This workflow follows the Agent → Cohere 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 →
{
"name": "INM_clase_2_flujo_2_raiway",
"nodes": [
{
"parameters": {
"promptType": "define",
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "\"Eres el HR Buddy, asistente virtual de RR. HH. de ChocolaTech.\nREGLAS:\n\nResponde siempre en espa\u00f1ol.\nResponde SOLO dudas relacionadas con RR. HH.\nIDENTIFICACI\u00d3N DEL EMPLEADO:\nSi el usuario no dice qui\u00e9n es, preg\u00fantale su nombre completo en la primera respuesta.\nUsa la herramienta MySQL para buscar en la tabla funcionarios usando SIEMPRE el NOMBRE COMPLETO informado por el usuario en la conversaci\u00f3n.\nSi se encuentra: usa los saldos de vacaciones y banco de horas.\nSi no se encuentra: no inventes datos personales. Responde solo con base en las pol\u00edticas generales de RR. HH. del Vector Store.\nUsa la base de conocimientos para dudas generales.\""
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 3.1,
"position": [
576,
0
],
"id": "61e9a43e-85c7-4b84-9b6c-b733136e8c77",
"name": "AI Agent"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatCohere",
"typeVersion": 1,
"position": [
416,
224
],
"id": "71149e49-5e1f-4169-ba8d-e94eb1822629",
"name": "Cohere Chat Model",
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $json.message.from.id }}"
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.4,
"position": [
544,
224
],
"id": "bfbd01c0-6856-4549-91a1-67a2b9afafc7",
"name": "Simple Memory"
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "Buscar informacion sobre RH, asuntos con vacaciones, horarios, etc.",
"memoryKey": {
"__rl": true,
"mode": "list",
"value": "vector_store_key"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory",
"typeVersion": 1.3,
"position": [
672,
224
],
"id": "0f44932f-ca58-4270-b69d-9ce134534364",
"name": "Simple Vector Store"
},
{
"parameters": {
"modelName": "embed-multilingual-v3.0"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsCohere",
"typeVersion": 1,
"position": [
752,
432
],
"id": "b0f46d18-62d6-4e21-a2fe-ccfa850558ba",
"name": "Embeddings Cohere",
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "select",
"table": {
"__rl": true,
"value": "empleados",
"mode": "list",
"cachedResultName": "empleados"
},
"where": {
"values": [
{
"column": "nombre",
"condition": "LIKE",
"value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('values0_Value', `Usa siempre el formato %nombre% para busqueda parcial. por ejemplo : %Eric Monn\u00e9%`, 'string') }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.mySqlTool",
"typeVersion": 2.5,
"position": [
960,
224
],
"id": "9cea5e79-10a0-48c3-a190-df413c37c5c1",
"name": "Select rows from a table in MySQL",
"credentials": {
"mySql": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"type": "n8n-nodes-base.telegramTrigger",
"typeVersion": 1.3,
"position": [
192,
0
],
"id": "ad17a949-f56d-4b84-8268-8c69a92077d8",
"name": "Telegram Trigger",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"text": "={{ $json.output }}",
"additionalFields": {}
},
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
1168,
0
],
"id": "e70b9308-bdb7-40fc-abe0-733073fc5f51",
"name": "Send a text message",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Cohere Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Simple Vector Store": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Embeddings Cohere": {
"ai_embedding": [
[
{
"node": "Simple Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Select rows from a table in MySQL": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Send a text message",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "7ac6ebb1-d2a6-4fb2-9f5e-58f7dd362a9b",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "f08VqEKE3qNJ8FZa",
"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.
cohereApimySqltelegramApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
INM_clase_2_flujo_2_raiway. Uses agent, lmChatCohere, memoryBufferWindow, vectorStoreInMemory. Event-driven trigger; 8 nodes.
Source: https://github.com/CarolinaChambique/telegram-ai-agent-rag/blob/main/INM_clase_2_flujo_2_raiway.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.
Description 📌 Overview
Alfred (funcional). Uses gmailTool, googleCalendarTool, gmail, embeddingsOpenAi. Event-driven trigger; 83 nodes.
/billing - For payment and invoice questions /tech-support - For technical assistance /return-policy - For returns and refunds Command-based routing Direct department access via slash commands Tracks
This workflow transforms your Telegram bot into J.A.R.V.I.S., a powerful, multimodal AI assistant. It can understand and process text, voice messages, images, and documents. The assistant can search t
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.