Guillaume Duvernay This workflow corresponds to n8n.io template #9870 — we link there as the canonical source.
This workflow follows the Agent → 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 →
{
"nodes": [
{
"id": "cad8de80-6b0b-430c-a3c0-8e6a6a25c393",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
240,
544
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "3ccede32-2481-454e-9ccb-9e206b32d67f",
"name": "Myself?",
"type": "n8n-nodes-base.if",
"position": [
464,
544
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "fae16f10-e497-47ea-92ec-741f54cedd62",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.message.from.username }}",
"rightValue": "<Replace with your Telegram username>"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "87342e86-4f25-43ed-ae19-8a495b0888c3",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2256,
560
],
"parameters": {
"text": "={{ $json.final_user_message }}",
"options": {
"systemMessage": "=You are a helpful assistant that answers the user based on a knowledge base.\n\nWhenever the user query requires specific knowledge (most queries except empty queries like \"hi\"), call the tool \"Query knowledge base\" with a question to have it output an answer based on the knowledge base.\n\nIf the output from the knowledge base tool indicates that the knowledge base doesn't contain enough insights to answer, communicate this to the user transparently.\n\nAnswer considring that this conversation happens on Telegram - adapt your style/format to that platform."
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "e17cfbab-3149-45b3-9903-6b5b8b264b8f",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
2272,
816
],
"parameters": {
"sessionKey": "={{ $('Telegram Trigger').item.json.message.from.username }}",
"sessionIdType": "customKey",
"contextWindowLength": 7
},
"typeVersion": 1.3
},
{
"id": "182a9d2e-8747-48bf-9c8b-ca606915ce7b",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
880,
240
],
"parameters": {
"color": 2,
"width": 873,
"height": 325,
"content": "# Process Audio"
},
"typeVersion": 1
},
{
"id": "5ad3276d-f713-401f-8ee2-de72243eb426",
"name": "Get Audio File",
"type": "n8n-nodes-base.telegram",
"position": [
912,
400
],
"parameters": {
"fileId": "={{ $('Telegram Trigger').item.json.message.voice.file_id }}",
"resource": "file",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "4ac926fe-165b-4b11-ad8d-a5ebc040c4fc",
"name": "Message Router",
"type": "n8n-nodes-base.switch",
"position": [
688,
512
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "audio",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b5d9f703-2a1b-4942-906c-7a7d1404a4d7",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('Telegram Trigger').item.json.message.voice }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "342f0883-d959-44a2-b80d-379e39c76218",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('Telegram Trigger').item.json.message.text }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {
"fallbackOutput": "extra"
}
},
"typeVersion": 3.2
},
{
"id": "49027af2-e53b-4dfc-ac8e-b849cb6c9db6",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
2400,
768
],
"parameters": {
"color": 6,
"width": 336,
"height": 400,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n## Lookio tool\n\nThe agent calls this tool to get answers based on the knowledge base you've built in Lookio.\n- Add your [Lookio](https://www.lookio.app/) API key\n- Specify the ID of the Lookio assistant to query"
},
"typeVersion": 1
},
{
"id": "ce0b2d93-2276-47ca-857a-c83a72f0c3e1",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1904,
768
],
"parameters": {
"color": 5,
"width": 336,
"height": 400,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n## AI model\n\nThe core AI model of your agent. Connect your OpenAI API key or switch to your favorite LLM provider."
},
"typeVersion": 1
},
{
"id": "f667095e-cf14-4784-9a55-a4261ae00f1a",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
2192,
320
],
"parameters": {
"color": 4,
"width": 352,
"height": 400,
"content": "## The agent\n\nThis agent will distribute the relevant questions to Lookio via the \"Query knowledge base\" tool. Feel free to provide more context in its system message and add instructions when it comes to the format or style of responses?"
},
"typeVersion": 1
},
{
"id": "615e79ce-d872-4b99-96a2-02c9436b63c2",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
2032,
832
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "a8da1688-7bfd-4c68-a1da-45523c8628a2",
"name": "Telegram answer",
"type": "n8n-nodes-base.telegram",
"position": [
2832,
560
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "1dbd7647-e5ac-449a-8e45-34126b4af8bf",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
1216,
272
],
"parameters": {
"color": 7,
"width": 265,
"height": 277,
"content": "### AI transcription\n\nYou can replace with another model like OpenAI's."
},
"typeVersion": 1
},
{
"id": "73f644d2-97f9-4718-b0e6-982a44129470",
"name": "Query knowledge base",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
2544,
832
],
"parameters": {
"url": "https://api.lookio.app/webhook/query",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "query",
"value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('parameters0_Value', `The query to the knowledge base, in the form of a question`, 'string') }}"
},
{
"name": "assistant_id",
"value": "<your-assistant-id>"
},
{
"name": "query_mode",
"value": "flash"
}
]
},
"toolDescription": "Call this tool when the knowledge base is required to answer the user query.",
"headerParameters": {
"parameters": [
{
"name": "api_key",
"value": "<your-lookio-api-key>"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "6d132f95-391c-4a97-a8fa-92663fa608f0",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
384,
304
],
"parameters": {
"color": 3,
"width": 265,
"height": 405,
"content": "### Make this bot private\n\nTelegram bots are public by default, so we're adding a filter here based on your unique Telegram username. Change the value to ensure only your messages can go through, or delete this step to make it 100% public"
},
"typeVersion": 1
},
{
"id": "d4f5488f-f234-4142-b561-4349550c57f5",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
896,
592
],
"parameters": {
"color": 2,
"width": 873,
"height": 293,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n# Process text"
},
"typeVersion": 1
},
{
"id": "dd9663af-3587-42c9-bdf0-a6c3cc2ba6d1",
"name": "Prepare message from audio",
"type": "n8n-nodes-base.set",
"position": [
1584,
400
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "bffc2c1f-990e-4396-b59a-ab82b843e061",
"name": "preset_user_message",
"type": "string",
"value": "={{ $json.choices[0].message.content }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c18dfaf8-6189-4d78-b0d1-47af2a6e17be",
"name": "Prepare message from text",
"type": "n8n-nodes-base.set",
"position": [
1168,
672
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b37b48ba-8fef-4e6c-bbca-73e6c2e1e0a8",
"name": "preset_user_message",
"type": "string",
"value": "={{ $('Telegram Trigger').item.json.message.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c348dadb-0377-4a6e-9e5e-2f8ec77bd411",
"name": "Consolidate user message",
"type": "n8n-nodes-base.set",
"position": [
1872,
560
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "7db97ffc-b1eb-422e-8bb1-90eea55c7aa2",
"name": "final_user_message",
"type": "string",
"value": "={{ $json.preset_user_message }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "a881e44a-f8f4-456e-98e5-51850791967d",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
208,
-400
],
"parameters": {
"width": 880,
"height": 544,
"content": "# **RAG Telegram bot with Lookio & GPT-4.1 (text + voice)**\n\n**Summary**: A Telegram bot that answers questions using your Lookio assistant. Accepts text and voice (transcribed via **Mistral** by default) and uses an LLM agent that calls the **Query knowledge base** tool.\n\n**How it works (short)**:\n1. **Telegram Trigger** \u2192 Detects text or voice via **Message Router**.\n2. Voice: **Get Audio File** \u2192 **Mistral transcribe** \u2192 prepare text.\n3. **AI Agent** calls **Query knowledge base** (Lookio) when domain knowledge is needed and sends answers via **Telegram answer**.\n\n**How to use / Setup**:\n1. Create a Lookio assistant; get **API Key** and **Assistant ID**.\n2. In **Query knowledge base**, replace `<your-lookio-api-key>` and `<your-assistant-id>`.\n3. Add credentials: **Telegram API**, **OpenAI (or LLM)**, **Mistral Cloud**.\n4. (Optional) Edit **Myself?** to set your Telegram username for private testing or delete it to make the bot public.\n5. Activate the workflow and message your bot in Telegram.\n\n\n**Bold nodes to configure:** **Telegram Trigger**, **Query knowledge base**, **OpenAI Chat Model**, **Mistral transcribe**, **Myself?**\n\n*A template created by Guillaume Duvernay*\n"
},
"typeVersion": 1
},
{
"id": "eda43537-92a0-47f0-ba3f-377b3ba9f5a3",
"name": "Mistral transcribe",
"type": "n8n-nodes-base.httpRequest",
"position": [
1296,
400
],
"parameters": {
"url": "https://api.mistral.ai/v1/audio/transcriptions",
"method": "POST",
"options": {
"redirect": {
"redirect": {}
}
},
"sendBody": true,
"contentType": "multipart-form-data",
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "model",
"value": "voxtral-mini-2507"
},
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
}
]
},
"nodeCredentialType": "mistralCloudApi"
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
}
],
"connections": {
"Myself?": {
"main": [
[
{
"node": "Message Router",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Telegram answer",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Get Audio File": {
"main": [
[
{
"node": "Mistral transcribe",
"type": "main",
"index": 0
}
]
]
},
"Message Router": {
"main": [
[
{
"node": "Get Audio File",
"type": "main",
"index": 0
}
],
[
{
"node": "Prepare message from text",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Myself?",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Mistral transcribe": {
"main": [
[
{
"node": "Prepare message from audio",
"type": "main",
"index": 0
}
]
]
},
"Query knowledge base": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Consolidate user message": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Prepare message from text": {
"main": [
[
{
"node": "Consolidate user message",
"type": "main",
"index": 0
}
]
]
},
"Prepare message from audio": {
"main": [
[
{
"node": "Consolidate user message",
"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.
mistralCloudApiopenAiApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Create a Telegram bot that answers questions using Retrieval-Augmented Generation (RAG) powered by Lookio and an LLM agent (GPT-4.1).
Source: https://n8n.io/workflows/9870/ — 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.
Digital marketers, content creators, social media managers, and businesses who want to use AI marketing automation for YouTube Shorts without spending hours on production. This AI workflow helps anyon
OpenAI, HTTP Request, OpenAI Chat +7
This automation is designed to help you generate AI-powered music tracks, cover art, and fully rendered music videos — all triggered from a simple Telegram chat and managed via Google Sheets.
OpenAI Chat, Memory Buffer Window, Output Parser Structured +11
This multi-agent n8n workflow delivers an automated, intelligent trading analysis system for the WEEX Spot Market. It uses GPT-4o to interpret user prompts, route them to the correct sub-agent tools,
OpenAI Chat, Telegram Trigger, Agent +7
Template Carnaval - time instagram. Uses toolWorkflow, lmChatOpenAi, memoryBufferWindow, agent. Event-driven trigger; 56 nodes.
Tool Workflow, OpenAI Chat, Memory Buffer Window +10
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Output Parser Structured, Telegram, N8N Nodes Tesseractjs +14