微学习创建器（改进版）
高级
这是一个Content Creation, Miscellaneous, Multimodal AI领域的自动化工作流，包含 25 个节点。主要使用 If, Set, Code, Merge, Slack 等节点。 使用 GPT-4 和 Google Docs 将长内容转换为碎片化学习模块
前置要求
- •Slack Bot Token 或 Webhook URL
- •OpenAI API Key
- •HTTP Webhook 端点（n8n 会自动生成）
工作流预览
可视化展示节点连接关系，支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"id": "nH6lZ9ACSB5XxZ4K",
"meta": {
"instanceId": "3c35a703d75886d08705c211ee107a7513430dd05494ec0c569f28570a3768fa",
"templateCredsSetupCompleted": true
},
"name": "微学习创建器（改进版）",
"tags": [],
"nodes": [
{
"id": "webhook-input",
"name": "内容输入",
"type": "n8n-nodes-base.webhook",
"position": [
-992,
144
],
"webhookId": "cbafb9f0-76e2-4fb4-be9d-c5872093c0d8",
"parameters": {
"path": "micro-learning-v2",
"options": {},
"httpMethod": "POST",
"responseMode": "lastNode"
},
"typeVersion": 1
},
{
"id": "validate",
"name": "验证内容",
"type": "n8n-nodes-base.if",
"position": [
-288,
144
],
"parameters": {
"conditions": {
"string": [
{
"value1": "={{ $json.body.content }}",
"operation": "isNotEmpty"
}
]
}
},
"typeVersion": 1
},
{
"id": "ai-analyzer",
"name": "AI内容分析器",
"type": "n8n-nodes-base.openAi",
"position": [
432,
64
],
"parameters": {
"model": "gpt-4.1",
"prompt": {
"messages": [
{
"content": "=Break down this content into micro-learning modules: {{ $json.body.content }}"
},
{
"role": "system",
"content": "=You are a micro-learning expert. You're receiving a section of a larger document about: \"{{ $json.chunker.topic_hint }}\".\n\nAnalyze this content section and create 2-4 focused micro-learning modules that:\n1. Cover the specific topics in this section (don't create modules about topics not mentioned)\n2. Are each 2-3 minutes to consume\n3. Use the section's actual content (don't add external information)\n4. Include practical examples from the provided text\n5. Create questions that test understanding of THIS section's content\n6. Do not Hallucinate\n\nThis is chunk {{ $json.chunker.chunk_id }} of {{ $json.chunker.total_chunks }} from a larger document.\n\nDo not include any text before or after the JSON array.\nReturn ONLY a valid JSON array with modules containing: \n\ntitle, \nkey_concept, \nexplanation (150-200 words), \npractical_example, \nquick_quiz_question. "
}
]
},
"options": {
"topP": 1,
"temperature": 0.5,
"frequency_penalty": 0
},
"resource": "chat",
"requestOptions": {}
},
"credentials": {
"openAiApi": {
"id": "PzzLblAykQPFIDZf",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "success",
"name": "成功响应",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
2304,
464
],
"parameters": {
"options": {},
"respondWith": "json",
"responseBody": "={{ $json }}"
},
"typeVersion": 1
},
{
"id": "error",
"name": "错误响应",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
32,
320
],
"parameters": {
"options": {},
"respondWith": "json",
"responseBody": "{\"error\": \"Missing content field. Please provide content to analyze.\", \"example\": {\"content\": \"Your learning content here...\"}}"
},
"typeVersion": 1
},
{
"id": "8f2cb4de-e2cf-4c7b-85c5-da1ad294850f",
"name": "提取内容",
"type": "n8n-nodes-base.set",
"position": [
-624,
144
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d1a1f21c-61ec-43d3-817d-4503eba6d3f3",
"name": "body.content",
"type": "string",
"value": "={{ $json.body.content }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "d6f42e5d-c52b-4863-9274-5d7523a17802",
"name": "分块器",
"type": "n8n-nodes-base.code",
"position": [
16,
-128
],
"parameters": {
"jsCode": "// Topic-Based Document Chunker - Smart Content Division\nconst content = $input.first().json.body.content;\nconst maxChunkSize = 4000; // Larger chunks for complete topics\nconst minChunkSize = 1000; // Minimum viable chunk size\n\nconsole.log('Original content length:', content.length, 'characters');\n\n// If content is small enough, don't chunk\nif (content.length <= maxChunkSize) {\n console.log('Content is small enough, no chunking needed');\n return items;\n}\n\nconsole.log('Content is large, applying topic-based chunking');\n\nfunction topicBasedChunk(text, maxSize, minSize) {\n const chunks = [];\n \n // Strategy 1: Split by clear section headers (most common in business docs)\n let sections = [];\n \n // Look for various header patterns\n const headerPatterns = [\n /\\n\\s*(?:\\d+\\.|Chapter \\d+|Section \\d+|Part \\d+)[\\s:]/gi, // 1. Section 1: or Chapter 1:\n /\\n\\s*[A-Z][A-Z\\s]{10,}(?:\\n|$)/g, // UPPERCASE HEADERS\n /\\n\\s*#{1,3}\\s+[^\\n]+/g, // # Markdown headers\n /\\n\\s*[^\\n]*(?:Policy|Procedure|Guidelines|Rules)[\\s:]/gi, // Policy headers\n /\\n\\s*[^\\n]*(?:Overview|Introduction|Summary|Conclusion)[\\s:]?/gi // Common section names\n ];\n \n // Try each pattern to find the best split\n for (const pattern of headerPatterns) {\n const matches = text.match(pattern);\n if (matches && matches.length >= 2) {\n console.log(`Found ${matches.length} sections using pattern:`, pattern.toString().substring(0, 50));\n sections = text.split(pattern);\n break;\n }\n }\n \n // Fallback: Split by paragraph breaks if no clear headers\n if (sections.length < 2) {\n console.log('No clear headers found, splitting by paragraphs');\n sections = text.split(/\\n\\s*\\n\\s*\\n/); // Double line breaks\n }\n \n // Strategy 2: Group sections into logical chunks\n let currentChunk = '';\n let chunkStartIndex = 0;\n \n for (let i = 0; i < sections.length; i++) {\n const section = sections[i].trim();\n if (!section) continue;\n \n const sectionWithNewline = (currentChunk ? '\\n\\n' : '') + section;\n const potentialChunk = currentChunk + sectionWithNewline;\n \n // Decision logic for chunk boundaries\n if (potentialChunk.length > maxSize && currentChunk.length >= minSize) {\n // Current chunk is full and viable - save it\n chunks.push({\n chunk_id: chunks.length + 1,\n content: currentChunk.trim(),\n topic_hint: extractTopicHint(currentChunk),\n sections_count: i - chunkStartIndex,\n length: currentChunk.length\n });\n \n console.log(`Created chunk ${chunks.length}: \"${chunks[chunks.length-1].topic_hint}\" (${currentChunk.length} chars)`);\n \n // Start new chunk\n currentChunk = section;\n chunkStartIndex = i;\n \n } else {\n // Add section to current chunk\n currentChunk = potentialChunk;\n }\n }\n \n // Don't forget the last chunk\n if (currentChunk.trim()) {\n chunks.push({\n chunk_id: chunks.length + 1,\n content: currentChunk.trim(),\n topic_hint: extractTopicHint(currentChunk),\n sections_count: sections.length - chunkStartIndex,\n length: currentChunk.length\n });\n \n console.log(`Created final chunk ${chunks.length}: \"${chunks[chunks.length-1].topic_hint}\" (${currentChunk.length} chars)`);\n }\n \n return chunks;\n}\n\n// Helper function to extract topic hints from content\nfunction extractTopicHint(text) {\n const firstLine = text.split('\\n')[0].trim();\n \n // Look for clear topic indicators\n const topicPatterns = [\n /(?:policy|procedure|guideline|rule|protocol)s?\\s+(?:for|on|about)\\s+([^.]+)/gi,\n /(?:section|chapter|part)\\s+\\d+[:\\s]+([^.\\n]+)/gi,\n /^([^.\\n]{10,50})(?:\\.|:|\\n)/, // First substantial line\n /([A-Z][^.\\n]{10,40})/ // Capitalized phrases\n ];\n \n for (const pattern of topicPatterns) {\n const match = firstLine.match(pattern);\n if (match && match[1]) {\n return match[1].trim().substring(0, 40);\n }\n }\n \n // Fallback: first meaningful words\n const words = text.split(/\\s+/).slice(0, 6).join(' ');\n return words.length > 50 ? words.substring(0, 47) + '...' : words;\n}\n\n// Apply the chunking\nconst chunks = topicBasedChunk(content, maxChunkSize, minChunkSize);\n\nconsole.log('=== CHUNKING RESULTS ===');\nconsole.log(`Created ${chunks.length} topic-based chunks:`);\nchunks.forEach((chunk, i) => {\n console.log(` ${i+1}. \"${chunk.topic_hint}\" - ${chunk.length} chars, ${chunk.sections_count} sections`);\n});\n\n// Return chunks with enhanced metadata\nconst result = chunks.map(chunk => ({\n json: {\n ...items[0].json, // Keep original metadata\n content: chunk.content,\n chunk_info: {\n chunk_id: chunk.chunk_id,\n total_chunks: chunks.length,\n chunk_size: chunk.length,\n topic_hint: chunk.topic_hint,\n sections_in_chunk: chunk.sections_count,\n chunking_strategy: 'topic-based'\n },\n is_chunked: chunks.length > 1,\n original_content_length: content.length\n }\n}));\n\nconsole.log('Returning', result.length, 'topic-based chunks for AI processing');\nreturn result;"
},
"typeVersion": 2
},
{
"id": "ce7acd35-9c73-430c-976a-9384e6da9174",
"name": "拆分输出",
"type": "n8n-nodes-base.splitOut",
"position": [
1040,
-32
],
"parameters": {
"options": {},
"fieldToSplitOut": "modules"
},
"typeVersion": 1
},
{
"id": "a9eb5bf0-761d-4e38-b6ae-f86499e50d26",
"name": "更新文档",
"type": "n8n-nodes-base.googleDocs",
"position": [
2032,
736
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "={{ $('Merge').item.json.google_docs_content }}",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "={{ $json.id }}"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "I3SWEhEVJoaLogmU",
"name": "Google Docs account"
}
},
"typeVersion": 2
},
{
"id": "2dd7a638-7d51-47fc-8203-945d7c336874",
"name": "创建文档",
"type": "n8n-nodes-base.googleDocs",
"position": [
1808,
736
],
"parameters": {
"title": "={{ $('Format_Output').item.json.course_id }}",
"folderId": "default"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "I3SWEhEVJoaLogmU",
"name": "Google Docs account"
}
},
"executeOnce": true,
"typeVersion": 2
},
{
"id": "e1019640-d08a-476b-91d1-80c1905556ef",
"name": "格式化输出",
"type": "n8n-nodes-base.code",
"position": [
768,
224
],
"parameters": {
"jsCode": "// Fixed merge code for OpenAI message format\nconsole.log('=== MERGE PROCESSING ===');\nconsole.log('Total items received:', items.length);\n\nlet allModules = [];\nlet processingErrors = [];\n\n// Process each item from the AI Content Analyzer\nfor (let i = 0; i < items.length; i++) {\n const item = items[i];\n console.log('Processing item', i + 1);\n \n if (item && item.json && item.json.message && item.json.message.content) {\n const aiResponseString = item.json.message.content;\n console.log('Found AI response string, length:', aiResponseString.length);\n \n try {\n // Parse the JSON string from the AI response\n const parsedModules = JSON.parse(aiResponseString);\n \n if (Array.isArray(parsedModules)) {\n console.log('Successfully parsed', parsedModules.length, 'modules from item', i + 1);\n allModules = allModules.concat(parsedModules);\n } else {\n console.log('Parsed content is not an array for item', i + 1);\n processingErrors.push('Item ' + (i + 1) + ' - Not an array');\n }\n \n } catch (error) {\n console.log('JSON parse error for item', i + 1, ':', error.message);\n processingErrors.push('Item ' + (i + 1) + ' - Parse error: ' + error.message);\n }\n \n } else {\n console.log('Item', i + 1, 'missing expected structure');\n processingErrors.push('Item ' + (i + 1) + ' - Missing message.content');\n }\n}\n\nconsole.log('=== PROCESSING SUMMARY ===');\nconsole.log('Total modules extracted:', allModules.length);\nconsole.log('Processing errors:', processingErrors.length);\n\n// Remove duplicates based on title\nconst uniqueModules = [];\nconst seenTitles = new Set();\n\nfor (let i = 0; i < allModules.length; i++) {\n const module = allModules[i];\n const normalizedTitle = (module.title || 'untitled').toLowerCase().trim();\n \n if (!seenTitles.has(normalizedTitle)) {\n seenTitles.add(normalizedTitle);\n uniqueModules.push(module);\n } else {\n console.log('Skipping duplicate module:', module.title);\n }\n}\n\nconsole.log('Unique modules after deduplication:', uniqueModules.length);\n\n// Create final result with all modules\nconst result = {\n course_id: 'course_' + Date.now(),\n total_modules: uniqueModules.length,\n estimated_total_time: uniqueModules.length * 3 + ' minutes',\n difficulty_level: uniqueModules.length <= 3 ? 'beginner' : uniqueModules.length <= 5 ? 'intermediate' : 'advanced',\n created_at: new Date().toISOString(),\n \n processing_info: {\n chunks_processed: items.length,\n modules_found: allModules.length,\n modules_after_dedup: uniqueModules.length,\n processing_errors: processingErrors\n },\n \n modules: uniqueModules.map((module, index) => ({\n id: 'module_' + (index + 1),\n sequence: index + 1,\n title: module.title || 'Module ' + (index + 1),\n key_concept: module.key_concept || 'Key concept not provided',\n content: module.explanation || 'Content not provided',\n example: module.practical_example || 'Example not provided',\n quiz: module.quick_quiz_question || 'Question not provided',\n estimated_minutes: 3,\n \n // Multi-channel formats\n formats: {\n email: {\n subject: '📚 Module ' + (index + 1) + ': ' + (module.title || 'Untitled'),\n body: '🎯 **Key Concept**: ' + (module.key_concept || 'N/A') + '\\n\\n📖 **Learn This**:\\n' + (module.explanation || 'N/A') + '\\n\\n💡 **Real Example**: ' + (module.practical_example || 'N/A') + '\\n\\n❓ **Quick Check**: ' + (module.quick_quiz_question || 'N/A') + '\\n\\n⏱️ **Time**: 3 minutes'\n },\n \n slack: {\n text: '📚 *Module ' + (index + 1) + ': ' + (module.title || 'Untitled') + '*\\n\\n🎯 *Key*: ' + (module.key_concept || 'N/A') + '\\n\\n' + (module.explanation || 'N/A') + '\\n\\n💡 *Example*: ' + (module.practical_example || 'N/A') + '\\n\\n❓ *Quiz*: ' + (module.quick_quiz_question || 'N/A') + '\\n\\n⏱️ 3 min read'\n },\n \n mobile: '📚 ' + (module.title || 'Untitled') + '\\n\\n🎯 ' + (module.key_concept || 'N/A') + '\\n\\n' + (module.explanation || 'N/A') + '\\n\\n💡 ' + (module.practical_example || 'N/A') + '\\n\\n❓ ' + (module.quick_quiz_question || 'N/A') + '\\n\\n⏱️ 3 min'\n }\n }))\n};\n\nconsole.log('=== FINAL RESULT ===');\nconsole.log('Returning course with', result.total_modules, 'modules');\nconsole.log('Module titles:', result.modules.map(m => m.title));\n\nreturn [{ json: result }];"
},
"typeVersion": 2
},
{
"id": "cd6e38e3-64c6-4c9d-9d87-9f79a29fa195",
"name": "编辑字段",
"type": "n8n-nodes-base.set",
"position": [
1024,
672
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e63b0306-2fc5-4d8c-bde0-87f1c450762d",
"name": "course_id",
"type": "string",
"value": "={{ $json.course_id }}"
},
{
"id": "b823595a-0e14-4c0a-9965-9d429735ba3b",
"name": "total_modules",
"type": "number",
"value": "={{ $json.total_modules }}"
},
{
"id": "582ab2a2-4a88-4cfa-9e16-253f10cc9d0f",
"name": "estimated_total_time",
"type": "string",
"value": "={{ $json.estimated_total_time }}"
},
{
"id": "959c51e8-e588-4a20-ae1c-bd79e17e1941",
"name": "difficulty_level",
"type": "string",
"value": "={{ $json.difficulty_level }}"
},
{
"id": "750c4608-acc1-4097-bb6d-6c66ade37be0",
"name": "created_at",
"type": "string",
"value": "={{ $json.created_at }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "709671a3-a263-46b2-9d29-7ffb77894f37",
"name": "合并",
"type": "n8n-nodes-base.merge",
"position": [
1408,
736
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3.2
},
{
"id": "2fe4d651-6820-4a04-a080-a593cf74221e",
"name": "无操作，不执行任何操作",
"type": "n8n-nodes-base.noOp",
"position": [
1952,
-272
],
"parameters": {},
"typeVersion": 1
},
{
"id": "4152f8e3-fad2-4f29-b6fb-9c5c14204067",
"name": "无操作，什么也不做1",
"type": "n8n-nodes-base.noOp",
"position": [
288,
464
],
"parameters": {},
"typeVersion": 1
},
{
"id": "adb4236e-2b96-4eab-b42e-de6c13696232",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-736,
-224
],
"parameters": {
"width": 368,
"height": 544,
"content": "# 内容准备"
},
"typeVersion": 1
},
{
"id": "slack-notify",
"name": "Slack模块",
"type": "n8n-nodes-base.slack",
"position": [
1536,
-96
],
"webhookId": "88b71c18-bb46-4fc1-a464-c33f5da4505e",
"parameters": {
"text": "=Title: {{ $json.title }}\nModule: {{ $json.sequence }}\nID: {{ $json.id }}\nTime: {{ $json.estimated_minutes }} minutes\n\n{{ $json.formats.slack.text }}\n-------------------------------------",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "C0963H18JCX",
"cachedResultName": "all-mytest2025"
},
"otherOptions": {
"mrkdwn": true
}
},
"credentials": {
"slackApi": {
"id": "TjO2nAExXHrUpUIC",
"name": "Slack account"
}
},
"typeVersion": 2
},
{
"id": "12566e4f-2759-4d8f-b597-8320fbd38b49",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-144,
-528
],
"parameters": {
"width": 416,
"height": 544,
"content": "# 智能内容分块"
},
"typeVersion": 1
},
{
"id": "bc48247f-6ba3-452b-8f0f-868000abc254",
"name": "便签 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
320,
-384
],
"parameters": {
"width": 336,
"height": 608,
"content": "# AI内容处理"
},
"typeVersion": 1
},
{
"id": "dd2956a1-1a92-4ff0-b935-ce2de38b4191",
"name": "便签 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
672,
-288
],
"parameters": {
"width": 304,
"height": 672,
"content": "# 模块格式化器"
},
"typeVersion": 1
},
{
"id": "1c7ead8b-a53f-47a2-9a01-f30aff48dc08",
"name": "Google格式化器",
"type": "n8n-nodes-base.code",
"position": [
1504,
400
],
"parameters": {
"jsCode": "// Google Docs Formatter - Handles Individual Modules\nconsole.log('Processing', items.length, 'module items');\n\n// Check if we have individual modules or course data\nlet modules = [];\nlet courseMetadata = {};\n\nif (items.length === 1 && items[0].json.modules) {\n // Single course object with modules array\n const courseData = items[0].json;\n modules = courseData.modules;\n courseMetadata = courseData;\n} else {\n // Multiple individual module objects\n modules = items.map(item => item.json);\n \n // Extract course metadata from first module or create defaults\n courseMetadata = {\n course_id: 'Generated Course',\n total_modules: modules.length,\n estimated_total_time: `${modules.length * 3} minutes`,\n difficulty_level: modules.length <= 3 ? 'beginner' : modules.length <= 5 ? 'intermediate' : 'advanced',\n created_at: new Date().toISOString()\n };\n}\n\n// Sort modules by sequence\nmodules.sort((a, b) => (a.sequence || 0) - (b.sequence || 0));\n\nconsole.log('Found', modules.length, 'modules to process');\n\n// Extract course metadata with fallbacks\nconst courseTitle = \"Template Submission Guidelines - Micro-Learning Course\";\nconst courseId = courseMetadata.course_id || 'Generated Course';\nconst totalModules = courseMetadata.total_modules || modules.length;\nconst estimatedTime = courseMetadata.estimated_total_time || `${modules.length * 3} minutes`;\nconst difficultyLevel = courseMetadata.difficulty_level || 'intermediate';\nconst createdDate = courseMetadata.created_at ? new Date(courseMetadata.created_at).toLocaleDateString() : new Date().toLocaleDateString();\n\n// Start building the Google Docs formatted content\nlet googleDocsContent = `${courseTitle}\n\nCOURSE OVERVIEW\nCourse ID: ${courseId}\nTotal Modules: ${totalModules}\nEstimated Completion Time: ${estimatedTime}\nDifficulty Level: ${difficultyLevel.toUpperCase()}\nCreated: ${createdDate}\n\n===============================================\n\n`;\n\n// Process each module\nmodules.forEach((module, index) => {\n const moduleNum = module.sequence || (index + 1);\n const title = module.title || `Module ${moduleNum}`;\n const duration = module.estimated_minutes || 3;\n const keyConcept = module.key_concept || 'Key concept not provided';\n const content = module.content || 'Content not provided';\n const example = module.example || module.practical_example || 'Example not provided';\n const quiz = module.quiz || module.quick_quiz_question || 'Quiz question not provided';\n\n googleDocsContent += `MODULE ${moduleNum}: ${title}\nDuration: ${duration} minutes\n\nKEY CONCEPT\n${keyConcept}\n\nCONTENT\n${content}\n\nPRACTICAL EXAMPLE\n${example}\n\nKNOWLEDGE CHECK\n${quiz}\n\n---\n\n`;\n});\n\n// Add completion section\ngoogleDocsContent += `COURSE COMPLETION\nCongratulations! You have completed all ${totalModules} modules of the Template Submission Guidelines course.\n\nTotal time invested: ${estimatedTime}\nKnowledge areas covered:\n`;\n\n// Add module summary\nmodules.forEach((module, index) => {\n const title = module.title || `Module ${index + 1}`;\n googleDocsContent += `• ${title}\\n`;\n});\n\ngoogleDocsContent += `\nFor additional questions or clarification on template submission guidelines, please refer to the official documentation or contact support.\n\nDocument generated: ${new Date().toLocaleString()}`;\n\n// Return the formatted content\nconst result = {\n google_docs_content: googleDocsContent,\n metadata: {\n original_course_id: courseId,\n modules_processed: modules.length,\n formatted_at: new Date().toISOString(),\n content_length: googleDocsContent.length,\n estimated_pages: Math.ceil(googleDocsContent.length / 2500)\n },\n debug_info: {\n input_items: items.length,\n modules_found: modules.length,\n first_module_title: modules[0]?.title || 'N/A',\n data_format: items.length === 1 ? 'single_course' : 'individual_modules'\n }\n};\n\nconsole.log('Google Docs format generated successfully');\nconsole.log('Content length:', googleDocsContent.length, 'characters');\nconsole.log('Modules processed:', modules.length);\n\nreturn [{ json: result }];"
},
"typeVersion": 2
},
{
"id": "d73fc192-416b-4d81-b993-8381ceffae80",
"name": "便签 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1152,
240
],
"parameters": {
"width": 512,
"height": 432,
"content": "# Google文档转换器"
},
"typeVersion": 1
},
{
"id": "6b4acc67-8681-46b9-9ae4-973274e2c2a3",
"name": "便签 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1296,
-576
],
"parameters": {
"width": 560,
"height": 656,
"content": "团队通知"
},
"typeVersion": 1
},
{
"id": "bd6f3caf-736a-4ef3-a3a9-4c9a98a552d7",
"name": "Slack课程详情",
"type": "n8n-nodes-base.slack",
"position": [
1536,
-272
],
"webhookId": "88b71c18-bb46-4fc1-a464-c33f5da4505e",
"parameters": {
"text": "=🎉 *New Micro-Learning Course Created!*📊 \n**Course Details**: \nCourse ID: {{ $('Format_Output').item.json.course_id }}\nTotal Modules: {{ $('Format_Output').item.json.total_modules }}\nTotal Estimated Time: {{ $('Format_Output').item.json.estimated_total_time }}\n",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "C0963H18JCX",
"cachedResultName": "all-mytest2025"
},
"otherOptions": {
"mrkdwn": true
}
},
"credentials": {
"slackApi": {
"id": "TjO2nAExXHrUpUIC",
"name": "Slack account"
}
},
"executeOnce": true,
"typeVersion": 2
},
{
"id": "f3f9b3fb-662d-466d-9961-91dd57622eb7",
"name": "便签6",
"type": "n8n-nodes-base.stickyNote",
"position": [
1728,
496
],
"parameters": {
"width": 480,
"height": 432,
"content": "# 创建Google文档"
},
"typeVersion": 1
}
],
"active": true,
"pinData": {},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true,
"saveExecutionProgress": true,
"saveDataErrorExecution": "all",
"saveDataSuccessExecution": "all"
},
"versionId": "b2e4b490-199e-48e5-8c70-6311cd94c066",
"connections": {
"Merge": {
"main": [
[
{
"node": "Create a document",
"type": "main",
"index": 0
}
]
]
},
"Chunker": {
"main": [
[
{
"node": "AI Content Analyzer",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Google Formatter",
"type": "main",
"index": 0
},
{
"node": "Slack Modules",
"type": "main",
"index": 0
},
{
"node": "Slack Course Details",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Content Input": {
"main": [
[
{
"node": "Extract Content",
"type": "main",
"index": 0
}
]
]
},
"Format_Output": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
},
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Slack Modules": {
"main": [
[
{
"node": "Success Response",
"type": "main",
"index": 0
}
]
]
},
"Error Response": {
"main": [
[
{
"node": "No Operation, do nothing1",
"type": "main",
"index": 0
}
]
]
},
"Extract Content": {
"main": [
[
{
"node": "Validate Content",
"type": "main",
"index": 0
}
]
]
},
"Google Formatter": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Success Response": {
"main": [
[]
]
},
"Validate Content": {
"main": [
[
{
"node": "Chunker",
"type": "main",
"index": 0
}
],
[
{
"node": "Error Response",
"type": "main",
"index": 0
}
]
]
},
"Create a document": {
"main": [
[
{
"node": "Update a document",
"type": "main",
"index": 0
}
]
]
},
"Update a document": {
"main": [
[
{
"node": "Success Response",
"type": "main",
"index": 0
}
]
]
},
"AI Content Analyzer": {
"main": [
[
{
"node": "Format_Output",
"type": "main",
"index": 0
}
]
]
},
"Slack Course Details": {
"main": [
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
高级 - 内容创作, 杂项, 多模态 AI
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
故事锻造AI V2.09.25
使用DeepSeek、RunwayML、ElevenLabs和Creatomate将创意转换为电影
Set
Code
Wait
+13
45 节点Țugui Dragoș
内容创作
使用Groq、Gemini和Slack审批系统自动化RSS到Medium发布
通过Groq、Gemini和Slack审批系统实现RSS到Medium发布的自动化流程
If
Set
Code
+16
41 节点ObisDev
内容创作
旅行故事讲述器
使用GPT-4O Vision将旅行照片转换为叙事故事
Set
Code
Merge
+5
19 节点inderjeet Bhambra
内容创作
使用 OpenAI、LangChain 和 API 集成的工作流自动化初学者指南
使用 OpenAI、LangChain 和 API 集成的工作流自动化初学者指南
If
Set
Code
+13
33 节点Meelioo
内容创作
防欺诈潜在客户捕获与培育系统
通过AI评分、表格跟踪和多渠道提醒捕获和培育防欺诈潜在客户
If
Set
Code
+11
28 节点Jitesh Dugar
内容创作
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
If
Set
Code
+20
52 节点Daniel Lianes
杂项
工作流信息
难度等级
高级
节点数量25
分类3
节点类型12
作者
inderjeet Bhambra
@idsinghbhambraI am on a journey to learn and spread the automations through n8n workflows.
外部链接
在 n8n.io 查看 →
分享此工作流