This workflow follows the Agent → Chainllm 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": "ejemplo RAG vs CRAG",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-1340,
-460
],
"id": "ed97f20e-8c3e-4269-8db4-80a7ab07f18f",
"name": "When clicking \u2018Test workflow\u2019"
},
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "1QpF2zj4Dsa2Mc40P3ZyfHzUIowG5S97k",
"mode": "list",
"cachedResultName": "Toward Autonomic Internet of Things_Recent Advances, Evaluation Criteria,_and Future Research Directions.grobid.tei.xml",
"cachedResultUrl": "https://drive.google.com/file/d/1QpF2zj4Dsa2Mc40P3ZyfHzUIowG5S97k/view?usp=drivesdk"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
-420,
-200
],
"id": "2555909c-50d2-4b65-8494-d24e710d1c63",
"name": "Google Drive",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "insert",
"qdrantCollection": {
"__rl": true,
"value": "=prueba_CRAG",
"mode": "id"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.1,
"position": [
100,
320
],
"id": "583c96cd-40b9-4c35-bb53-ab8b596953dc",
"name": "Qdrant Vector Store",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
0,
520
],
"id": "32e58937-54b6-4b30-9700-98afea25065a",
"name": "Embeddings Ollama",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"promptType": "define",
"text": "=I have a question related to the contents of a research paper. Please use only the infopapers tool to answer.\n\nMy question:\n{{ $json.chatInput }}",
"options": {
"systemMessage": "You are a specialized AI assistant. Your **ONLY** source of knowledge is the RAG tool named **\"infopapers\"**, which queries a specific vector store. Do **not** use your internal pre-trained knowledge.\n\n**Key Instructions:**\n\n1. **Mandatory Query:** For **ANY** user question that requires information from papers or specific data, you **MUST** invoke and use the **\"infopapers\"** tool.\n\n2. **Present the Result Directly:** Once the **\"infopapers\"** tool returns information, your response **MUST** consist of presenting that information **directly** to the user. Base your answer **ONLY and EXCLUSIVELY** on the data retrieved by the tool. Do **not** add comments, external information, or use general knowledge.\n\n3. **Handling Missing Information:** If the **\"infopapers\"** tool explicitly indicates that the information is not available or does not return any relevant data for the question, you **MUST** clearly and directly inform the user that the information is not available in the consulted knowledge base. **Do not** invent, assume, or speculate.\n\n4. **Faithfulness to the Result:** Your role is to be a faithful interface to the results of the **\"infopapers\"** tool. If the tool gives an answer, your job is to communicate it as-is.\n\n**Simple Process:** Receive question \u2192 Call **\"infopapers\"** \u2192 Check **infopapers** result. \n**IF** relevant result: present it as-is. \n**IF NOT**: inform that no relevant information was found. \nDo **nothing else**.",
"maxIterations": 10,
"returnIntermediateSteps": true,
"passthroughBinaryImages": false
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.8,
"position": [
-1500,
1060
],
"id": "5ae1fcbd-abd4-48d9-bbe0-1c509bf2ae3c",
"name": "AI Agent"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
-1420,
1280
],
"id": "b0edeeba-d97a-4dc9-9138-b14b8ce0708d",
"name": "Simple Memory"
},
{
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
-1540,
1280
],
"id": "d963fb4d-7c73-4975-8b0f-3d30e0d9f02c",
"name": "Ollama Chat Model1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"qdrantCollection": {
"__rl": true,
"value": "prueba_CRAG",
"mode": "list",
"cachedResultName": "prueba_CRAG"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.1,
"position": [
-1400,
1480
],
"id": "2de2d76b-70f9-4b87-aa1f-d8182b788317",
"name": "Qdrant Vector Store1",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
-1320,
1680
],
"id": "bc9873d4-cf73-49a6-863a-ba3b80c30553",
"name": "Embeddings Ollama2",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-1760,
1060
],
"id": "48331bd5-3a78-4c6d-b3f1-339bbd2cfef1",
"name": "When chat message received"
},
{
"parameters": {
"name": "infopapers",
"description": "It contains all the papers you can consult to get context and answer the user's questions.",
"topK": 10
},
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
-1300,
1280
],
"id": "3ee9930b-6c6b-47da-908d-9096ba499a92",
"name": "Answer questions with a vector store"
},
{
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"typeVersion": 1,
"position": [
-1120,
1480
],
"id": "47caa540-1290-4d19-a5a9-e5d36763822c",
"name": "Ollama Model",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "# EJEMPLO C-RAG",
"height": 1120,
"width": 1720,
"color": 3
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-1240,
-260
],
"typeVersion": 1,
"id": "5cceccd1-df8a-46ee-8ab5-b62be8ab8708",
"name": "Sticky Note"
},
{
"parameters": {
"content": "# USUARIO",
"height": 880,
"width": 1190,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-1880,
960
],
"typeVersion": 1,
"id": "c2658da5-cb47-45d5-ac1d-25c6cc5c2c04",
"name": "Sticky Note1"
},
{
"parameters": {
"jsCode": "return [{\n json: {\n text: $json.intermediateSteps[0].observation\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-900,
1060
],
"id": "b297ad13-d7a2-4a89-ba74-d57934a1a952",
"name": "Code"
},
{
"parameters": {
"content": "# EJEMPLO RAG\n",
"height": 1120,
"width": 1580
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-2880,
-260
],
"typeVersion": 1,
"id": "3d9352ef-372e-4aab-8ab5-0428894b33b2",
"name": "Sticky Note2"
},
{
"parameters": {
"chunkSize": 5000,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
300,
700
],
"id": "fa9f139a-9627-49de-a8fa-0d3684cb6e7d",
"name": "Recursive Character Text Splitter"
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const text = $json.data.replace(/\\n/g, ' ');\n\n// 1. Partimos en oraciones (capturamos tambi\u00e9n el espacio que sigue al punto o signo)\nconst sentences = text.match(/[^\\.!\\?]+[\\.!\\?]+(\\s|$)/g) || [];\n\nconst chunks = [];\nconst chunkSize = 1000;\nlet current = '';\n\nfor (const sentence of sentences) {\n // Si a\u00f1adiendo esta oraci\u00f3n supera el tama\u00f1o deseado,\n // cerramos el chunk actual y arrancamos uno nuevo.\n if ((current + sentence).length > chunkSize) {\n if (current) {\n chunks.push(current.trim());\n }\n current = sentence;\n } else {\n current += sentence;\n }\n}\n\n// A\u00f1adimos el \u00faltimo trozo si qued\u00f3 algo\nif (current) {\n chunks.push(current.trim());\n}\n\nreturn { chunks };"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-1060,
280
],
"id": "f05a92f5-8eea-445f-be8d-05f85918d4da",
"name": "Dividir chunks"
},
{
"parameters": {
"fieldToSplitOut": "chunks",
"options": {}
},
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
-800,
280
],
"id": "2042cb3b-b0bd-4d5e-be2d-d567949f2fc5",
"name": "Separar lista"
},
{
"parameters": {
"batchSize": 5,
"options": {
"reset": false
}
},
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
-580,
280
],
"id": "aa349368-4210-4409-bb44-3376a1479c6a",
"name": "Loop"
},
{
"parameters": {
"promptType": "define",
"text": "=<document> \n{{ $('Extract from File1').item.json.data }}\n</document>\nAqu\u00ed est\u00e1 el fragmento que queremos ubicar dentro del documento completo\n<chunk> \n{{ $json.chunks }}\n</chunk> \nPor favor, proporciona un contexto breve y conciso para ubicar este fragmento dentro del documento general con el fin de mejorar el Retrieval Augmented Generation. Responde solo con el contexto conciso y nada m\u00e1s."
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.6,
"position": [
-360,
160
],
"id": "7e7ef704-5688-4288-b48f-7550d1adcb5a",
"name": "Crear contexto",
"retryOnFail": true,
"waitBetweenTries": 5000
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{\n{\n \"content\": `${ $json.text }\\n---\\n${ $('Separar lista').item.json.chunks }`\n}\n}}",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1,
"position": [
180,
540
],
"id": "863b0e01-f7f7-455a-bd99-f2c97a7623ba",
"name": "Default Data Loader1"
},
{
"parameters": {
"operation": "xml",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-200,
-200
],
"id": "10f66bc1-859a-43cd-8e6c-0d0a2f616a78",
"name": "Extract from File1"
},
{
"parameters": {
"model": "llama3.1:8b",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"typeVersion": 1,
"position": [
-220,
300
],
"id": "fd6a3f35-7ad0-4127-b1fc-2baf7f464fbb",
"name": "Ollama Model1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "1QpF2zj4Dsa2Mc40P3ZyfHzUIowG5S97k",
"mode": "list",
"cachedResultName": "Toward Autonomic Internet of Things_Recent Advances, Evaluation Criteria,_and Future Research Directions.grobid.tei.xml",
"cachedResultUrl": "https://drive.google.com/file/d/1QpF2zj4Dsa2Mc40P3ZyfHzUIowG5S97k/view?usp=drivesdk"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
-2640,
140
],
"id": "e2bdf87a-cb41-40bf-8f7b-e73993596dbc",
"name": "Google Drive1",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "insert",
"qdrantCollection": {
"__rl": true,
"value": "=prueba_RAG",
"mode": "id"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1.1,
"position": [
-1840,
20
],
"id": "62b5c253-47ca-4d5b-b36e-05c3dfcbc6ff",
"name": "Qdrant Vector Store2",
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
-1940,
220
],
"id": "f74562a2-7a1e-41a2-b9b7-fa92f9c2182c",
"name": "Embeddings Ollama1",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"chunkSize": 5000,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
-1640,
400
],
"id": "c29fe34b-c6d1-4978-8dd2-639086ec4f58",
"name": "Recursive Character Text Splitter1"
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{\n{\n \"content\": `${ $json.text }\\n---\\n${ $('Separar lista1').item.json.chunks }`\n}\n}}",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1,
"position": [
-1760,
240
],
"id": "ed438293-4c46-4c86-9943-a42874702cc1",
"name": "Default Data Loader"
},
{
"parameters": {
"operation": "xml",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-2420,
140
],
"id": "c1b2d99c-155a-40ba-bd0d-6fc1d29e3aa3",
"name": "Extract from File"
}
],
"connections": {
"When clicking \u2018Test workflow\u2019": {
"main": [
[]
]
},
"Google Drive": {
"main": [
[
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Ollama Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Qdrant Vector Store1": {
"ai_tool": [
[]
],
"ai_vectorStore": [
[
{
"node": "Answer questions with a vector store",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Embeddings Ollama2": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Answer questions with a vector store": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Ollama Model": {
"ai_languageModel": [
[
{
"node": "Answer questions with a vector store",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader1",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Dividir chunks": {
"main": [
[
{
"node": "Separar lista",
"type": "main",
"index": 0
}
]
]
},
"Separar lista": {
"main": [
[
{
"node": "Loop",
"type": "main",
"index": 0
}
]
]
},
"Loop": {
"main": [
[],
[
{
"node": "Crear contexto",
"type": "main",
"index": 0
}
]
]
},
"Crear contexto": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader1": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Extract from File1": {
"main": [
[
{
"node": "Dividir chunks",
"type": "main",
"index": 0
}
]
]
},
"Ollama Model1": {
"ai_languageModel": [
[
{
"node": "Crear contexto",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"main": [
[
{
"node": "Loop",
"type": "main",
"index": 0
}
]
]
},
"Google Drive1": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Qdrant Vector Store2": {
"main": [
[]
]
},
"Embeddings Ollama1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store2",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Recursive Character Text Splitter1": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store2",
"type": "ai_document",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Qdrant Vector Store2",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "cbd24953-46f1-4882-8cda-dc4cd0f02bd7",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "ejXH95TYwgZr2EiO",
"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.
googleDriveOAuth2ApiollamaApiqdrantApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
ejemplo RAG vs CRAG. Uses googleDrive, vectorStoreQdrant, embeddingsOllama, agent. Event-driven trigger; 30 nodes.
Source: https://github.com/danunziata/pps-kevin_haponiuk-2025/blob/5cd62ce1ee05f04432f000a00a2070962c3c5b88/docs/archivos/ejemplos/ejemplo_RAG_vs_CRAG.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.
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
Code Extractfromfile. Uses manualTrigger, sort, httpRequest, compression. Event-driven trigger; 50 nodes.
HTTP Request, Compression, Edit Image +15
🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant. Uses documentDefaultDataLoader, textSplitterTokenSplitter, vectorStoreQdrant, splitInBatches. Event-driven trigger; 50 nodes.
Document Default Data Loader, Text Splitter Token Splitter, Qdrant Vector Store +10
BambooHR AI-Powered Company Policies and Benefits Chatbot. Uses manualTrigger, documentDefaultDataLoader, embeddingsOpenAi, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 50 nodes.
Document Default Data Loader, OpenAI Embeddings, Text Splitter Recursive Character Text Splitter +14