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": [
{
"parameters": {
"promptType": "define",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.8,
"position": [
-16,
-896
],
"id": "c8d77577-bafc-486d-9705-7f7f01fa2691",
"name": "Inference A",
"notes": "{\"taskType\": \"inference\"}"
},
{
"parameters": {
"model": "meta-llama/Llama-3.2-1B-Instruct",
"options": {
"maxTokens": 128,
"temperature": 1,
"topK": 1,
"topP": 1
}
},
"type": "@n8n/n8n-nodes-langchain.lmOpenHuggingFaceInference",
"typeVersion": 1,
"position": [
-16,
-736
],
"id": "ddbfcacc-b5b5-4167-8373-31e7ae2bfbef",
"name": "Model Spec A",
"credentials": {
"huggingFaceApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"type\": \"list\",\n \"items\": [\n \"List three long-term benefits of transitioning to renewable energy.\"\n ]\n}",
"options": {
"dotNotation": false
}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-176,
-896
],
"id": "bd30c2d8-f512-4a95-9721-1de7c86daee3",
"name": "Input A"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"tensor_parallel_size\": 1,\n \"gpu_memory_utilization\": 0.9,\n \"trust_remote_code\": true\n}",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-32,
-1040
],
"id": "c2f905a0-84c7-4a4a-b35c-63dd3fd78c31",
"name": "Runtime Spec A"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"hardware\": {\n \"cpu\": \"8\",\n \"memory\": \"32Gi\",\n \"gpu\": {\n \"type\": \"any\",\n \"count\": 1\n }\n }\n}\n",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
128,
-1040
],
"id": "25bb0591-af79-4c90-827e-661554cc3649",
"name": "Resource Spec A"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"type\": \"list\",\n \"items\": [\n \"Identify two major challenges organizations face when adopting renewable energy.\"\n ]\n}",
"options": {
"dotNotation": false
}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-176,
-464
],
"id": "afe6841b-eba0-47e2-921e-b7a520172800",
"name": "Input B"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"tensor_parallel_size\": 1,\n \"gpu_memory_utilization\": 0.9,\n \"trust_remote_code\": true\n}",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-16,
-608
],
"id": "4dacdaec-6b5f-4b62-8930-becd684dbf70",
"name": "Runtime Spec B"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"hardware\": {\n \"cpu\": \"8\",\n \"memory\": \"32Gi\",\n \"gpu\": {\n \"type\": \"any\",\n \"count\": 1\n }\n }\n}\n",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
144,
-608
],
"id": "e6f83719-9e22-4d7a-a298-e6e5253fbf49",
"name": "Resource Spec B"
},
{
"parameters": {
"model": "meta-llama/Llama-3.2-1B-Instruct",
"options": {
"maxTokens": 128,
"temperature": 1,
"topK": 1,
"topP": 1
}
},
"type": "@n8n/n8n-nodes-langchain.lmOpenHuggingFaceInference",
"typeVersion": 1,
"position": [
0,
-304
],
"id": "6ae94922-1702-4c77-9228-99f5b7de4121",
"name": "Model Spec B",
"credentials": {
"huggingFaceApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"type\": \"graph_template\",\n \"template\": {\n \"name\": \"two_column_briefing\",\n \"columns\": [\n {\n \"label\": \"Benefits insight\",\n \"node\": \"Inference A\",\n \"path\": \"items[0].output\"\n },\n {\n \"label\": \"Challenges insight\",\n \"node\": \"Inference B\",\n \"path\": \"items[0].output\"\n }\n ]\n }\n }",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
352,
-720
],
"id": "39bf2958-fd88-48e3-b31b-5f66fcfda5f9",
"name": "Format"
},
{
"parameters": {
"promptType": "define",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.8,
"position": [
0,
-464
],
"id": "c8cf547c-38e1-4d7c-9c12-6bd4e62dc0d6",
"name": "Inference B",
"notes": "{\"taskType\": \"inference\"}"
},
{
"parameters": {
"promptType": "define",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.8,
"position": [
528,
-720
],
"id": "b72d5b93-d9fd-4e66-868e-1a5ecf16e6b4",
"name": "Synthesis",
"notes": "{\"taskType\": \"inference\"}"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"tensor_parallel_size\": 1,\n \"gpu_memory_utilization\": 0.9,\n \"trust_remote_code\": true\n}",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
496,
-896
],
"id": "26953702-1736-4d9a-8c17-ba6523ded5db",
"name": "Runtime Spec S"
},
{
"parameters": {
"mode": "raw",
"jsonOutput": "{\n \"hardware\": {\n \"cpu\": \"8\",\n \"memory\": \"32Gi\",\n \"gpu\": {\n \"type\": \"any\",\n \"count\": 1\n }\n }\n}\n",
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
656,
-896
],
"id": "ac3519b9-0f58-40ef-9edd-9712792577d8",
"name": "Resource Spec S"
},
{
"parameters": {
"model": "meta-llama/Llama-3.2-1B-Instruct",
"options": {
"maxTokens": 128,
"temperature": 1,
"topK": 1,
"topP": 1
}
},
"type": "@n8n/n8n-nodes-langchain.lmOpenHuggingFaceInference",
"typeVersion": 1,
"position": [
528,
-544
],
"id": "477f4948-b75a-44e3-9ed0-2f183bfa0a8e",
"name": "Model Spec S1",
"credentials": {
"huggingFaceApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-350,
-896
],
"id": "9d4aeb2d-0407-479c-a94b-067197a44839",
"name": "When clicking \u2018Execute workflow\u2019"
}
],
"connections": {
"Inference A": {
"main": [
[
{
"node": "Format",
"type": "main",
"index": 0
}
]
]
},
"Model Spec A": {
"ai_languageModel": [
[
{
"node": "Inference A",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Input A": {
"main": [
[
{
"node": "Inference A",
"type": "main",
"index": 0
}
]
]
},
"Runtime Spec A": {
"main": [
[
{
"node": "Inference A",
"type": "main",
"index": 0
}
]
]
},
"Resource Spec A": {
"main": [
[
{
"node": "Inference A",
"type": "main",
"index": 0
}
]
]
},
"Input B": {
"main": [
[
{
"node": "Inference B",
"type": "main",
"index": 0
}
]
]
},
"Runtime Spec B": {
"main": [
[
{
"node": "Inference B",
"type": "main",
"index": 0
}
]
]
},
"Resource Spec B": {
"main": [
[
{
"node": "Inference B",
"type": "main",
"index": 0
}
]
]
},
"Model Spec B": {
"ai_languageModel": [
[
{
"node": "Inference B",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Format": {
"main": [
[
{
"node": "Synthesis",
"type": "main",
"index": 0
}
]
]
},
"Inference B": {
"main": [
[
{
"node": "Format",
"type": "main",
"index": 0
}
]
]
},
"Runtime Spec S": {
"main": [
[
{
"node": "Synthesis",
"type": "main",
"index": 0
}
]
]
},
"Resource Spec S": {
"main": [
[
{
"node": "Synthesis",
"type": "main",
"index": 0
}
]
]
},
"Model Spec S1": {
"ai_languageModel": [
[
{
"node": "Synthesis",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Input A",
"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.
huggingFaceApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Dag Inference. Uses chainLlm, lmOpenHuggingFaceInference. Event-driven trigger; 16 nodes.
Source: https://github.com/mlsys-io/FlowMesh/blob/4e50132d802ed23dcc4fab8a043d94d024915046/examples/templates/n8n/dag_inference.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.
Episode 11: AI shorts factory app. Uses httpRequest, googleSheets, lmChatOpenAi, lmChatOllama. Event-driven trigger; 96 nodes.
HTTP Request, Google Sheets, OpenAI Chat +15
This workflow creates a multi-talented AI assistant named Simran that interacts with users via Telegram. It can handle text and voice messages, understand the user's intent, and perform various tasks.
MongoDB, Chain Llm, Google Gemini Chat +11
This workflow automates Invoice & Payment Tracking (with Approvals) across Notion and Slack. Ingest — You drop invoices/receipts (PDF/IMG/JSON) into the flow. Extract — OCR + parsing pulls out key fie
HTTP Request, Chain Llm, Anthropic Chat +5
Content - Newsletter Agent. Uses formTrigger, chainLlm, outputParserStructured, httpRequest. Event-driven trigger; 91 nodes.
Form Trigger, Chain Llm, Output Parser Structured +8
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