This workflow follows the Documentdefaultdataloader → 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": "Agente de Procesamiento de Documentos",
"nodes": [
{
"parameters": {
"url": "http://127.0.0.1:8000/api/documentos/pendientes/",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "X-Api-Key",
"value": "4tVC1zrNwl9lD3xM5JO8ugF7DYshwEd-Xy2P0sABCDE"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-1620,
1035
],
"id": "9255d367-1cbe-4b2a-94d7-88fe9e68138a",
"name": "HTTP Request",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"number": [
{
"value1": "={{ $json.documentos.length }}",
"operation": "larger"
}
]
}
},
"name": "\u00bfHay Documentos?",
"type": "n8n-nodes-base.if",
"typeVersion": 1,
"position": [
-1400,
1035
],
"id": "bab21db5-7979-4a71-a037-26736055f021"
},
{
"parameters": {
"options": {
"reset": false
}
},
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
-1180,
1035
],
"id": "56584f97-0794-4729-ba55-f2de62b168ed",
"name": "Loop Over Items",
"retryOnFail": false,
"executeOnce": false,
"notesInFlow": false
},
{
"parameters": {
"url": "={{ $json.datos_recibidos.documentos[0].ruta_documento }}",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-960,
660
],
"id": "00d036d0-7bf9-4516-8c1c-8cf2e66dde9d",
"name": "HTTP Request1"
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.datos_recibidos.documentos[0].tipo_archivo }}",
"rightValue": "application/pdf",
"operator": {
"type": "string",
"operation": "equals"
},
"id": "401e14ae-4b98-477d-b755-565c5c707482"
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "PDF"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "ccbb3571-1a6d-45f9-86e3-b47a1975e1b9",
"leftValue": "={{ $json.datos_recibidos.documentos[0].tipo_archivo }}",
"rightValue": "application/word",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "WORD"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "93df6928-321d-4029-911d-7234bcf647d4",
"leftValue": "={{ $json.datos_recibidos.documentos[0].tipo_archivo }}",
"rightValue": "application/txt",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "TXT"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "42f41a52-41e9-4d42-9474-4641713c3639",
"leftValue": "={{ $json.datos_recibidos.documentos[0].tipo_archivo }}",
"rightValue": "application/xls",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "EXCELL"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
-740,
639
],
"id": "0c50b4d0-faa7-4fac-9f8c-0618f7f79444",
"name": "Switch"
},
{
"parameters": {
"fields": {
"values": [
{
"name": "ocr_data",
"stringValue": "={{ $json.output.ocr_data }}"
},
{
"name": "json_data",
"stringValue": "={{ $json.output.json_data }}"
},
{
"name": "documents_id",
"stringValue": "={{ $('HTTP Request1').item.json.datos_recibidos.documentos[0].documento_id }}"
}
]
},
"include": "none",
"options": {
"includeBinary": false
}
},
"name": "Preparar Datos",
"type": "n8n-nodes-base.set",
"typeVersion": 3.2,
"position": [
76,
660
],
"id": "6b98af93-4911-466d-b72f-ef9b8656eedb"
},
{
"parameters": {
"method": "POST",
"url": "http://127.0.0.1:8000/api/documentos/webhook/",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "documento_id",
"value": "={{ $json.documents_id }}"
},
{
"name": "ocr_data",
"value": "={{ $json.ocr_data }}"
},
{
"name": "json_data",
"value": "={{ $json.json_data }}"
},
{
"name": "status",
"value": "procesando"
}
]
},
"options": {}
},
"name": "Actualizar Documento",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
516,
660
],
"id": "b93277c3-c072-4d3b-ad1f-f7ab348d287a",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "insert",
"tableName": {
"__rl": true,
"value": "documents",
"mode": "list",
"cachedResultName": "documents"
},
"options": {
"queryName": "match_documents"
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.1,
"position": [
760,
660
],
"id": "2e9ddadf-0a0c-4047-aade-189bccb5b2c7",
"name": "Supabase Vector Store",
"alwaysOutputData": true,
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1,
"position": [
856,
882.5
],
"id": "37444caa-22f4-4e56-8876-c2c090760d17",
"name": "Default Data Loader"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
944,
1080
],
"id": "3c51b981-cc9a-40f6-9aae-c1052b2ebf70",
"name": "Recursive Character Text Splitter"
},
{
"parameters": {
"jsCode": "// Este nodo se ejecuta cuando el Loop Over Items termina (no hay m\u00e1s documentos)\nconst input_data = $input.first().json;\n\nconsole.log(\"Loop terminado - datos recibidos:\", input_data);\n\nreturn [{\n json: {\n mensaje: \"Procesamiento de documentos completado\",\n estado: \"finalizado\", \n timestamp: new Date().toISOString(),\n datos_recibidos: input_data\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-960,
960
],
"id": "d6b470ff-98d5-4cfb-956b-8bad3f431f82",
"name": "Verificar Documentos"
},
{
"parameters": {
"content": "## Flujo de Procesamiento de Documentos\n\n1. Consulta documentos pendientes\n2. Descarga y procesa PDFs\n3. Extrae texto con OCR\n4. Analiza con IA para clasificaci\u00f3n\n5. Actualiza estado en Django\n6. Almacena vectores en Supabase",
"height": 267,
"width": 329
},
"name": "Descripci\u00f3n del Flujo",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-1660,
440
],
"id": "aeec9257-aa68-40d3-a424-de085d3a727a"
},
{
"parameters": {
"jsCode": "// Este nodo procesa el resultado despu\u00e9s de completar un documento\n// y permite continuar con el siguiente documento en la cola\n\nconst result = $input.first().json;\n\n// Retorna se\u00f1al para continuar con el siguiente documento\nreturn [{\n json: {\n success: result.success || true,\n document_id: result.document_id || 'N/A',\n cantidad_fragmentos: result.cantidad_fragmentos || 0,\n estado: 'completado',\n continuar_loop: true,\n timestamp: new Date().toISOString()\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1672,
935
],
"id": "257cfa12-54dc-4301-80b0-820a224fa273",
"name": "Finalizar Documento"
},
{
"parameters": {
"operation": "pdf",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-520,
460
],
"id": "8a2c2477-a14b-4608-9d84-7f0c1d93bed6",
"name": "Extract from File"
},
{
"parameters": {
"jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nconst document_id = $input.first().json.pageContent; // o como se llame tu id\nconst cantidad_fragmentos = items.length;\n\nreturn [{\n json: {\n document_id,\n cantidad_fragmentos\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1232,
660
],
"id": "4bc922e4-2158-447f-ba11-616d860c6587",
"name": "Code"
},
{
"parameters": {
"method": "POST",
"url": "http://127.0.0.1:8000/api/documentos/update_fragmentos/",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"name": "document_id",
"value": "={{ $json.document_id }}"
},
{
"name": "cantidad_fragmentos",
"value": "={{ $json.cantidad_fragmentos }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1452,
660
],
"id": "c11fd4f0-8a40-4754-bbfb-364a104623a5",
"name": "API update Fragmentos",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"rule": {
"interval": [
{
"field": "minutes",
"minutesInterval": 1
}
]
}
},
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
-1840,
1035
],
"id": "0de4519d-e320-4932-949e-5b932083ddbd",
"name": "Schedule Trigger"
},
{
"parameters": {
"text": "={{ $json.text }}",
"attributes": {
"attributes": [
{
"name": "ocr_data",
"description": "Texto literal del documento, tal como fue extra\u00eddo",
"required": true
},
{
"name": "json_data",
"description": "Datos estructurados extra\u00eddos del documento formato 100% json",
"required": true
}
]
},
"options": {
"systemPromptTemplate": "=Eres un asistente experto en extracci\u00f3n de datos de documentos. \nRecibir\u00e1s dos entradas:\n- \"ocr_data\": texto plano extra\u00eddo del documento.\n- \"json_data\": una plantilla JSON con los campos que debes completar.\n\nTu tarea es:\n- Analizar el \"ocr_data\" y extraer la informaci\u00f3n correspondiente para cada campo de la plantilla \"json_data\".\n- Completa todos los campos posibles. Si alg\u00fan dato no est\u00e1 presente, deja el campo vac\u00edo o en null, pero nunca elimines ni cambies el nombre de los campos.\n- Devuelve \u00fanicamente el JSON final, sin explicaciones ni texto adicional.\n\nEjemplo de plantilla:\n{{ $('HTTP Request').item.json.documentos[0].modulo_obj.esquema_json.json_data }}\n\nRecuerda: responde solo con el JSON estructurado y v\u00e1lido, siguiendo exactamente la plantilla.\n\n{{ $('HTTP Request').item.json.documentos[0].modulo_obj.esquema_json.json_data }}\n\n"
}
},
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"typeVersion": 1,
"position": [
-300,
660
],
"id": "6636e03b-d00e-487f-954c-1f2873b39fce",
"name": "Information Extractor Dcouments",
"retryOnFail": true,
"maxTries": 5,
"alwaysOutputData": false,
"executeOnce": false
},
{
"parameters": {
"model": "mxbai-embed-large:latest"
},
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
700,
880
],
"id": "5fcf8d07-faa6-47db-ba28-9fba52bc6f78",
"name": "Embeddings Ollama",
"notesInFlow": false,
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
100,
340
],
"id": "e4e902ee-6251-4f06-b648-726af63d153e",
"name": "Ollama Chat Model",
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "text",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-520,
660
],
"id": "2dc3a0fd-7108-4fbc-8fac-f4f75ef60b49",
"name": "Extract from File1"
},
{
"parameters": {
"operation": "xls",
"options": {}
},
"type": "n8n-nodes-base.convertToFile",
"typeVersion": 1.1,
"position": [
-520,
860
],
"id": "fc581a0e-7aa7-465f-9e49-91047b2c9a00",
"name": "Convert to File"
},
{
"parameters": {
"jsCode": "// n8n Code node: solo limpia y formatea json_data, deja el resto igual\nfunction cleanString(str) {\n // Elimina espacios al inicio/final, saltos de l\u00ednea, tabulaciones y reduce m\u00faltiples espacios a uno solo\n return str\n .replace(/\\s+/g, ' ') // reemplaza cualquier secuencia de espacios, tabs o saltos de l\u00ednea por un solo espacio\n .trim();\n}\n\nfunction cleanObject(obj) {\n for (const key in obj) {\n if (typeof obj[key] === 'string') {\n obj[key] = cleanString(obj[key]);\n } else if (typeof obj[key] === 'object' && obj[key] !== null) {\n obj[key] = cleanObject(obj[key]);\n }\n }\n return obj;\n}\n\nfor (const item of $input.all()) {\n // Solo limpiar json_data si es string JSON\n if (item.json.json_data && typeof item.json.json_data === 'string') {\n try {\n const parsed = JSON.parse(item.json.json_data);\n const cleaned = cleanObject(parsed);\n item.json.json_data = JSON.stringify(cleaned);\n } catch (e) {\n // Si no es JSON v\u00e1lido, lo deja como est\u00e1\n }\n }\n // Imprimir todo el item y el json_data limpio (para debug)\n console.log(item);\n console.log('json_data limpio:', item.json.json_data);\n}\n\nreturn $input.all();"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
296,
660
],
"id": "5f3bbf41-0780-4f73-9833-be975855f4c4",
"name": "Reseteao de espacios en json_data"
},
{
"parameters": {
"model": "gpt-4.1",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
"typeVersion": 1,
"position": [
-280,
900
],
"id": "0b63474b-3532-444a-b187-6861197f9729",
"name": "Azure OpenAI Chat Model",
"credentials": {
"azureOpenAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
-40,
340
],
"id": "966cf8ad-476f-42d8-a024-67ffc577be3c",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"HTTP Request": {
"main": [
[
{
"node": "\u00bfHay Documentos?",
"type": "main",
"index": 0
}
]
]
},
"\u00bfHay Documentos?": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[
{
"node": "HTTP Request1",
"type": "main",
"index": 0
}
],
[
{
"node": "Verificar Documentos",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request1": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
],
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"Preparar Datos": {
"main": [
[
{
"node": "Reseteao de espacios en json_data",
"type": "main",
"index": 0
}
]
]
},
"Actualizar Documento": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Supabase Vector Store": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Supabase Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Verificar Documentos": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Finalizar Documento": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Information Extractor Dcouments",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "API update Fragmentos",
"type": "main",
"index": 0
}
]
]
},
"API update Fragmentos": {
"main": [
[
{
"node": "Finalizar Documento",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "HTTP Request",
"type": "main",
"index": 0
}
]
]
},
"Information Extractor Dcouments": {
"main": [
[
{
"node": "Preparar Datos",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[]
]
},
"Extract from File1": {
"main": [
[
{
"node": "Information Extractor Dcouments",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Information Extractor Dcouments",
"type": "main",
"index": 0
}
]
]
},
"Reseteao de espacios en json_data": {
"main": [
[
{
"node": "Actualizar Documento",
"type": "main",
"index": 0
}
]
]
},
"Azure OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Information Extractor Dcouments",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "259f36c8-1b03-456d-aafb-88498be58177",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "9WZiKACKwRyAQ82V",
"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.
azureOpenAiApihttpHeaderAuthollamaApiopenAiApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Agente de Procesamiento de Documentos. Uses httpRequest, vectorStoreSupabase, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter. Scheduled trigger; 25 nodes.
Source: https://github.com/C1ZC/app_future/blob/104efa086f5ad38a9a48656176655c6c481f41d7/BotAI_n8n.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.
crawl4 ai. Uses documentDefaultDataLoader, textSplitterCharacterTextSplitter, vectorStoreSupabase, embeddingsOllama. Scheduled trigger; 65 nodes.
Document Default Data Loader, Text Splitter Character Text Splitter, Supabase Vector Store +12
local_RAG. Uses documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, chatTrigger, memoryBufferWindow. Event-driven trigger; 39 nodes.
Document Default Data Loader, Text Splitter Recursive Character Text Splitter, Chat Trigger +9
Splitout Schedule. Uses scheduleTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter. Scheduled trigger; 36 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +5
This can be one way to help reduce the amount of manual work in managing the issue backlog for busy teams with little effort. This template contains 2 separate flows which run continuously via schedul
OpenAI Embeddings, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +5
Overview
Agent, OpenAI Chat, HTTP Request +7