iamvaar This workflow corresponds to n8n.io template #5680 — we link there as the canonical source.
This workflow follows the Chainllm → Chat Trigger 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "7ac1a47f-3373-418c-84ff-30106c911340",
"name": "Content for the Training",
"type": "n8n-nodes-base.googleDocs",
"position": [
-1880,
-100
],
"parameters": {
"operation": "get",
"documentURL": "1shUBSb2aEFZrOWOROcCeG9glxi7u205p4lEopNt1e7E",
"authentication": "serviceAccount"
},
"credentials": {
"googleApi": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "2aabc964-23e8-4113-8280-9eb70588c858",
"name": "Splitting into Chunks",
"type": "n8n-nodes-base.code",
"position": [
-1660,
-100
],
"parameters": {
"jsCode": "const text = $input.first().json.content;\nconst chunkSize = 1000;\n\nlet chunks = [];\nfor (let i = 0; i < text.length; i += chunkSize) {\n chunks.push({\n json: { chunk: text.slice(i, i + chunkSize) }\n });\n}\n\nreturn chunks;\n\n"
},
"typeVersion": 2
},
{
"id": "561cff53-365d-4d09-baf6-f1a864ec6c46",
"name": "Embedding Uploaded document",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1440,
-100
],
"parameters": {
"url": "https://api.together.xyz/v1/embeddings",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "BAAI/bge-large-en-v1.5"
},
{
"name": "input",
"value": "={{ $json.chunk }}"
}
]
},
"genericAuthType": "httpBearerAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "57488d21-d59b-4e1a-916c-e35409d796c4",
"name": "Save the embedding in DB",
"type": "n8n-nodes-base.supabase",
"position": [
-1220,
-100
],
"parameters": {
"tableId": "embed",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "chunk",
"fieldValue": "={{ $('Splitting into Chunks').item.json.chunk }}"
},
{
"fieldId": "embedding",
"fieldValue": "={{ JSON.stringify($json.data[0].embedding) }}"
}
]
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "a91cd4dd-eab7-468b-932e-3fd7122bd5f5",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"disabled": true,
"position": [
-2160,
-100
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f9bd510a-1894-4f03-abb1-b1aa9fa007e1",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-300,
-140
],
"parameters": {
"public": true,
"options": {},
"initialMessages": "Hi there! \ud83d\udc4b\nTest the basic RAG chat with Supabase "
},
"typeVersion": 1.1
},
{
"id": "d4be0adb-e8ad-4ce8-aaaa-2bb957da47ce",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"position": [
360,
-140
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "chunk"
}
]
}
},
"typeVersion": 1
},
{
"id": "2db8d4ed-e32a-449e-ae2b-68399c552ea4",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
680,
-140
],
"parameters": {
"text": "=You are an AI assistant. Use the following context to answer the user's question.\n\nContext:\n{{ $json.chunk }}\n\nUser's message:\n{{ $('When chat message received').item.json.chatInput }}\n\nProvide a helpful and detailed answer based *only* on the context. If the answer is not in the context, say \"I don't know based on the provided information.\"\n",
"batching": {},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "db2ba386-1a3b-4d46-abc3-c53f98323ca4",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
680,
60
],
"parameters": {
"model": "qwen/qwen3-8b:free",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ed1849e9-fb30-4763-a6bf-2ba8c6c243f7",
"name": "Search Embeddings",
"type": "n8n-nodes-base.httpRequest",
"position": [
140,
-140
],
"parameters": {
"url": "https://fqdttboovkcezrxizkpw.supabase.co/rest/v1/rpc/matchembeddings1",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "=query_embedding",
"value": "={{ $json.data[0].embedding }}"
},
{
"name": "match_count",
"value": "5"
}
]
},
"nodeCredentialType": "supabaseApi"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "e5966ced-618c-4fbf-85c9-d8fd8bf0576b",
"name": "Embend User Message",
"type": "n8n-nodes-base.httpRequest",
"position": [
-80,
-140
],
"parameters": {
"url": "https://api.together.xyz/v1/embeddings",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "BAAI/bge-large-en-v1.5"
},
{
"name": "input",
"value": "={{ $json.chatInput }}"
}
]
},
"genericAuthType": "httpBearerAuth"
},
"credentials": {
"httpBearerAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "3aed0aa2-25ab-4f5e-b6d1-fe536bce5ef3",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2900,
-300
],
"parameters": {
"width": 1900,
"height": 1080,
"content": "## \u26a0\ufe0f RUN THIS FIRST & RUN IT FOR ONLY ONCE \n(as it will convert your content in Embedding format and save it in DB and is ready for the RAG Chat)\n\n## \ud83d\udccc Telegram Trigger\n\n* **Type:** `telegramTrigger`\n* **Purpose:** Waits for new Telegram messages to trigger the workflow.\n* **Note:** Currently disabled.\n\n---\n\n## \ud83d\udcc4 Content for the Training\n\n* **Type:** `googleDocs`\n* **Purpose:** Fetches document content from Google Docs using its URL.\n* **Details:** Uses Service Account authentication.\n\n---\n\n## \u2702\ufe0f Splitting into Chunks\n\n* **Type:** `code`\n* **Purpose:** Splits the fetched document text into smaller chunks (1000 chars each) for processing.\n* **Logic:** Loops over text and slices it.\n\n---\n\n## \ud83e\udde0 Embedding Uploaded Document\n\n* **Type:** `httpRequest`\n* **Purpose:** Calls Together AI embedding API to get vector embeddings for each text chunk.\n* **Details:** Sends JSON with model name and chunk as input.\n\n---\n\n## \ud83d\udee2 Save the embedding in DB\n\n* **Type:** `supabase`\n* **Purpose:** Saves each text chunk and its embedding vector into the Supabase `embed` table."
},
"typeVersion": 1
},
{
"id": "6afc7ab6-18d2-4781-bfc5-a0ae03a9ef68",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-900,
-300
],
"parameters": {
"width": 1900,
"height": 1080,
"content": "## \ud83d\udcac When chat message received\n\n* **Type:** `chatTrigger`\n* **Purpose:** Starts the workflow when a user sends a chat message.\n* **Details:** Sends an initial greeting message to the user.\n\n---\n\n## \ud83e\udde9 Embend User Message\n\n* **Type:** `httpRequest`\n* **Purpose:** Generates embedding for the user\u2019s input message.\n* **Details:** Calls Together AI embeddings API.\n\n---\n\n## \ud83d\udd0d Search Embeddings\n\n* **Type:** `httpRequest`\n* **Purpose:** Searches Supabase DB for the top 5 most similar text chunks based on the generated embedding.\n* **Details:** Calls Supabase RPC function `matchembeddings1`.\n\n---\n\n## \ud83d\udce6 Aggregate\n\n* **Type:** `aggregate`\n* **Purpose:** Combines all retrieved text chunks into a single aggregated context for the LLM.\n\n---\n\n## \ud83e\udde0 Basic LLM Chain\n\n* **Type:** `chainLlm`\n* **Purpose:** Passes the user's question + aggregated context to the LLM to generate a detailed answer.\n* **Details:** Contains prompt instructing the LLM to answer only based on context.\n\n---\n\n## \ud83e\udd16 OpenRouter Chat Model\n\n* **Type:** `lmChatOpenRouter`\n* **Purpose:** Provides the actual AI language model that processes the prompt.\n* **Details:** Uses `qwen/qwen3-8b:free` model via OpenRouter."
},
"typeVersion": 1
}
],
"connections": {
"Aggregate": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Content for the Training",
"type": "main",
"index": 0
}
]
]
},
"Search Embeddings": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Embend User Message": {
"main": [
[
{
"node": "Search Embeddings",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Splitting into Chunks": {
"main": [
[
{
"node": "Embedding Uploaded document",
"type": "main",
"index": 0
}
]
]
},
"Content for the Training": {
"main": [
[
{
"node": "Splitting into Chunks",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Embend User Message",
"type": "main",
"index": 0
}
]
]
},
"Embedding Uploaded document": {
"main": [
[
{
"node": "Save the embedding in DB",
"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.
googleApihttpBearerAuthopenRouterApisupabaseApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
(as it will convert your content in Embedding format and save it in DB and is ready for the RAG Chat)
Source: https://n8n.io/workflows/5680/ — 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.
Pitch Paul. Uses lmChatOpenRouter, telegram, outputParserStructured, supabaseTool. Event-driven trigger; 33 nodes.
OpenRouter Chat, Telegram, Output Parser Structured +10
Telegram Message Recap. Uses telegramTrigger, supabase, lmChatGoogleGemini, telegram. Event-driven trigger; 23 nodes.
Telegram Trigger, Supabase, Google Gemini Chat +4
A Telegram bot that converts natural-language work descriptions into detailed cost estimates using AI parsing, vector search, and the open-source DDC CWICR database with 55,000+ construction work item
HTTP Request, Telegram, Telegram Trigger +6
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
Automatically capture, categorize, and log expenses from receipts, PDFs, voice notes, or text — powered by AI and integrated with Telegram and Google Sheets.
HTTP Request, OpenAI, Chain Llm +6