\n- Do not share full order details without proper verification\n- Avoid providing speculative or unconfirmed information\n\n## Communication Style\n- Be direct and helpful\n- Use clear, professional language\n- Focus on solving the customer's specific query\n- Provide step-by-step guidance when necessary\n\nToday is {{$now}}"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "571a225d-edc8-499e-a48d-5d8253d38b64",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1456,
3216
],
"parameters": {
"color": 5,
"width": 532,
"height": 136,
"content": "The tracking code request is made through the most popular WooCommerce tracking plugin: \"YITH WooCommerce Order & Shipment Tracking\". The free version can be [downloaded here](https://wordpress.org/plugins/yith-woocommerce-order-tracking/)\n- Create a new workflow and change URL in the node \"Http Request\" with your WooCommerce shop url"
},
"typeVersion": 1
},
{
"id": "c0d82557-5f90-4115-8673-216e2274f25d",
"name": "Get tracking",
"type": "n8n-nodes-base.httpRequest",
"position": [
1648,
3392
],
"parameters": {
"url": "=https://URL/wp-json/wc/v3/orders/{{ $json.order_number }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpBasicAuth"
},
"credentials": {
"httpBasicAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "85450f4c-7329-4876-af32-792764d1c726",
"name": "Set tracking code",
"type": "n8n-nodes-base.set",
"position": [
1824,
3392
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "19b33abc-5191-4449-b682-4466f1975ff2",
"name": "tracking_code",
"type": "string",
"value": "={{ $json[\"meta_data\"].find(item => item.key === \"ywot_tracking_code\").value }}"
},
{
"id": "2e18b337-e3e8-4669-a902-ecc2ba027a1a",
"name": "carrier_url",
"type": "string",
"value": "={{ $json[\"meta_data\"].find(item => item.key === \"ywot_carrier_url\").value }}"
},
{
"id": "ae834f65-67b2-4e95-9a49-5172e36fc5b9",
"name": "pick_up",
"type": "string",
"value": "={{ $json[\"meta_data\"].find(item => item.key === \"ywot_pick_up_date\").value }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "1153e7e1-269a-472f-8dc5-df3b59a48705",
"name": "GPT 4o-mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
464,
3408
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "5a29fd84-fb55-4f89-98a4-a7ba0c5f3889",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
352,
3120
],
"parameters": {
"path": "f265a558-2787-4f8c-96a1-7b1068e45d3c",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2.1
},
{
"id": "a5aef818-952a-401e-bfa4-a6e2ec1b52de",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
3136
],
"parameters": {
"color": 4,
"width": 384,
"height": 112,
"content": "## Post-sale Agent\nGet a WooCommerce user's orders and shipping tracking"
},
"typeVersion": 1
},
{
"id": "2d963ce1-5a68-4f59-9162-8e256349f056",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
3728
],
"parameters": {
"color": 4,
"width": 400,
"height": 144,
"content": "## General info\n\nExtract information saved in the vector database\n\nTo build the RAG system please view [this Workflow](https://n8n.io/workflows/7647-build-a-self-updating-rag-system-with-openai-google-gemini-qdrant-and-google-drive/)"
},
"typeVersion": 1
},
{
"id": "8b837fa9-8c26-4454-97a6-0a0d7e0cd0e2",
"name": "Set response",
"type": "n8n-nodes-base.set",
"position": [
976,
3120
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d6a208ab-3fb3-4b4a-9615-b29183bbce39",
"name": "message",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "1ef5425b-d66b-44b6-985b-5cc5adcb3ca6",
"name": "Send response to VAPI",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
1216,
3120
],
"parameters": {
"options": {}
},
"typeVersion": 1.4
},
{
"id": "7a91965a-bf65-404d-86b8-69990f687e9e",
"name": "Send RAG response to VAPI",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
1216,
3728
],
"parameters": {
"options": {}
},
"typeVersion": 1.4
},
{
"id": "cbebeb82-f172-45d6-afa6-9f8409a8432d",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
2624
],
"parameters": {
"width": 1072,
"height": 368,
"content": "## STEP 1\nCreate two \"API Request\" tools in VAPI:\n- WooCommerce tool: connect the n8n webhook and set two parameters as the request body: 'email' and 'n_order'\n- Rag tool: connect the n8n webhook and set the 'search' parameter as the request body\n\n## STEP 2\n- Create a wizard by generating a system prompt that includes the functionality of the two tools created in STEP 1.\n- Set the voice in the Voice tab.\n- Include the two tools created in STEP 1 in the 'Tools' tab.\n\n## STEP 3\n- Create or import a phone number from Twilio, setting it as \"Inbound.\"\n- Associate the phone number with the wizard."
},
"typeVersion": 1
},
{
"id": "dbd67324-fb3e-4559-a013-33e37216900c",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
2384
],
"parameters": {
"color": 3,
"width": 1072,
"height": 208,
"content": "## Build AI Voice Assistent with VAPI & Twilio for WooCommerce Post-Sales & RAG\nThis workflow integrates a **Retrieval-Augmented Generation (RAG) system** with a **post-sales AI agent for WooCommerce**. It combines vector-based search (Qdrant + OpenAI embeddings) with LLMs (Google Gemini and GPT-4o-mini) to provide accurate and contextual responses.\n\nBoth systems are connected to **VAPI webhooks**, making the workflow usable in a **voice AI assistant** via **Twilio** phone numbers.\n\nThe workflow receives JSON payloads from VAPI via webhooks, processes the request through the appropriate chain (Agent or RAG), and sends a structured response back to VAPI to be read out to the user."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "abceb79d-e0c7-4d43-b622-7f24d92563b0",
"connections": {
"rag": {
"main": [
[
{
"node": "Question and Answer Chain",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Post-Sales Agent",
"type": "main",
"index": 0
}
]
]
},
"get_user": {
"ai_tool": [
[
{
"node": "Post-Sales Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"get_order": {
"ai_tool": [
[
{
"node": "Post-Sales Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Calculator": {
"ai_tool": [
[
{
"node": "Post-Sales Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"get_orders": {
"ai_tool": [
[
{
"node": "Post-Sales Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"GPT 4o-mini": {
"ai_languageModel": [
[
{
"node": "Post-Sales Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Get tracking": {
"main": [
[
{
"node": "Set tracking code",
"type": "main",
"index": 0
}
]
]
},
"Set response": {
"main": [
[
{
"node": "Send response to VAPI",
"type": "main",
"index": 0
}
]
]
},
"get_tracking": {
"ai_tool": [
[
{
"node": "Post-Sales Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Post-Sales Agent": {
"main": [
[
{
"node": "Set response",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Qdrant Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Retriever",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Vector Store Retriever": {
"ai_retriever": [
[
{
"node": "Question and Answer Chain",
"type": "ai_retriever",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Question and Answer Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Question and Answer Chain": {
"main": [
[
{
"node": "Send RAG response to VAPI",
"type": "main",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Get tracking",
"type": "main",
"index": 0
}
]
]
}
}
}
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.
googlePalmApihttpBasicAuthopenAiApiqdrantApiwooCommerceApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow integrates a Retrieval-Augmented Generation (RAG) system with a post-sales AI agent for WooCommerce. It combines vector-based search (Qdrant + OpenAI embeddings) with LLMs (Google Gemini and GPT-4o-mini) to provide accurate and contextual responses.
Source: https://n8n.io/workflows/8488/ — 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.
Indoor Farming Agent. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, toolVectorStore. Webhook trigger; 36 nodes.
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +16
Bitrix24 Open Chanel RAG Chatbot Application Workflow example with Webhook Integration. Uses httpRequest, noOp, respondToWebhook, documentDefaultDataLoader. Webhook trigger; 34 nodes.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +6
This workflow implements a complete Voice AI Chatbot system for Wordress that integrates speech recognition, guardrails for safety, retrieval-augmented generation (RAG), Qdrant vector search, and audi
OpenAI Chat, Memory Buffer Window, Tool Calculator +10
Transform your Bitrix24 Open Line channels with an intelligent chatbot that leverages Retrieval-Augmented Generation (RAG) technology to provide accurate, document-based responses to customer inquirie
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +6
This workflow implements an advanced AI automation agent (OpenClaw Agent) that interacts with users through Telegram and integrates multiple AI models, external tools, and cloud services to automate c
Telegram Trigger, Telegram, OpenAI +21