{ "id": "R82cCEu45d5np7SQ", "meta": { "templateCredsSetupCompleted": true }, "tags": [], "nodes": [ { "id": "beeb0f7f-e489-4955-b87a-702ca909628a", "name": "File Created", "type": "n8n-nodes-base.googleDriveTrigger", "position": [ -1792, -272 ], "parameters": { "event": "fileCreated", "options": { "fileType": "all" }, "pollTimes": { "item": [ { "mode": "everyX", "unit": "minutes", "value": 5 } ] }, "triggerOn": "specificFolder", "folderToWatch": { "__rl": true, "mode": "id", "value": "" } }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 1 }, { "id": "70baab34-54e4-4933-8093-b28d34090c3e", "name": "File Updated", "type": "n8n-nodes-base.googleDriveTrigger", "position": [ -1792, -80 ], "parameters": { "event": "fileUpdated", "options": {}, "pollTimes": { "item": [ { "mode": "everyX", "unit": "minutes", "value": 5 } ] }, "triggerOn": "specificFolder", "folderToWatch": { "__rl": true, "mode": "id", "value": "" } }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 1 }, { "id": "59f4249a-2445-488e-9a5c-78718506d9f9", "name": "Set File ID", "type": "n8n-nodes-base.set", "position": [ -1296, -160 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "500b4c9d-617a-4d88-9d74-9beb5922a00a", "name": "file_id", "type": "string", "value": "={{ $json.id }}" }, { "id": "d5779b2e-12fd-4a73-9181-da4b9eec5b67", "name": "file_name", "type": "string", "value": "={{ $json.name }}" }, { "id": "3349c2ff-89a4-4b95-93b3-52c4d5316127", "name": "dest_folder", "type": "string", "value": "={{ $json.name.split('.').slice(0, -1).join('.'); }}" }, { "id": "f79e2578-3375-4e1d-88e0-748e2daac35b", "name": "file_name_no_ext", "type": "string", "value": "={{ $json.name.split('.').slice(0, -1).join('.'); }}" }, { "id": "45b4ffe8-1ebc-48f8-8234-c497c4081f39", "name": "mime_type", "type": "string", "value": "={{ $json.mimeType }}" } ] } }, "typeVersion": 3.4 }, { "id": "9d4db769-a867-4938-b513-c5402f007e4d", "name": "Convert to File", "type": "n8n-nodes-base.convertToFile", "position": [ 2208, 208 ], "parameters": { "options": { "fileName": "={{ $json.id }}", "mimeType": "={{ $json.image_base64.split(';')[0].split(':').pop() }}" }, "operation": "toBinary", "sourceProperty": "stripped_image_base64", "binaryPropertyName": "=image" }, "typeVersion": 1.1 }, { "id": "4521d9c9-2040-4181-b298-2ad0640d0002", "name": "Merge", "type": "n8n-nodes-base.merge", "position": [ 2640, -16 ], "parameters": { "mode": "chooseBranch", "numberInputs": 3 }, "typeVersion": 3.2 }, { "id": "9ed3238e-d415-43f7-b452-9806479b7de9", "name": "Save Image", "type": "n8n-nodes-base.googleDrive", "position": [ 2400, 208 ], "parameters": { "name": "={{ $binary.data.fileName }}", "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Create Folder').item.json.id }}" }, "inputDataFieldName": "=image" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "fc0c520a-6650-4952-a161-5fe389ff9dfa", "name": "Split Images", "type": "n8n-nodes-base.splitOut", "position": [ 1808, 208 ], "parameters": { "options": {}, "fieldToSplitOut": "images" }, "typeVersion": 1 }, { "id": "c5851dc0-b183-46a6-82b9-b8cbf3907248", "name": "Split Pages", "type": "n8n-nodes-base.splitOut", "position": [ 1472, 0 ], "parameters": { "options": {}, "fieldToSplitOut": "body.pages" }, "typeVersion": 1 }, { "id": "2976c696-75ba-4876-b378-f4db44782da6", "name": "OCR Document", "type": "n8n-nodes-base.httpRequest", "position": [ 1216, -208 ], "parameters": { "url": "https://api.mistral.ai/v1/ocr", "method": "POST", "options": { "response": { "response": { "fullResponse": true, "responseFormat": "json" } } }, "jsonBody": "={\n \"model\": \"mistral-ocr-latest\",\n \"document\": {\n \"type\": \"{{ $('Use Url').item.json.document_type }}\",\n \"{{ $('Use Url').item.json.document_type }}\": \"data:{{ $('Set File ID').item.json.mime_type }};base64,{{ $('Download File').item.binary.binary_file_data.data }}\"\n },\n \"include_image_base64\": true\n}", "sendBody": true, "specifyBody": "json", "authentication": "predefinedCredentialType", "nodeCredentialType": "mistralCloudApi" }, "credentials": { "mistralCloudApi": { "name": "" } }, "typeVersion": 4.2 }, { "id": "82a0d06b-50e1-4427-a459-45a59ed0ff1c", "name": "Download File", "type": "n8n-nodes-base.googleDrive", "position": [ 1024, -208 ], "parameters": { "fileId": { "__rl": true, "mode": "id", "value": "={{ $('Copy file').item.json.id }}" }, "options": { "binaryPropertyName": "binary_file_data" }, "operation": "download" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "d6d25c96-67a3-4ae3-873f-2cd54fabb366", "name": "Create Folder", "type": "n8n-nodes-base.googleDrive", "position": [ -576, -176 ], "parameters": { "name": "={{ $('Set File ID').item.json.dest_folder }}_{{ $now.format('yyyyMMdd-hhmmss') }}", "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.dest_folder_id }}" }, "resource": "folder" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "c2119a4c-7b3b-465e-9437-12ff585f6bd6", "name": "Copy file", "type": "n8n-nodes-base.googleDrive", "position": [ -208, -176 ], "parameters": { "name": "={{ $('Set File ID').item.json.file_name }}", "fileId": { "__rl": true, "mode": "id", "value": "={{ $('Set File ID').item.json.file_id }}" }, "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Create Folder').item.json.id }}" }, "operation": "copy", "sameFolder": false }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "1f4180a9-333a-421c-aea6-0f9666ce55ed", "name": "Save Page MD File", "type": "n8n-nodes-base.googleDrive", "position": [ 1808, 0 ], "parameters": { "name": "={{ $('Set File ID').item.json.file_name_no_ext }}_page_{{ String($json.index + 1).padStart($('OCR Document').item.json.body.pages.length.toString().length, '0') }}.md", "content": "={{ $json.markdown }}", "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Create Folder').item.json.id }}" }, "operation": "createFromText" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "45fe0471-0558-49a4-afd9-a63e42ca198f", "name": "Code in JavaScript", "type": "n8n-nodes-base.code", "position": [ 2000, -176 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "return { markdown: $json.full_markdown.join('\\n\\n') };" }, "typeVersion": 2 }, { "id": "0dac4cc0-5506-4690-bd13-c0e4d4bfb91f", "name": "Aggregate", "type": "n8n-nodes-base.aggregate", "position": [ 1808, -176 ], "parameters": { "options": {}, "fieldsToAggregate": { "fieldToAggregate": [ { "renameField": true, "outputFieldName": "full_markdown", "fieldToAggregate": "markdown" } ] } }, "typeVersion": 1 }, { "id": "856f5947-55d6-42c7-91bf-d98f82440094", "name": "Save MD File", "type": "n8n-nodes-base.googleDrive", "position": [ 2208, -176 ], "parameters": { "name": "={{ $('Set File ID').item.json.file_name_no_ext }}.md", "content": "={{ $json.markdown }}", "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Create Folder').item.json.id }}" }, "operation": "createFromText" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "c52e230e-1185-4461-a6f5-26204ec481be", "name": "Save raw OCR file", "type": "n8n-nodes-base.googleDrive", "position": [ 1472, -320 ], "parameters": { "name": "={{ $('Set File ID').item.json.file_name_no_ext }}.json", "content": "={{ JSON.stringify($json.body, null, 2) }}", "driveId": { "__rl": true, "mode": "list", "value": "My Drive" }, "options": {}, "folderId": { "__rl": true, "mode": "id", "value": "={{ $('Create Folder').item.json.id }}" }, "operation": "createFromText" }, "credentials": { "googleDriveOAuth2Api": { "name": "" } }, "typeVersion": 3 }, { "id": "1cda08ff-f68a-40e6-b0cd-89d7d9f60847", "name": "Merge1", "type": "n8n-nodes-base.merge", "position": [ 2864, -160 ], "parameters": { "mode": "chooseBranch", "output": "empty" }, "typeVersion": 3.2 }, { "id": "2dc3cd63-1430-42ca-a475-caf7e2138b23", "name": "Add MD file in sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 2400, -176 ], "parameters": { "columns": { "value": { "MD File": "=https://drive.google.com/file/d/{{ $json.id }}", "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": true, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": false, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "aee9f683-30ea-4817-a51a-1d6884a630d4", "name": "Add json file in sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 2640, -320 ], "parameters": { "columns": { "value": { "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}", "JSON file": "=https://drive.google.com/file/d/{{ $json.id }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": false, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "28756c24-c8ca-4a91-8d98-e4c3bc30a8b3", "name": "Create Entry in sheet", "type": "n8n-nodes-base.googleSheets", "position": [ -384, -176 ], "parameters": { "columns": { "value": { "Status": "Started", "Started": "={{ $now.format('yyyy-MM-dd hh:mm:ss') }}", "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}", "File Name": "={{ $('Set File ID').item.json.file_name }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": true, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "cb5b2286-ab97-4021-a674-b3ee1289b7f4", "name": "Complete job in sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 3072, -160 ], "parameters": { "columns": { "value": { "Status": "Done", "Completed": "={{ $now.format('yyyy-MM-dd hh:mm:ss') }}", "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": true, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "e2696f2f-5442-444e-873e-fc40e7b742bb", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ 1392, -528 ], "parameters": { "color": 7, "width": 2112, "height": 1020, "content": "## 4. Upload to Google Drive\n[Read more about Slack OAuth2 credentials](https://docs.n8n.io/integrations/builtin/credentials/slack/#using-oauth2)\n\n\n**\ud83d\udcc4 MD Files:** \n * An MD file per page is created. This is helpful for validating OCR accuracy. \n * An aggregate file with the entire content is created for further processing.\n \n**\ud83d\udcca Images:** Images are Base64 strings with a Mime Type headers. Header is stripped and Base64 string is converted to binary before saving to Google Drive. " }, "typeVersion": 1 }, { "id": "ac3a9ab0-4a5f-4f4d-a882-3c2fdeac3b72", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ 176, -528 ], "parameters": { "color": 7, "width": 1168, "height": 1020, "content": "## 3. Perform OCR Using Mistral Document\n[Read more about Mistral Document ](https://docs.mistral.ai/capabilities/document_ai/basic_ocr/)\n[Read more about Mistral Cloud Credentials](https://docs.n8n.io/integrations/builtin/credentials/mistral/)\n[Read more about Slack OAuth2 credentials](https://docs.n8n.io/integrations/builtin/credentials/slack/#using-oauth2)\n\n* Validate the file Mime Type and exit if type is unsupported.\n * **Note:** Configure the Switch node to add more file types supported by Mistral Document. This workflow currently supports `pdf`, `docx`, `png`, `jpg`, and `jpeg`.\n* Download the file into n8n and pass it as a Base64-encoded document in the body of the POST request. \n * **Implementation Note:** Alternatively, you can upload the file to Mistral and provide a signed URL to Mistral Document.\n* Parse the document using Mistral Document. \n * **Implementation Note:** The Mistral AI Extract Text node cannot be used here, as it does not return images in the response. The Mistral API must be called directly instead.\n" }, "typeVersion": 1 }, { "id": "440b897e-5a82-45a5-888b-051616e617cc", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [ -608, -528 ], "parameters": { "color": 7, "width": 728, "height": 1020, "content": "## 2. Copy File to Target Directory\n\n* Create a destination directory and copy the source file into it.\n* Add a row to the Google Sheet to track progress. The row identifier is the unique URL of the destination directory.\n" }, "typeVersion": 1 }, { "id": "a05f0d84-d6dd-4826-b887-919edb13d1c6", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -1888, -528 ], "parameters": { "color": 7, "width": 728, "height": 1020, "content": "## 1. Watch for New and Updated Files in Google Drive Folder\n\n[Read more about the Google Drive Trigger node](https://docs.n8n.io/integrations/builtin/trigger-nodes/n8n-nodes-base.googledrivetrigger/)\n[Read more about Google Credentials](https://docs.n8n.io/integrations/builtin/credentials/google/)\n\nOther sources like local file system, OneDrive, S3 can be used instead.\n\n" }, "typeVersion": 1 }, { "id": "41536036-583f-4823-bafe-67d1bac4715a", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ -1088, -528 ], "parameters": { "color": 4, "width": 432, "height": 464, "content": "## \u2699\ufe0f Update the Workflow Configuration Node\n\n- `google_sheet_id`: Set this to the ID of your Google Sheet. See **Google Sheets Configuration** for the sheet name and column details.\n- `dest_folder_id`: Set this to the ID of the folder that will contain all output files.\n" }, "typeVersion": 1 }, { "id": "a8ed6e6e-6cc7-420a-8be9-f22d1309f55d", "name": "Workflow Configuration", "type": "n8n-nodes-base.set", "position": [ -928, -272 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "c16e829e-d2f6-49e0-9ffe-ee0c4fca0487", "name": "google_sheet_id", "type": "string", "value": "" }, { "id": "4c4d3dc8-d102-40dc-9943-7de13cb2324a", "name": "dest_folder_id", "type": "string", "value": "" } ] } }, "typeVersion": 3.4 }, { "id": "fa6c28ed-ddf0-4616-879d-7ec9bf420a5a", "name": "Extract Base64 value", "type": "n8n-nodes-base.set", "position": [ 2016, 208 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "6a29a531-c96a-4c0e-b867-343ab08e884e", "name": "stripped_image_base64", "type": "string", "value": "={{ $json.image_base64.split(',').pop() }}" } ] }, "includeOtherFields": true }, "typeVersion": 3.4 }, { "id": "b1481ea4-501f-492a-9937-ed686d1ac0b1", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [ -1088, -16 ], "parameters": { "color": 4, "width": 432, "height": 512, "content": "## \ud83d\udd12 Setup credentials\n- `Slack` node: Configure authentication in the Slack node. [Read more about Slack credentials](https://docs.n8n.io/integrations/builtin/credentials/slack/)\n- `OCR Document` node: Configure authentication in the node using your Mistral AI API key [Read more about Mistral credentials](https://docs.n8n.io/integrations/builtin/credentials/mistral/)\n- All `Google` nodes: Configure authentication in all the Google nodes (Drive and Sheet). [Read more about Google credentials](https://docs.n8n.io/integrations/builtin/credentials/google/)\n\n\n" }, "typeVersion": 1 }, { "id": "db701dbb-6259-4b8c-9d6d-ddb556dbebd8", "name": "Sticky Note7", "type": "n8n-nodes-base.stickyNote", "position": [ -528, -16 ], "parameters": { "color": 6, "width": 528, "height": 496, "content": "## \ud83d\udcca Google Sheets Configuration\n\n**Required Sheet Name:** `\"Files\"` \nThe spreadsheet can have any name and contain any number of sheets. However, it must include a sheet named `Files`.\n\n**Required Headers (Row 1):**\n- **File Name** \u2013 Name of the input file\n- **File** \u2013 Link to the input file (copy)\n- **Directory** \u2013 Link to the output directory\n- **JSON File** \u2013 Link to the OCR JSON file\n- **MD File** \u2013 Link to the OCR Markdown file\n- **Started** \u2013 Timestamp when the job started\n- **Completed** \u2013 Timestamp when the job completed\n- **Status** \u2013 Job status (`Started`, `Done`, `Unsupported Type`)\n\n**\ud83d\udd17 Account Permissions** \nThe signed-in account must have **Editor** access to the Google Sheet.\n\n**\u2699\ufe0f Setup** \nThe Google Sheet ID is set in the `Workflow Configuration` step." }, "typeVersion": 1 }, { "id": "ee6c21e6-f369-4575-88dc-7513b6531e4a", "name": "Use Document Url", "type": "n8n-nodes-base.set", "position": [ 480, -208 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "f229d051-0ac2-4aed-9e6f-6315270a9dad", "name": "document_type", "type": "string", "value": "document_url" } ] }, "includeOtherFields": true }, "typeVersion": 3.4 }, { "id": "d019b653-d7e8-4795-9741-a350c98068d4", "name": "Use Image Url", "type": "n8n-nodes-base.set", "position": [ 480, -48 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "f229d051-0ac2-4aed-9e6f-6315270a9dad", "name": "document_type", "type": "string", "value": "image_url" } ] }, "includeOtherFields": true }, "typeVersion": 3.4 }, { "id": "bb211334-f05d-4d96-ac23-33c5fead8c57", "name": "Determine Document Type", "type": "n8n-nodes-base.switch", "position": [ 208, -192 ], "parameters": { "rules": { "values": [ { "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict" }, "combinator": "and", "conditions": [ { "id": "6bba9a77-2985-44f3-a746-2431ec9ed3d6", "operator": { "type": "string", "operation": "regex" }, "leftValue": "={{ $('Set File ID').item.json.mime_type }}", "rightValue": "^(application\\/pdf|application\\/vnd\\.openxmlformats\\-officedocument\\.wordprocessingml\\.document)$" } ] } }, { "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict" }, "combinator": "and", "conditions": [ { "id": "3fbb7b81-6b50-4ba9-8c73-0def8f8d4ab6", "operator": { "type": "string", "operation": "regex" }, "leftValue": "={{ $('Set File ID').item.json.mime_type }}", "rightValue": "^image\\/(png|jpeg|jpg)$" } ] } } ] }, "options": { "fallbackOutput": "extra" } }, "typeVersion": 3.3 }, { "id": "a59769d9-b68b-4492-93b0-453db7e717b1", "name": "Add Source File in Sheet", "type": "n8n-nodes-base.googleSheets", "position": [ -32, -176 ], "parameters": { "columns": { "value": { "File": "=https://drive.google.com/file/d/{{ $json.id }}", "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": false, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": true, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "e34491fc-b2e2-4356-a37f-aac18d0a7ff6", "name": "Set Error in Sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 480, 112 ], "parameters": { "columns": { "value": { "Status": "Unsupported Type", "Completed": "={{ $now.format('yyyy-MM-dd hh:mm:ss') }}", "Directory": "=https://drive.google.com/drive/folders/{{ $('Create Folder').item.json.id }}" }, "schema": [ { "id": "File Name", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File Name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Directory", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Directory", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "JSON file", "type": "string", "display": true, "removed": true, "required": false, "displayName": "JSON file", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "MD File", "type": "string", "display": true, "removed": true, "required": false, "displayName": "MD File", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Status", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Started", "type": "string", "display": true, "removed": true, "required": false, "displayName": "Started", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Completed", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Directory" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mN6Pszfd3D0Vora4Kl8JHJQxuaZ7rD_Zbs0p2wyfnZw/edit#gid=0", "cachedResultName": "Files" }, "documentId": { "__rl": true, "mode": "id", "value": "={{ $('Workflow Configuration').item.json.google_sheet_id }}" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "7c803662-2051-414c-8bc4-9495b4d8034f", "name": "Send Success Message", "type": "n8n-nodes-base.slack", "position": [ 3280, 288 ], "parameters": { "text": "=\u2705 File processed.\n\ud83d\udcc2 Results are available .", "select": "channel", "channelId": { "__rl": true, "mode": "list", "value": "C0462450N", "cachedResultName": "general" }, "otherOptions": { "mrkdwn": true }, "authentication": "oAuth2" }, "credentials": { "slackOAuth2Api": { "name": "" } }, "typeVersion": 2.3 }, { "id": "53c9dbc7-1b0f-4fc5-8cec-032b79393413", "name": "Send Error Message", "type": "n8n-nodes-base.slack", "position": [ 720, 288 ], "parameters": { "text": "=\u26d4 File not processed.\nReason: File type is not supported.\n\ud83d\udcc2 Results are available .", "select": "channel", "channelId": { "__rl": true, "mode": "list", "value": "C0462450N", "cachedResultName": "general" }, "otherOptions": { "mrkdwn": true }, "authentication": "oAuth2" }, "credentials": { "slackOAuth2Api": { "name": "" } }, "typeVersion": 2.3 }, { "id": "b37f2994-8114-4776-a9ad-c9a48ead4397", "name": "Use Url", "type": "n8n-nodes-base.set", "position": [ 784, -208 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "e5f7685c-237a-4338-b19a-354d53125129", "name": "document_type", "type": "string", "value": "={{ $json.document_type }}" } ] } }, "typeVersion": 3.4 }, { "id": "4ee78018-6234-428f-a353-1f3c4ee2ab04", "name": "Sticky Note8", "type": "n8n-nodes-base.stickyNote", "position": [ -2976, -640 ], "parameters": { "width": 1036, "height": 1216, "content": "## Automated OCR for PDFs, DOCX & images via Google Drive & Mistral\n\n### Use cases \n* Monitor Google Drive folder, parsing PDF, DOCX and image file into a destination folder, ready for further processing (e.g. RAG ingestion, translation, etc.)\n* Keep processing log in Google Sheet and send Slack notifications. \n\n### How it works\n* Trigger: Watch Google Drive folder for new and updated files.\n* Create a uniquely named destination folder, copying the input file.\n* Parse the file using Mistral Document, extracting content and handling non-OCRable images separately.\n* Save the data returned by Mistral Document into the destination Google Drive folder (raw JSON file, Markdown files, and images) for further processing.\n\n\n### How to use\n* Google Drive and Google Sheets nodes:\n * Create Google credentials with access to Google Drive and Google Sheets. [Read more about Google Credentials](https://docs.n8n.io/integrations/builtin/credentials/google/).\n * Update **all** Google Drive and Google Sheets nodes (14 nodes total) to use the credentials\n* Mistral node:\n * Create Mistral Cloud API credentials. [Read more about Mistral Cloud Credentials](https://docs.n8n.io/integrations/builtin/credentials/mistral/).\n * Update the `OCR Document` node to use the Mistral Cloud credentials.\n* Slack nodes:\n * Create Slack OAuth2 credentials. [Read more about Slack OAuth2 credentials](https://docs.n8n.io/integrations/builtin/credentials/slack/#using-oauth2)\n * Update the two Slack nodes: `Send Success Message` and `Send Error Message`:\n * Set the credentials\n * Select the channel where you want to send the notifications (channels can be different for success and errors). \n* Create a Google Sheets spreadsheet following the steps in `Google Sheets Configuration` (see right \u27a1\ufe0f). Ensure the spreadsheet can be accessed as `Editor` by the account used by the Google Credentials above.\n* Create a directory for input files and a directory for output folders/files. Ensure the directories can be accessed by the account used by the Google Credentials.\n* Update the `File Created`, `File Updated` and `Workflow Configuration` node following the steps in the green Notes (see right \u27a1\ufe0f).\n\n\n### Requirements\n* Google account with Google API access\n* Mistral Cloud account access to Mistral API key.\n* Slack account with access to Slack client ID and secret ID. \n* Basic n8n knowledge: understanding of triggers, expressions, and credential management\n\n\n### Who\u2019s it for\nAnyone building a data pipeline ingesting files to be OCRed for further processing. \n\n\n### \ud83d\udd12 Security\nAll credentials are stored as n8n credentials. The only information stored in this workflow that *could* be considered sensitive are the Google Drive Directory and Sheet IDs. These directories and the spreadsheet should be secured according to your needs.\n\n\n### Need Help?\nReach out on [LinkedIn](https://www.linkedin.com/in/ytkaczyk/) or Ask in the [Forum](https://community.n8n.io/)!\n" }, "typeVersion": 1 }, { "id": "e1fa4d46-e61b-48ac-8fea-dda6daadba9e", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [ -1840, 80 ], "parameters": { "color": 4, "width": 656, "height": 384, "content": "## \u2699\ufe0f Configuration\n\n* **`File Created` and `File Updated` nodes**: \n Update the `Folder` field in both Google Drive nodes to point to the ID of the folder you want to monitor. You can also set the folder by URL or select it from a list.\n\n### \u2754 How to Get the ID of a Sheet or Directory \u2754\n\nOpen the sheet or directory in your browser. The ID is the randomly generated alphanumeric string in the URL.\n\n* **For a directory**: The ID appears after the last `/` in the URL and looks like `abcdefghijklmnopqr_abcdefghijklmn`\n* **For a sheet**: The ID is located in the middle of the URL and looks like `abcdefghijklmnopqrstuvwxyzABCDE_abcdefghijkl`\n" }, "typeVersion": 1 }, { "id": "f751279b-aaaf-4237-a7dd-4f767ba04811", "name": "Loop over Items", "type": "n8n-nodes-base.splitInBatches", "position": [ -1568, -176 ], "parameters": { "options": {} }, "typeVersion": 3 } ], "active": false, "settings": { "callerPolicy": "workflowsFromSameOwner", "executionOrder": "v1", "timeSavedPerExecution": 5 }, "versionId": "9bcb21b1-2f19-4cee-b3c5-9bc580a3e72f", "connections": { "Merge": { "main": [ [ { "node": "Merge1", "type": "main", "index": 1 } ] ] }, "Merge1": { "main": [ [ { "node": "Complete job in sheet", "type": "main", "index": 0 } ] ] }, "Use Url": { "main": [ [ { "node": "Download File", "type": "main", "index": 0 } ] ] }, "Aggregate": { "main": [ [ { "node": "Code in JavaScript", "type": "main", "index": 0 } ] ] }, "Copy file": { "main": [ [ { "node": "Add Source File in Sheet", "type": "main", "index": 0 } ] ] }, "Save Image": { "main": [ [ { "node": "Merge", "type": "main", "index": 2 } ] ] }, "Set File ID": { "main": [ [ { "node": "Workflow Configuration", "type": "main", "index": 0 } ] ] }, "Split Pages": { "main": [ [ { "node": "Split Images", "type": "main", "index": 0 }, { "node": "Save Page MD File", "type": "main", "index": 0 }, { "node": "Aggregate", "type": "main", "index": 0 } ] ] }, "File Created": { "main": [ [ { "node": "Loop over Items", "type": "main", "index": 0 } ] ] }, "File Updated": { "main": [ [ { "node": "Loop over Items", "type": "main", "index": 0 } ] ] }, "OCR Document": { "main": [ [ { "node": "Save raw OCR file", "type": "main", "index": 0 }, { "node": "Split Pages", "type": "main", "index": 0 } ] ] }, "Save MD File": { "main": [ [ { "node": "Add MD file in sheet", "type": "main", "index": 0 } ] ] }, "Split Images": { "main": [ [ { "node": "Extract Base64 value", "type": "main", "index": 0 } ] ] }, "Create Folder": { "main": [ [ { "node": "Create Entry in sheet", "type": "main", "index": 0 } ] ] }, "Download File": { "main": [ [ { "node": "OCR Document", "type": "main", "index": 0 } ] ] }, "Use Image Url": { "main": [ [ { "node": "Use Url", "type": "main", "index": 0 } ] ] }, "Convert to File": { "main": [ [ { "node": "Save Image", "type": "main", "index": 0 } ] ] }, "Loop over Items": { "main": [ [], [ { "node": "Set File ID", "type": "main", "index": 0 } ] ] }, "Use Document Url": { "main": [ [ { "node": "Use Url", "type": "main", "index": 0 } ] ] }, "Save Page MD File": { "main": [ [ { "node": "Merge", "type": "main", "index": 1 } ] ] }, "Save raw OCR file": { "main": [ [ { "node": "Add json file in sheet", "type": "main", "index": 0 } ] ] }, "Code in JavaScript": { "main": [ [ { "node": "Save MD File", "type": "main", "index": 0 } ] ] }, "Send Error Message": { "main": [ [ { "node": "Loop over Items", "type": "main", "index": 0 } ] ] }, "Set Error in Sheet": { "main": [ [ { "node": "Send Error Message", "type": "main", "index": 0 } ] ] }, "Add MD file in sheet": { "main": [ [ { "node": "Merge", "type": "main", "index": 0 } ] ] }, "Extract Base64 value": { "main": [ [ { "node": "Convert to File", "type": "main", "index": 0 } ] ] }, "Complete job in sheet": { "main": [ [ { "node": "Send Success Message", "type": "main", "index": 0 } ] ] }, "Create Entry in sheet": { "main": [ [ { "node": "Copy file", "type": "main", "index": 0 } ] ] }, "Send Success Message": { "main": [ [ { "node": "Loop over Items", "type": "main", "index": 0 } ] ] }, "Add json file in sheet": { "main": [ [ { "node": "Merge1", "type": "main", "index": 0 } ] ] }, "Workflow Configuration": { "main": [ [ { "node": "Create Folder", "type": "main", "index": 0 } ] ] }, "Determine Document Type": { "main": [ [ { "node": "Use Document Url", "type": "main", "index": 0 } ], [ { "node": "Use Image Url", "type": "main", "index": 0 } ], [ { "node": "Set Error in Sheet", "type": "main", "index": 0 } ] ] }, "Add Source File in Sheet": { "main": [ [ { "node": "Determine Document Type", "type": "main", "index": 0 } ] ] } } }