This workflow follows the Agent → Chat Trigger 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": "Reranker",
"nodes": [
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "1ihasqbcDf8vv_JpQOjFsCc6K-amHK_B5",
"mode": "list",
"cachedResultName": "Reglas Golf (Simplificadas).pdf",
"cachedResultUrl": "https://drive.google.com/file/d/1ihasqbcDf8vv_JpQOjFsCc6K-amHK_B5/view?usp=drivesdk"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
380,
-380
],
"id": "7e5a111b-7c56-49cc-829a-904165636dec",
"name": "Download File",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsonMode": "expressionData",
"jsonData": "={{ $('Code').item.json.fullText }}",
"options": {
"metadata": {
"metadataValues": [
{
"name": "ruleNumber",
"value": "={{ $json.ruleNumber }}"
}
]
}
}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
940,
-240
],
"id": "a8041f32-eaf4-411c-a3b5-132c948ef70f",
"name": "Default Data Loader"
},
{
"parameters": {
"operation": "pdf",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
520,
-380
],
"id": "7f61c56a-5617-4233-a833-d31da60f8548",
"name": "Extract from File"
},
{
"parameters": {
"jsCode": "// \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n// n8n Code Node \u2013 Dividir \u00abRegla X\u00bb en \u00edtems independientes\n// Entrada : 1er \u00edtem \u2192 .json.text (todas las reglas juntas)\n// Salida : un \u00edtem por regla, con n\u00famero, t\u00edtulo, texto completo e \u00edndice\n// \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n\n/** 1. Obtener el texto completo */\nconst inputText = $input.first().json.text ?? '';\nif (!inputText) {\n\tthrow new Error('El campo json.text est\u00e1 vac\u00edo o no existe');\n}\n\n/** 2. Partir por \u201cRegla N\u201d (look-ahead para conservar el encabezado) */\nconst ruleSections = inputText.split(/(?=Regla\\s+\\d+)/);\n\n/** 3. Limpiar posibles elementos vac\u00edos (antes de la primera regla) */\nconst cleaned = ruleSections.filter(sec => sec.trim().startsWith('Regla'));\n\n/** 4. Crear los \u00edtems de salida */\nconst outputItems = cleaned.map((ruleText, idx) => {\n\n\t// 4-a) N\u00famero de regla\n\tconst nMatch = ruleText.match(/Regla\\s+(\\d+)/);\n\tconst ruleNumber = nMatch ? nMatch[1] : String(idx + 1);\n\n\t// 4-b) T\u00edtulo (lo que va tras el guion y antes del salto de l\u00ednea)\n\t// Ejemplo: \"Regla 3 - Stroke Play (Juego por Golpes)\"\n\tconst tMatch = ruleText.match(/Regla\\s+\\d+\\s*[-\u2013]\\s*(.+?)(?:\\n|$)/);\n\tconst ruleTitle = tMatch ? tMatch[1].trim() : 'T\u00edtulo no encontrado';\n\n\treturn {\n\t\tjson: {\n\t\t\truleNumber, // \"3\"\n\t\t\truleTitle, // \"Stroke Play (Juego por Golpes)\"\n\t\t\tfullText: ruleText.trim(),\n\t\t\toriginalIndex: idx // 0-based\n\t\t},\n\t};\n});\n\n/** 5. Devolver el array de \u00edtems */\nreturn outputItems;\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
660,
-380
],
"id": "45032551-fd6b-4d4e-8f41-62e0107eb8ed",
"name": "Code"
},
{
"parameters": {
"mode": "insert",
"tableName": {
"__rl": true,
"value": "documents",
"mode": "list",
"cachedResultName": "documents"
},
"options": {
"queryName": "match_documents"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.3,
"position": [
800,
-380
],
"id": "4747a478-baba-4a7d-89fa-954878bb252b",
"name": "Upload to Supabase",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "Use this tool to search the database",
"tableName": {
"__rl": true,
"value": "documents",
"mode": "list",
"cachedResultName": "documents"
},
"topK": 20,
"useReranker": true,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.3,
"position": [
320,
-860
],
"id": "68ec21f6-56fa-47ab-a763-df662b47ce4a",
"name": "Supabase Vector Store",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.rerankerCohere",
"typeVersion": 1,
"position": [
1780,
-720
],
"id": "1da7bad2-878e-42dc-b11c-df22f63a1f97",
"name": "Reranker Cohere1",
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
1620,
-720
],
"id": "d17c5210-4179-4213-b64b-f774bd3907ed",
"name": "Embeddings OpenAI2",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "Use this tool to search the database",
"tableName": {
"__rl": true,
"value": "documents",
"mode": "list",
"cachedResultName": "documents"
},
"topK": 20,
"useReranker": true,
"options": {
"metadata": {
"metadataValues": [
{
"name": "ruleNumber",
"value": "={{ $('Metadata Agent').item.json.output }}"
}
]
}
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.3,
"position": [
1620,
-860
],
"id": "f86e7e0b-791f-49af-bb9b-6a25e8c3c412",
"name": "Supabase Vector Store1",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "# Vectorizar Documentos \u00ac Metadata\n(Para este ejemplo)",
"height": 440,
"width": 1000,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
160,
-520
],
"id": "85508042-db85-4eec-838f-27482666c5f7",
"name": "Sticky Note"
},
{
"parameters": {
"content": "# Agente RAG\n",
"height": 380,
"width": 620,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-360,
-960
],
"id": "26eab455-f52e-4d59-a424-fe35b6185649",
"name": "Sticky Note1"
},
{
"parameters": {
"content": "## Vector Store Tool & Reranker\n",
"height": 380,
"width": 380,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
260,
-960
],
"id": "db4d58c3-bb8c-48cc-807d-fd5393333d5c",
"name": "Sticky Note2"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
780,
-240
],
"id": "da3d27df-72de-47db-ad22-f43f10624595",
"name": "Embeddings OpenAI1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
320,
-720
],
"id": "eb3a2117-7888-4a0e-a076-682fe551db2f",
"name": "Embeddings OpenAI",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview\nYour job is to understand the rule number that the human is requesting and output only the number.\n\n## Example\nInput - what's rule number 27?\nOutput - 27"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2,
"position": [
780,
-860
],
"id": "6476531d-7762-457e-90f8-75703e229488",
"name": "Metadata Agent"
},
{
"parameters": {
"options": {
"systemMessage": "=# Overview\nYou are an AI agent who is an expert at the rules of golf. You will receive a question from the human, and you must use your tool called \"Supabase Vector Store\" in order to retrieve information from the database to make sure you are answering the question accurately. "
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2,
"position": [
-120,
-860
],
"id": "3a708f5e-1e6f-4ec5-98e2-5280a4733c88",
"name": "RAG Agent"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('When chat message received').item.json.chatInput }}",
"options": {
"systemMessage": "=# Overview\nYou are an AI agent who is an expert at the rules of golf. You will receive a question from the human, and you must use your tool called \"Supabase Vector Store\" in order to retrieve information from the database to make sure you are answering the question accurately. "
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2,
"position": [
1200,
-860
],
"id": "e1a32998-3bd1-4e65-91e9-e368c3212df4",
"name": "RAG Agent 2"
},
{
"parameters": {
"content": "# Agente RAG\n",
"height": 380,
"width": 440,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
1120,
-960
],
"id": "a4d590cd-321f-40d5-aea3-acccbc58c30a",
"name": "Sticky Note3"
},
{
"parameters": {
"content": "## Vector Store Tool & Reranker Metadata\n",
"height": 380,
"width": 380,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
1560,
-960
],
"id": "e05c9fec-ccef-4046-b30e-59ac4c6f48dd",
"name": "Sticky Note4"
},
{
"parameters": {
"content": "# Agente Metadata\n",
"height": 380,
"width": 420,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
700,
-960
],
"id": "01e52d83-9aee-498a-b0ae-14397a003a4e",
"name": "Sticky Note5"
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
240,
-380
],
"id": "c4647870-1c31-409d-b355-837647392a29",
"name": "Manual Trigger"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
-60,
-720
],
"id": "719114a7-7d7d-4103-8102-fa014b5272f2",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
840,
-720
],
"id": "5ac6fb67-7722-45f9-ac1c-65aae041ec20",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
1260,
-720
],
"id": "05fb2e6c-e926-40b8-8b8e-9dca514dd5aa",
"name": "OpenAI Chat Model2",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.rerankerCohere",
"typeVersion": 1,
"position": [
480,
-720
],
"id": "7623668f-8554-4702-8da0-798fc5165d3e",
"name": "Reranker Cohere",
"credentials": {
"cohereApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-280,
-860
],
"id": "fec22e6d-4f3c-4183-b28e-899f26f8b708",
"name": "When chat message received"
}
],
"connections": {
"Download File": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Upload to Supabase",
"type": "ai_document",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "Upload to Supabase",
"type": "main",
"index": 0
}
]
]
},
"Supabase Vector Store": {
"ai_tool": [
[
{
"node": "RAG Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Reranker Cohere1": {
"ai_reranker": [
[
{
"node": "Supabase Vector Store1",
"type": "ai_reranker",
"index": 0
}
]
]
},
"Embeddings OpenAI2": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Supabase Vector Store1": {
"ai_tool": [
[
{
"node": "RAG Agent 2",
"type": "ai_tool",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Upload to Supabase",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Metadata Agent": {
"main": [
[
{
"node": "RAG Agent 2",
"type": "main",
"index": 0
}
]
]
},
"Manual Trigger": {
"main": [
[
{
"node": "Download File",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "RAG Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Metadata Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model2": {
"ai_languageModel": [
[
{
"node": "RAG Agent 2",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Reranker Cohere": {
"ai_reranker": [
[
{
"node": "Supabase Vector Store",
"type": "ai_reranker",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "RAG Agent",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "0b5f14c0-32be-40c3-98f4-26487be67a4d",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "T0wqayb9Q79XWZrS",
"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.
cohereApigoogleDriveOAuth2ApiopenAiApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Reranker. Uses googleDrive, documentDefaultDataLoader, vectorStoreSupabase, rerankerCohere. Event-driven trigger; 26 nodes.
Source: https://github.com/JOSEMARIAAUMA/JSON_PLANTILLAS/blob/1bcfa140d5a84f8dadad80c22963eec9d5e4c1fb/Reranker.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.
Your AI workforce is ready. Are you?
Google Sheets Tool, Mcp Trigger, Google Drive +29
This intelligent chatbot leverages cutting-edge financial APIs and AI-driven analysis to deliver comprehensive stock research reports. Get instant access to professional-grade investment analysis that
Tool Think, Supabase Vector Store, OpenAI Embeddings +15
Automate Outreach Prospect automates finding, enriching, and messaging potential partners (like restaurants, malls, and bars) using Apify Google Maps scraping, Perplexity enrichment, OpenAI LLMs, Goog
@Devlikeapro/N8N Nodes Waha, Google Drive Trigger, @Apify/N8N Nodes Apify +14
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