This workflow follows the Chainllm → 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": "04-SMS-Capture",
"nodes": [
{
"id": "webhook",
"name": "Webhook - SMS Incoming",
"type": "n8n-nodes-base.webhook",
"position": [
200,
300
],
"parameters": {
"httpMethod": "POST",
"path": "sms-capture",
"responseMode": "responseNode",
"options": {}
},
"typeVersion": 2
},
{
"id": "ollama",
"name": "Ollama Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"position": [
500,
500
],
"parameters": {
"model": "mistral:7b",
"options": {
"temperature": 0.1
}
},
"typeVersion": 1
},
{
"id": "llm",
"name": "Parse SMS",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
500,
300
],
"parameters": {
"text": "You are a financial SMS parser. Parse this Indian bank SMS and return ONLY a valid JSON object.\n\nSMS From: {{ $json.from }}\nSMS Text: {{ $json.text }}\n\nReturn ONLY JSON in this exact format:\n{\"amount\": number, \"currency\": \"INR\", \"transaction_type\": \"DEBIT or CREDIT\", \"merchant_name\": \"brand or null\", \"bank_name\": \"bank or null\", \"account_last4\": \"4 digits or null\", \"category\": \"groceries/utilities/transport/food/entertainment/medical/education/rent/shopping/salary/transfer/fuel/insurance/emi/other\", \"date\": \"YYYY-MM-DD\", \"time\": \"HH:MM or null\"}\n\nRules:\n- amount: number only (no Rs/INR/commas)\n- If field not found, use null\n- Return ONLY the JSON object, no explanation, no markdown",
"options": {
"systemMessage": "You parse Indian bank SMS messages. Always return valid JSON only."
}
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "insert_txn",
"name": "Insert Transaction",
"type": "n8n-nodes-base.httpRequest",
"position": [
750,
300
],
"parameters": {
"url": "http://transaction-api:8090/transactions",
"method": "POST",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"amount\": {{ $json.output.amount }},\n \"currency\": \"{{ $json.output.currency }}\",\n \"transaction_type\": \"{{ $json.output.transaction_type }}\",\n \"merchant_name\": \"{{ $json.output.merchant_name }}\",\n \"bank_name\": \"{{ $json.output.bank_name }}\",\n \"account_identifier\": \"{{ $json.output.account_last4 }}\",\n \"category\": \"{{ $json.output.category }}\",\n \"transaction_date\": \"{{ $json.output.date }}\",\n \"source\": \"bank_sms\",\n \"raw_text\": \"{{ $('Webhook - SMS Incoming').first().json.text }}\"\n}",
"options": {
"timeout": 15000
}
},
"typeVersion": 4.4
},
{
"id": "respond",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
1000,
300
],
"parameters": {
"respondWith": "json",
"responseBody": "={{ { 'success': true, 'amount': $json.output.amount, 'category': $json.output.category } }}"
},
"typeVersion": 1
}
],
"connections": {
"Webhook - SMS Incoming": {
"main": [
[
{
"node": "Parse SMS",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "Parse SMS",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Parse SMS": {
"main": [
[
{
"node": "Insert Transaction",
"type": "main",
"index": 0
}
]
]
},
"Insert Transaction": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
04-SMS-Capture. Uses lmChatOllama, chainLlm, httpRequest. Webhook trigger; 5 nodes.
Source: https://github.com/Santhosh-Manoharan/OmniTrack/blob/2623de8f1c434039baf67f270b0e539152b6fde3/n8n-workflows/04-SMS-Capture.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.
Receive WhatsApp messages via Whapi, generate AI replies with a local Ollama model, log conversations in Google Sheets, and auto-capture leads — all without touching a cloud LLM.
Nexus Omnichannel Router V5.1 (Refined) - Audit Mode. Uses chainLlm, lmChatOllama, httpRequest. Webhook trigger; 10 nodes.
This workflow receives YouTube Shorts webhook events, downloads the video via Apify, uses Google Gemini and an OpenAI-compatible chat model to generate Pinterest SEO metadata and choose a board, then
My Workflow. Uses httpRequest, chatTrigger, chainLlm, lmChatGoogleGemini. Webhook trigger; 5 nodes.
Planning Assistant 2. Uses httpRequest, chainLlm, lmChatMistralCloud, outputParserStructured. Webhook trigger; 5 nodes.