AutomationFlowsAI & RAG › Process DOCX with OpenAI LLM

Process DOCX with OpenAI LLM

Original n8n title: Docx処理とllm連携ワークフロー

docx処理とLLM連携ワークフロー. Uses lmChatOpenAi. Webhook trigger; 6 nodes.

Webhook trigger★★★★☆ complexityAI-powered6 nodesOpenAI Chat
AI & RAG Trigger: Webhook Nodes: 6 Complexity: ★★★★☆ AI nodes: yes Added:

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 →

Download .json
{
  "name": "docx\u51e6\u7406\u3068LLM\u9023\u643a\u30ef\u30fc\u30af\u30d5\u30ed\u30fc",
  "nodes": [
    {
      "parameters": {
        "path": "docx-processing",
        "options": {
          "allowedMethods": [
            "POST"
          ]
        },
        "responseMode": "responseNode"
      },
      "id": "webhook-trigger",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "operation": "extractText",
        "binaryPropertyName": "file",
        "options": {}
      },
      "id": "extract-docx",
      "name": "Extract from File",
      "type": "n8n-nodes-base.extractFromFile",
      "typeVersion": 1,
      "position": [
        460,
        300
      ]
    },
    {
      "parameters": {
        "model": "gpt-3.5-turbo",
        "messages": {
          "messageValues": [
            {
              "role": "system",
              "message": "\u3053\u308c\u306f\u30d7\u30ed\u30f3\u30d7\u30c8A\u3067\u3059\u3002\u4e8b\u524d\u306b\u5b9f\u884c\u3055\u308c\u308b\u51e6\u7406\u3068\u3057\u3066\u3001\u3053\u3053\u306b\u9069\u5207\u306a\u30d7\u30ed\u30f3\u30d7\u30c8\u3092\u8a2d\u5b9a\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u4f8b\uff1a\u30b7\u30b9\u30c6\u30e0\u306e\u521d\u671f\u5316\u3084\u6e96\u5099\u4f5c\u696d\u3092\u884c\u3063\u3066\u304f\u3060\u3055\u3044\u3002"
            }
          ]
        },
        "options": {}
      },
      "id": "llm-prompt-a",
      "name": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8A",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        680,
        300
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "model": "gpt-3.5-turbo",
        "messages": {
          "messageValues": [
            {
              "role": "system",
              "message": "\u3053\u308c\u306f\u30d7\u30ed\u30f3\u30d7\u30c8B\u3067\u3059\u3002\u4ee5\u4e0b\u306e\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u5185\u5bb9\u3092\u5206\u6790\u3057\u3066\u304f\u3060\u3055\u3044\u3002"
            },
            {
              "role": "user",
              "message": "=\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u5185\u5bb9\uff1a\n{{ $node[\"Extract from File\"].json[\"text\"] }}\n\n\u4e0a\u8a18\u306e\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3092\u5206\u6790\u3057\u3001\u8981\u7d04\u3084\u91cd\u8981\u306a\u30dd\u30a4\u30f3\u30c8\u3092\u62bd\u51fa\u3057\u3066\u304f\u3060\u3055\u3044\u3002"
            }
          ]
        },
        "options": {}
      },
      "id": "llm-prompt-b",
      "name": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8B",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        900,
        300
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "model": "gpt-3.5-turbo",
        "messages": {
          "messageValues": [
            {
              "role": "system",
              "message": "\u3053\u308c\u306f\u30d7\u30ed\u30f3\u30d7\u30c8C\u3067\u3059\u3002\u524d\u56de\u306e\u5206\u6790\u7d50\u679c\u3092\u57fa\u306b\u3001\u6700\u7d42\u7684\u306a\u7d50\u679c\u3092\u751f\u6210\u3057\u3066\u304f\u3060\u3055\u3044\u3002"
            },
            {
              "role": "user",
              "message": "=\u524d\u56de\u306e\u5206\u6790\u7d50\u679c\uff1a\n{{ $node[\"LLM - \u30d7\u30ed\u30f3\u30d7\u30c8B\"].json[\"text\"] }}\n\n\u4e0a\u8a18\u306e\u5206\u6790\u7d50\u679c\u3092\u57fa\u306b\u3001\u30e6\u30fc\u30b6\u30fc\u306b\u63d0\u793a\u3059\u308b\u6700\u7d42\u7684\u306a\u56de\u7b54\u3092\u4f5c\u6210\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u308f\u304b\u308a\u3084\u3059\u304f\u3001\u5b9f\u884c\u53ef\u80fd\u306a\u30a2\u30c9\u30d0\u30a4\u30b9\u3084\u7d50\u8ad6\u3092\u542b\u3081\u3066\u304f\u3060\u3055\u3044\u3002"
            }
          ]
        },
        "options": {}
      },
      "id": "llm-prompt-c",
      "name": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8C",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        1120,
        300
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "{\n  \"status\": \"success\",\n  \"result\": \"{{ $node[\"LLM - \u30d7\u30ed\u30f3\u30d7\u30c8C\"].json[\"text\"] }}\",\n  \"timestamp\": \"{{ new Date().toISOString() }}\"\n}"
      },
      "id": "respond-webhook",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1340,
        300
      ]
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Extract from File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from File": {
      "main": [
        [
          {
            "node": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8A",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8A": {
      "main": [
        [
          {
            "node": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8B",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8B": {
      "main": [
        [
          {
            "node": "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8C",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLM - \u30d7\u30ed\u30f3\u30d7\u30c8C": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "createdAt": "2025-05-27T00:00:00.000Z",
  "updatedAt": "2025-05-27T00:00:00.000Z",
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [],
  "triggerCount": 0,
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "docx-llm-workflow",
  "versionId": "1"
}

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.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

docx処理とLLM連携ワークフロー. Uses lmChatOpenAi. Webhook trigger; 6 nodes.

Source: https://github.com/ShunsukeTamura06/us-market-news-may21-2025/blob/3879f30fe5c1b2aef23cec3c8e31abd7a09ea841/n8n-docx-llm-workflow.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

The Ultimate Scraper for n8n uses Selenium and AI to retrieve any information displayed on a webpage. You can also use session cookies to log in to the targeted webpage for more advanced scraping need

OpenAI Chat, HTTP Request, Information Extractor +1
AI & RAG

z-Api. Uses httpRequest, openAi, redis, postgres. Webhook trigger; 61 nodes.

HTTP Request, OpenAI, Redis +4
AI & RAG

This template automates the extraction of structured data from Thai government letters received via LINE or uploaded to Google Drive. It uses Mistral AI for OCR and OpenAI for information extraction,

HTTP Request, Google Drive Trigger, Google Drive +4
AI & RAG

🤝🖊️🤖 This workflow automates the process of retrieving meeting transcripts from Fireflies.ai, extracting and summarizing relevant content using Google Gemini, and sending or drafting well-formatted su

@Firefliesai/N8N Nodes Fireflies, Gmail Trigger, Gmail +3
AI & RAG

I'll be honest, I built this because I was getting lazy in meetings and missing key details. I started with a simple VEXA integration for transcripts, then added AI to pull out summaries and tasks. Bu

Redis, Baserow, HTTP Request +3