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 →
{
"name": "Telegram bot",
"nodes": [
{
"parameters": {
"updates": [
"message"
],
"additionalFields": {
"download": false
}
},
"id": "6d79ea79-ee3b-4e3e-9bbd-63d5b194f765",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"typeVersion": 1.1,
"position": [
-260,
920
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"id": "0d27cb87-9aa1-4df8-a100-06b5046dd1da",
"name": "Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
1060,
1640
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"id": "e3efecdb-f1d3-4eff-9a25-8a9d2ffd981a",
"name": "Ollama Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
1040,
1140
],
"notesInFlow": false,
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "VectorDB"
},
"id": "2c450754-ec3a-4f1a-8640-c0055ffa3a03",
"name": "Vector Store Tool",
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
1180,
1360
]
},
{
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"id": "0f2fd9cc-7cbe-4d02-87c1-53557361c179",
"name": "Ollama Chat Model2",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
1300,
1500
],
"notesInFlow": false,
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"qdrantCollection": {
"__rl": true,
"value": "the_db_name",
"mode": "list",
"cachedResultName": "the_db_name"
},
"options": {}
},
"id": "12c68f85-715d-41e8-8550-a76b702e0bcb",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1,
"position": [
1060,
1500
],
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const photos = $json.message.photo;\nif (!photos || photos.length === 0) {\n return null;\n}\nconst highestResolutionPhoto = photos[photos.length - 1];\n\nreturn { json: { file_id: highestResolutionPhoto.file_id, caption: $json.message.caption } };"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
400,
1120
],
"id": "7b0dcd11-37d3-4036-a77b-836c363b9482",
"name": "Code",
"alwaysOutputData": true
},
{
"parameters": {
"content": "## Photo",
"height": 549.7036671240952,
"width": 574.2252256721589,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
360,
1060
],
"id": "b99f73ae-61ba-4f80-9e44-78579abad843",
"name": "Sticky Note2"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"contextWindowLength": 10
},
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1.3,
"position": [
1160,
1140
],
"id": "97000912-5d41-4b05-9d55-ae142e5ec449",
"name": "Postgres Chat Memory",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## Voice",
"height": 330.9506144115263,
"width": 635.1678977055899,
"color": 3
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
360,
569.0493855884736
],
"id": "294cdda3-4379-4569-92f2-49d49ebe52d0",
"name": "Sticky Note"
},
{
"parameters": {
"content": "## Vector store\nUse another workflow to create and load data",
"height": 508.118344862517,
"width": 461.64938745853254
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
980,
1272.9080039013422
],
"id": "f0142409-1e66-4472-8c74-b728d7ecad83",
"name": "Sticky Note1"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Telegram Trigger').item.json.message.chat.id }}"
},
"id": "0b771151-00ea-45c2-93ee-5c1d5f5297ab",
"name": "Postgres Chat Memory2",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1.3,
"position": [
600,
1460
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "insert",
"messages": {
"messageValues": [
{
"type": "user",
"message": "={{ $json.output }}"
}
]
}
},
"id": "b3b39677-9cff-4400-b416-f87c9614d4a9",
"name": "Chat Memory Manager",
"type": "@n8n/n8n-nodes-langchain.memoryManager",
"typeVersion": 1.1,
"position": [
600,
1300
]
},
{
"parameters": {
"method": "POST",
"url": "http://whisper:8000/v1/audio/transcriptions",
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"parameterType": "formBinaryData",
"name": "file",
"inputDataFieldName": "=data"
},
{
"name": "model",
"value": "large"
}
]
},
"options": {}
},
"id": "b348fa1d-2e64-48e4-a6ab-00a5d4d82beb",
"name": "Whisper",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
640,
720
],
"retryOnFail": true,
"waitBetweenTries": 5000,
"maxTries": 5
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.text }}",
"options": {
"systemMessage": "=You are an expert personal assistant. Any response should be in a conversational text format.\n\nThe person you are helping is based in Orem, Utah. The time is {{ $now }}. Software engineer. Aspiring entrepreneur. Interests include philosophy, psychology, physics, engineering, programming, software, computers, gaming, biking, and knowledge management.\n\nUnless otherwise specified, assume the environment in which a coding solution will be provided should be in typescript, using React, tailwind, MobX, ReactQuery, and ionic/capacitor when native APIs are necessary. Prefer functional components. Use function declarations instead of const, unless using a MobX observer from mobx-react-lite.\n\nConcise responses. Provide a lengthy response when requested. Do not repeat yourself in the same response. Do not provide disclaimers about what ChatGPT can or cannot do. Use MLA format to cite sources at the end of each response. Expand URLs so they are all selectable. State the confidence level of each response at the very end.\n\nRespond as an uplifting friend, with critical but constructive feedback. Do not tell me what you think I want to hear, but tell me verifiably true facts, with the references provided in MLA format. Do not lie, make things up, or hallucinate. Be absolutely certain to communicate the confidence of each response at the end of each message."
}
},
"id": "6df88a0f-69e2-4aff-aab7-8ef824490f92",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.6,
"position": [
1220,
920
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "2798e0e7-48ca-49ef-a75b-924ddc279d24",
"name": "=text",
"value": "={{ $json.message.text }}",
"type": "string"
}
]
},
"options": {}
},
"id": "c836328f-12a6-4b56-9956-dd515ed879ec",
"name": "Text",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
880,
920
]
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"text": "You are not allowed to use this bot.",
"additionalFields": {
"appendAttribution": false
}
},
"id": "6ea9774d-beb4-4443-9217-80811560ac64",
"name": "Deny Msg",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
100,
1100
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"leftValue": "[7848136566]",
"rightValue": "={{ $json.message.from.id }}",
"operator": {
"type": "array",
"operation": "contains",
"rightType": "any"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Allowed"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"id": "be4f384e-8e5d-442e-88fe-5811a09d533b",
"leftValue": "={{ $json.message.text }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Blocked"
}
]
},
"looseTypeValidation": true,
"options": {}
},
"id": "4a94f2b0-ff10-4737-82b2-8035e4232d10",
"name": "Allowed?",
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
-40,
920
]
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.message.voice.file_id }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Voice"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "be4f384e-8e5d-442e-88fe-5811a09d533b",
"leftValue": "={{ $json.message.text }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Text"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "eab53a85-0ac6-4b64-b5ae-5c19611dc3d0",
"leftValue": "={{ $json.message.photo }}",
"rightValue": "",
"operator": {
"type": "array",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Photo"
}
]
},
"options": {}
},
"id": "f59dcdaf-bedd-4266-a62a-241d739edcc8",
"name": "Format",
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
200,
920
]
},
{
"parameters": {
"resource": "file",
"fileId": "={{ $json.message.voice.file_id }}"
},
"id": "ee627f0b-4eb6-45a0-b92a-28c7895ad679",
"name": "Download Audio",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
460,
720
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "file",
"fileId": "={{ $json.file_id }}"
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
520,
1120
],
"id": "7779dd3d-b635-4a96-a2fc-6ffee30ca3ba",
"name": "Download Image",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "binaryToPropery",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
640,
1120
],
"id": "c015a8fd-ab4d-448f-8902-f326d7bd65c3",
"name": "Base64"
},
{
"parameters": {
"method": "POST",
"url": "http://ollama:11434/api/chat",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\": \"llama3.2-vision\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Be as specific and precise as possible. Describe the image as if it were to someone that is blind. {{ $('Code').item.json.caption }}\",\n \"images\": [\n \"{{ $json.data }}\"\n ]\n }\n ]\n}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
760,
1120
],
"id": "095db111-bf9d-4cda-bd10-52cccb55be02",
"name": "Llama 3.2 Vision"
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const data = $json.data.split('\\n');\nconst caption = $('Telegram Trigger').item.json.message.caption;\n\nconst contents = []\ndata.forEach(datum => {\n try {\n const item = JSON.parse(datum)\n if (item.message.content) {\n contents.push(item.message.content)\n }\n } catch (err) {}\n})\n\nreturn {\n output: `Caption: ${caption}\n\nImage analysis results: ${contents.join('')}`\n};"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
400,
1300
],
"id": "8a8584b7-a55c-4642-bd86-c07a5e9f4a69",
"name": "Image results"
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"text": "=`{{ $json.output }}`",
"additionalFields": {
"appendAttribution": false
}
},
"id": "a6bb8263-c879-4c7a-9da2-8cd1852049ed",
"name": "Response",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
1560,
920
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"text": "=Transcription: {{ $json.text }}",
"additionalFields": {
"appendAttribution": false
}
},
"id": "8d1b3baf-c275-4601-9acf-f66364d4baab",
"name": "Transcription",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
820,
600
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Telegram Trigger": {
"main": [
[
{
"node": "Allowed?",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Vector Store Tool": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Ollama Chat Model2": {
"ai_languageModel": [
[
{
"node": "Vector Store Tool",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"ai_vectorStore": [
[
{
"node": "Vector Store Tool",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "Download Image",
"type": "main",
"index": 0
}
]
]
},
"Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Postgres Chat Memory2": {
"ai_memory": [
[
{
"node": "Chat Memory Manager",
"type": "ai_memory",
"index": 0
}
]
]
},
"Whisper": {
"main": [
[
{
"node": "Transcription",
"type": "main",
"index": 0
},
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Response",
"type": "main",
"index": 0
}
]
]
},
"Text": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Allowed?": {
"main": [
[
{
"node": "Format",
"type": "main",
"index": 0
}
],
[
{
"node": "Deny Msg",
"type": "main",
"index": 0
}
]
]
},
"Format": {
"main": [
[
{
"node": "Download Audio",
"type": "main",
"index": 0
}
],
[
{
"node": "Text",
"type": "main",
"index": 0
}
],
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Download Audio": {
"main": [
[
{
"node": "Whisper",
"type": "main",
"index": 0
}
]
]
},
"Download Image": {
"main": [
[
{
"node": "Base64",
"type": "main",
"index": 0
}
]
]
},
"Base64": {
"main": [
[
{
"node": "Llama 3.2 Vision",
"type": "main",
"index": 0
}
]
]
},
"Llama 3.2 Vision": {
"main": [
[
{
"node": "Image results",
"type": "main",
"index": 0
}
]
]
},
"Image results": {
"main": [
[
{
"node": "Chat Memory Manager",
"type": "main",
"index": 0
},
{
"node": "Response",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "21b824c3-9a42-40ef-af10-1e891550bc2c",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "9LaAFjM28Itn8S8m",
"tags": []
}
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.
ollamaApipostgresqdrantApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow powers an intelligent Telegram bot that responds to user messages with context-aware replies, drawing on stored knowledge to deliver accurate and relevant information without manual intervention. It's ideal for developers or businesses seeking to automate customer support, Q&A services, or interactive chats on Telegram, saving hours of response time while maintaining a natural conversational flow. The core step involves processing incoming messages through Ollama's chat model, which generates embeddings and queries a Qdrant vector store to retrieve pertinent data before crafting the final output.
Use this workflow when building event-driven bots that need to handle queries against a knowledge base, such as FAQs or product info, integrated with Telegram for real-time interaction. Avoid it for simple bots without AI needs, like basic notifications, or when scaling to millions of users without custom optimisation. Common variations include swapping Qdrant for another vector store or adding Postgres memory for persistent conversation history across sessions.
About this workflow
Telegram bot. Uses telegramTrigger, embeddingsOllama, lmChatOllama, toolVectorStore. Event-driven trigger; 26 nodes.
Source: https://github.com/jtmckay/existential/blob/main/graveyard/n8n/workflows/workflow_01_telegram_bot.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.
HR & IT Helpdesk Chatbot with Audio Transcription. Uses stickyNote, manualTrigger, httpRequest, extractFromFile. Event-driven trigger; 27 nodes.
HTTP Request, Vector Store Pgvector, OpenAI Embeddings +9
HR & IT Helpdesk Chatbot with Audio Transcription. Uses stickyNote, manualTrigger, httpRequest, extractFromFile. Event-driven trigger; 27 nodes.
HTTP Request, Vector Store Pgvector, OpenAI Embeddings +9
An intelligent chatbot that assists employees by answering common HR or IT questions, supporting both text and audio messages. This unique feature ensures employees can conveniently ask questions via
HTTP Request, Vector Store Pgvector, OpenAI Embeddings +9
Local RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +9
V1 ocal RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Event-driven trigger; 24 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +9