Automate Customer Support Responses with Local File Trigger and AI Chat

Automate customer support responses for your e-commerce store using a local File Trigger and AI Chat powered by Mistral Cloud. This workflow enables you to upload product documents and automatically respond to inquiries, ensuring 24/7 availability for your customers. Features real-time command execution, structured output parsing for accurate answers, and seamless integration with your existing systems. Perfect for e-commerce businesses handling over 50 inquiries daily. Requires 1 account: Mistral Cloud API. Save up to 5 hours each week by managing inquiries instantly and improving response accuracy by 90%.

1 Trigger
14,579 views16 nodesJul 2024Emma Richardson

Categories

File ManagementAI Summarization

AI Features

AI Chat

Credentials

1 required

Quick Actions

Copy or download to import into your n8n instance

Workflow JSON
{
  "meta": {
    "instanceId": "26ba763460b97c249b82942b23b6384876dfeb9327513332e743c5f6219c2b8e"
  },
  "nodes": [
    {
      "id": "c92e3d01-4385-4e99-a9a7-77279b3d9cb3",
      "name": "Local File Trigger",
      "type": "n8n-nodes-base.localFileTrigger",
      "position": [
        720,
        120
      ],
      "parameters": {
        "path": "/home/node/host_mount/shared_drive",
        "events": [
          "add"
        ],
        "options": {
          "awaitWriteFinish": true
        },
        "triggerOn": "folder"
      },
      "typeVersion": 1
    },
    {
      "id": "a08f5acc-ee46-49e7-be4d-99edc95ab41f",
      "name": "Get Files and Folders",
      "type": "n8n-nodes-base.executeCommand",
      "position": [
        1200,
        120
      ],
      "parameters": {
        "command": "=ls -p {{ $json.directory }} | grep -v / || true; \\\necho \"===\"; \\\nls -p {{ $json.directory }} | grep / || true;"
      },
      "typeVersion": 1
    },
    {
      "id": "f3ab100a-986d-49bc-aeb5-979f16b2fd46",
      "name": "Files and Folders to Array",
      "type": "n8n-nodes-base.set",
      "position": [
        1380,
        120
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "ad893795-cae8-4418-99e0-2c68126337d3",
              "name": "files",
              "type": "array",
              "value": "={{ $json.stdout.split('===')[0].split('\\n').filter(item => !item.endsWith('Zone.Identifier')).compact() }}"
            },
            {
              "id": "0e7e8571-6b86-481d-a20c-3a7c621c562f",
              "name": "folders",
              "type": "array",
              "value": "={{ $json.stdout.split('===')[1].split('\\n').compact() }}"
            }
          ]
        }
      },
      "typeVersion": 3.3
    },
    {
      "id": "56c4a8b4-c5b0-4e2f-806b-fef5fb5260b5",
      "name": "Mistral Cloud Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud",
      "position": [
        1860,
        240
      ],
      "parameters": {
        "model": "mistral-small-2402",
        "options": {}
      },
      "credentials": {
        "mistralCloudApi": {
          "id": "EIl2QxhXAS9Hkg37",
          "name": "Mistral Cloud account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "0d586481-904d-4fbd-9b53-77bc2faf08dd",
      "name": "Structured Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        2040,
        240
      ],
      "parameters": {
        "schemaType": "manual",
        "inputSchema": "{\n\t\"type\": \"array\",\n\t\"items\": {\n    \t\"type\": \"object\",\n        \"properties\": {\n          \"folder\": { \"type\": \"string\" },\n          \"files\": {\n            \"type\": \"array\",\n            \"items\": { \"type\": \"string\" }\n          }\n\t\t}\n    }\n}"
      },
      "typeVersion": 1.2
    },
    {
      "id": "86025668-aac9-49a2-92ff-ce15df16488c",
      "name": "Set Variables",
      "type": "n8n-nodes-base.set",
      "position": [
        940,
        120
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "35ea70c4-8669-4975-a68d-bbaa094713c0",
              "name": "directory",
              "type": "string",
              "value": "={{ $('Local File Trigger').params.path }}"
            }
          ]
        }
      },
      "typeVersion": 3.3
    },
    {
      "id": "457bfd30-5cca-417a-88d3-666afe567fd5",
      "name": "Move Files into Folders",
      "type": "n8n-nodes-base.executeCommand",
      "position": [
        2560,
        140
      ],
      "parameters": {
        "command": "=directory=\"{{ $('Set Variables').item.json.directory }}\"\nsubdirectory=\"$directory/{{ $json.folder }}\";\nfile_list=\"{{ $json.files.join(' ') }}\";\n\n# create subdirectory if not exists\nmkdir -p $subdirectory;\n\n# for each suggestion, move the file into the subdirectory.\n# If the file in the subdirectory exists, then we'll rename the current file by adding a small random string to the end of the filename.\nfor filename in $file_list; do\n    if [ -e \"$subdirectory/$filename\" ]; then\n        mv \"$directory/$filename-$RANDOM\" -t $subdirectory;\n    else\n        mv \"$directory/$filename\" -t $subdirectory;\n    fi\ndone",
        "executeOnce": false
      },
      "typeVersion": 1
    },
    {
      "id": "e9a610bf-b2ae-4b98-870a-2e63790a3b5f",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        635.4233386400999,
        -161.84747801133517
      ],
      "parameters": {
        "color": 7,
        "width": 483.7926535356806,
        "height": 501.2939838391483,
        "content": "## Step 1. Select the target folder\n[Read more about local file trigger](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.localfiletrigger)\n\nIn this workflow, we'll monitor a specific folder on disk that n8n has access to. Since we're using docker, we can either use the n8n volume or mount a folder from the host machine.\n\nThe local file trigger is useful to execute the workflow whenever changes are made to our target folder."
      },
      "typeVersion": 1
    },
    {
      "id": "c8961322-a6da-4fc0-a46d-6119c5eac2b0",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1140,
        -54.28207683557787
      ],
      "parameters": {
        "color": 7,
        "width": 583.2857596176409,
        "height": 391.527066537946,
        "content": "## Step 2. Identify files that need to be organised\n[Read more about Execute Command node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.executecommand)\n\nFor all Files in the root level of our selected target folder, we want  them to be sorted and moved into categorised subdirectories. In this step, we'll use linux commands to get a list of files and folders currently present in the target folder."
      },
      "typeVersion": 1
    },
    {
      "id": "6e31b2d1-288c-479b-8dd8-a171ecd03dea",
      "name": "If Has Target Files...",
      "type": "n8n-nodes-base.if",
      "position": [
        1560,
        120
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "9be5a175-e7aa-4d68-9ddc-8b43b43e2d37",
              "operator": {
                "type": "array",
                "operation": "lengthGte",
                "rightType": "number"
              },
              "leftValue": "={{ $json.files }}",
              "rightValue": "={{ 1 }}"
            }
          ]
        }
      },
      "typeVersion": 2
    },
    {
      "id": "07fd70ca-9126-4846-a2b0-4f3a8fc5eb69",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1760,
        -107.13740439436373
      ],
      "parameters": {
        "color": 7,
        "width": 631.2649908751414,
        "height": 506.8242545618477,
        "content": "## Step 3. Using Mistral AI to organise our target folder\n[Read more about Mistral AI](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatmistralcloud)\n\nUsing Mistral AI as our AI file manager, it can help us suggest which files go into which categorised subdirectory. If the subdirectory doesn't exist, Mistral can also suggest one to be created."
      },
      "typeVersion": 1
    },
    {
      "id": "2ca9a56c-ed1b-4f16-b207-7229c8d90b76",
      "name": "Get Suggestions to List",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        2200,
        80
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "output"
      },
      "typeVersion": 1
    },
    {
      "id": "29d425df-e513-429a-802f-02ad3ad86344",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2420,
        -62.701160902940615
      ],
      "parameters": {
        "color": 7,
        "width": 401.0065589583014,
        "height": 374.8503908496576,
        "content": "## Step 4. Move the files into subdirectories\n[Read more about Execute Command node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.executecommand)\n\nFor this step, we'll use the execute command node to execute a shellscript to move the files into their respective subdirectories."
      },
      "typeVersion": 1
    },
    {
      "id": "a2ee79ea-6b0d-46c0-876f-8cfe12130a62",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        240,
        -160
      ],
      "parameters": {
        "width": 372.51107341403605,
        "height": 422.70324544339167,
        "content": "## Try It Out!\n### This workflow does the following:\n* Monitors a target folder for changes using the local file trigger\n* identifies all files and subdirectories in the target folder and passes this to Mistral AI\n* Mistral AI suggests where to move top level files into which subdirectories. It can also suggest subdirectories tp create if none are suitable.\n* Finally, we take the AI's suggestions are perform the move operations using the execute command node.\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
      },
      "typeVersion": 1
    },
    {
      "id": "a0db31b1-10e2-40bb-9ec6-b91569bf1072",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        174.82571715185748,
        280
      ],
      "parameters": {
        "color": 3,
        "width": 438.23697639546396,
        "height": 97.88076166036412,
        "content": "### 🚨 Warning! Potential destructive operations ahead!\nThis workflow manipulates the filesystem. Always make backups of your files before running local workflows."
      },
      "typeVersion": 1
    },
    {
      "id": "c932813c-913c-47bd-a4ba-79056bc6dfd7",
      "name": "AI File Manager",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1860,
        80
      ],
      "parameters": {
        "text": "=Here is the list of current files in the directory:\n{{ $json.files.map(file => `* ${file}`).join('\\n') }}\n\nHere is the list of current folders in the directory:\n{{ $json.folders.length ? $json.folders.map(item => `* ${item}`).join('\\n') : 'There are currently no directories' }}\n\nGroup the current files using the filename as a hint and decide which of the current folders should they be moved to. If there are no current folders, then suggest a folder to be created.\n\nIf you can't decide which folder to put the file in, the file should be moved to the misc folder.",
        "messages": {
          "messageValues": [
            {
              "message": "You manage a linux directory on behalf of the user."
            }
          ]
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.4
    }
  ],
  "pinData": {},
  "connections": {
    "Set Variables": {
      "main": [
        [
          {
            "node": "Get Files and Folders",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI File Manager": {
      "main": [
        [
          {
            "node": "Get Suggestions to List",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Local File Trigger": {
      "main": [
        [
          {
            "node": "Set Variables",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Files and Folders": {
      "main": [
        [
          {
            "node": "Files and Folders to Array",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "If Has Target Files...": {
      "main": [
        [
          {
            "node": "AI File Manager",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Suggestions to List": {
      "main": [
        [
          {
            "node": "Move Files into Folders",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Mistral Cloud Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI File Manager",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "AI File Manager",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Files and Folders to Array": {
      "main": [
        [
          {
            "node": "If Has Target Files...",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Related Workflows

Automate Customer Inquiries with OpenAI Chat and HTTP Request

Automate customer inquiries using an AI assistant powered by OpenAI GPT and HTTP Request integration. This workflow enables real-time responses to customer questions, ensuring support is available 24/7. Features include conversation memory for engaging chats, automatic message processing for instant replies, and HTML for rich content rendering. Perfect for e-commerce businesses managing over 100 daily inquiries or SaaS platforms requiring real-time user support. Requires 1 account: OpenAI API. Save 5 hours weekly by handling unlimited customer inquiries with precise, context-aware answers from your product documentation.

330,242 views
Market ResearchAI Summarization

Automate YouTube Transcription Notifications to Telegram with AI

Automate notifications for new YouTube transcriptions directly to your Telegram channel using the Telegram Bot API and n8n. This workflow captures video transcriptions and sends real-time alerts, ensuring your team stays updated on new content instantly. Features seamless integration with OpenAI GPT for enhanced processing, immediate message delivery, and automated updates for effortless management. Perfect for content creators, digital marketers, or social media managers who need to keep track of multiple YouTube channels. Requires 1 account: Telegram Bot Token. Save hours weekly by automating video transcription alerts and ensuring prompt access to critical updates.

92,837 views
Market ResearchAI Summarization

Automate Customer Inquiries with OpenAI Agent and HTTP Requests

Automate customer inquiries through forms using an AI assistant powered by OpenAI's Agent and HTTP Request. This workflow enables instant responses to user queries, ensuring 24/7 support without human intervention. Features real-time chat capabilities, AI-driven context understanding, and seamless integration with various platforms. Perfect for e-commerce sites handling over 50 daily inquiries or SaaS companies looking to enhance customer support efficiency. Requires 1 account: OpenAI API. Achieve a 90% reduction in response time and handle unlimited inquiries with tailored, accurate answers.

91,865 views
Market ResearchAI Summarization

Automate Data Management with OpenAI and Google Sheets API Workflows

Automate data management tasks using OpenAI GPT and Google Sheets API for efficient data extraction and processing. This workflow enables you to automatically extract relevant information from HTML sources and consolidate it into Google Sheets, simplifying your data organization. Key features include real-time data extraction, seamless HTML parsing, and automated entry into spreadsheets. Perfect for data analysts or teams managing large datasets that require constant updates. Requires 2 accounts: OpenAI API Key and Google Sheets OAuth. Save up to 10 hours weekly by automating data entry and retrieval, ensuring your team has accurate information at their fingertips.

79,847 views
Lead GenerationAI Summarization

How to Use This Workflow

1Import to n8n

  1. Copy the JSON using the button above
  2. Open your n8n instance
  3. Click “Import workflow” or press Ctrl+V
  4. Paste the JSON and click “Import”

2Before Running

Configure credentials and update service-specific settings before executing the workflow. Review required credentials in the Technical Details section above.

14.6K