vinci-king-01 This workflow corresponds to n8n.io template #6691 — we link there as the canonical source.
This workflow follows the Form Trigger → 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 →
{
"id": "VhEwspDqzu7ssFVE",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "My workflow 2",
"tags": [
{
"id": "DxXGubfBzRKh6L8T",
"name": "Revenue Optimization",
"createdAt": "2025-07-25T16:24:30.370Z",
"updatedAt": "2025-07-25T16:24:30.370Z"
},
{
"id": "IxkcJ2IpYIxivoHV",
"name": "Content Strategy",
"createdAt": "2025-07-25T12:57:37.677Z",
"updatedAt": "2025-07-25T12:57:37.677Z"
},
{
"id": "PAKIJ2Mm9EvRcR3u",
"name": "Trend Monitoring",
"createdAt": "2025-07-25T12:57:37.670Z",
"updatedAt": "2025-07-25T12:57:37.670Z"
},
{
"id": "YtfXmaZk44MYedPO",
"name": "Dynamic Pricing",
"createdAt": "2025-07-25T16:24:30.369Z",
"updatedAt": "2025-07-25T16:24:30.369Z"
},
{
"id": "wJ30mjhtrposO8Qt",
"name": "Simple RAG",
"createdAt": "2025-07-28T12:55:14.424Z",
"updatedAt": "2025-07-28T12:55:14.424Z"
}
],
"nodes": [
{
"id": "0247527a-478c-4ce6-a999-cea55f4923ac",
"name": "\ud83d\ude80 Advanced RAG Form",
"type": "n8n-nodes-base.formTrigger",
"position": [
-1696,
160
],
"parameters": {
"options": {},
"formTitle": "\ud83e\udde0 Enterprise RAG Assistant",
"formFields": {
"values": [
{
"fieldType": "textarea",
"fieldLabel": "query",
"requiredField": true
},
{
"fieldType": "select",
"fieldLabel": "search_scope",
"requiredField": true
},
{
"fieldType": "select",
"fieldLabel": "response_style"
},
{
"fieldType": "select",
"fieldLabel": "language"
},
{
"fieldType": "select",
"fieldLabel": "output_format"
},
{
"fieldType": "email",
"fieldLabel": "user_email"
},
{
"fieldType": "select",
"fieldLabel": "priority_level"
}
]
},
"formDescription": "Advanced RAG system for intelligent research and content generation"
},
"typeVersion": 2.2
},
{
"id": "97c556f7-c675-4fb7-9e31-10926885485a",
"name": "\ud83d\udccb Form Configuration",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1760,
-512
],
"parameters": {
"color": 4,
"width": 650,
"height": 600,
"content": "# Advanced RAG Form \ud83d\ude80\n\n**Intelligent Input System:**\n- Advanced query processing\n- Search scope selection\n- Response style customization\n- Multi-language support\n- Diverse output formats\n\n**Main Fields:**\n- **Query**: User input (textarea)\n- **Search Scope**: Web/Academic/News/Technical/Internal\n- **Response Style**: Comprehensive/Concise/Technical/Executive\n- **Language**: IT/EN/ES/FR/DE\n- **Output Format**: MD/HTML/PDF/JSON/PPT\n- **Email**: For notifications\n- **Priority**: Queue management\n\n**Features:**\n\u2705 Real-time input validation\n\u2705 Webhook response for feedback\n\u2705 Multi-format support\n\u2705 Priority queue management"
},
"typeVersion": 1
},
{
"id": "de5b5d88-8e1e-4bfc-91bf-905d709a6cb9",
"name": "\ud83d\udd0d Query Preprocessor",
"type": "n8n-nodes-base.code",
"position": [
-1376,
160
],
"parameters": {
"jsCode": "// Input validation and preprocessing\nconst input = $input.all()[0].json;\n\n// Validate required fields\nif (!input.query || input.query.trim().length < 3) {\n throw new Error('Query too short. Please enter at least 3 characters.');\n}\n\n// Clean and preprocess query\nconst processedQuery = {\n original_query: input.query,\n cleaned_query: input.query.trim().replace(/\\s+/g, ' '),\n query_length: input.query.trim().length,\n estimated_complexity: input.query.split(' ').length > 10 ? 'high' : 'medium',\n search_scope: input.search_scope || 'web_general',\n response_style: input.response_style || 'comprehensive',\n language: input.language || 'italian',\n output_format: input.output_format || 'markdown',\n priority_level: input.priority_level || 'medium',\n user_email: input.user_email || null,\n session_id: `rag_${Date.now()}_${Math.random().toString(36).substr(2, 9)}`,\n timestamp: new Date().toISOString(),\n processing_steps: []\n};\n\n// Add processing metadata\nprocessedQuery.processing_steps.push({\n step: 'input_validation',\n status: 'completed',\n timestamp: new Date().toISOString()\n});\n\n// Generate search keywords from query\nconst keywords = processedQuery.cleaned_query\n .toLowerCase()\n .split(' ')\n .filter(word => word.length > 3)\n .slice(0, 8);\n\nprocessedQuery.search_keywords = keywords;\n\n// Determine search strategy based on scope\nconst searchStrategies = {\n 'web_general': ['google', 'bing', 'duckduckgo'],\n 'academic_papers': ['scholar', 'arxiv', 'pubmed'],\n 'news_articles': ['news_api', 'rss_feeds'],\n 'technical_docs': ['github', 'stackoverflow', 'documentation'],\n 'company_internal': ['drive', 'confluence', 'notion'],\n 'multi_source': ['google', 'scholar', 'news_api', 'github']\n};\n\nprocessedQuery.search_strategy = searchStrategies[processedQuery.search_scope] || ['google'];\n\nconsole.log('Processed query:', JSON.stringify(processedQuery, null, 2));\n\nreturn [{ json: processedQuery }];"
},
"typeVersion": 2
},
{
"id": "00133ca9-7379-4692-9500-35289f24c5f0",
"name": "\ud83d\udd04 Search Router",
"type": "n8n-nodes-base.if",
"position": [
-1056,
160
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "scope-check",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.search_scope }}",
"rightValue": "company_internal"
}
]
}
},
"typeVersion": 2
},
{
"id": "377114fa-2f1b-4135-a054-86ac460fc319",
"name": "\ud83c\udfe2 Internal Knowledge Search",
"type": "n8n-nodes-base.googleDriveSearch",
"position": [
-1056,
368
],
"parameters": {},
"typeVersion": 1
},
{
"id": "48da1505-73dd-424f-8c70-fa54ef66cf2c",
"name": "\ud83c\udf10 Enhanced Web Search",
"type": "n8n-nodes-base.webSearch",
"position": [
-1056,
-48
],
"parameters": {},
"typeVersion": 1
},
{
"id": "9a805200-52bb-4e8b-8435-87be41b23c40",
"name": "\ud83c\udf93 Academic Papers Search",
"type": "n8n-nodes-base.httpRequest",
"position": [
-736,
64
],
"parameters": {
"url": "https://api.crossref.org/works",
"options": {
"timeout": 30000
},
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "query",
"value": "={{ $json.cleaned_query }}"
},
{
"name": "rows",
"value": "10"
},
{
"name": "sort",
"value": "relevance"
},
{
"name": "order",
"value": "desc"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "e441e67d-4de3-41cf-939b-3232f7389fe3",
"name": "\ud83d\udcf0 News Search API",
"type": "n8n-nodes-base.httpRequest",
"position": [
-736,
272
],
"parameters": {
"url": "https://newsapi.org/v2/everything",
"options": {
"timeout": 30000
},
"sendQuery": true,
"authentication": "headerAuth",
"queryParameters": {
"parameters": [
{
"name": "q",
"value": "={{ $json.cleaned_query }}"
},
{
"name": "sortBy",
"value": "relevancy"
},
{
"name": "pageSize",
"value": "10"
},
{
"name": "language",
"value": "={{ $json.language === 'italian' ? 'it' : 'en' }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "4faa39af-1e65-4f1b-8a54-3648f0cc285a",
"name": "\ud83d\udcca Data Aggregator",
"type": "n8n-nodes-base.code",
"position": [
-416,
160
],
"parameters": {
"jsCode": "// Advanced data aggregation and processing\nconst allInputs = $input.all();\nlet aggregatedData = {\n session_id: '',\n query_info: {},\n sources: [],\n total_results: 0,\n processing_time: Date.now(),\n quality_score: 0\n};\n\n// Process each input source\nallInputs.forEach((input, index) => {\n const data = input.json;\n \n // Extract session info from first input\n if (index === 0) {\n aggregatedData.session_id = data.session_id || `rag_${Date.now()}`;\n aggregatedData.query_info = {\n original_query: data.original_query || data.cleaned_query,\n cleaned_query: data.cleaned_query,\n search_scope: data.search_scope,\n response_style: data.response_style || 'comprehensive',\n language: data.language || 'italian'\n };\n }\n \n // Process web search results\n if (data.results && Array.isArray(data.results)) {\n data.results.forEach(item => {\n aggregatedData.sources.push({\n type: 'web_content',\n title: item.title || 'Web Content',\n content: item.snippet || item.description || '',\n url: item.url || item.link || '',\n relevance_score: 0.8,\n source_quality: 'high',\n timestamp: new Date().toISOString()\n });\n });\n }\n \n // Process Google Drive results\n if (data.name && data.mimeType) {\n aggregatedData.sources.push({\n type: 'internal_document',\n title: data.name,\n content: data.content || data.description || '',\n url: data.webViewLink || '',\n relevance_score: 0.9,\n source_quality: 'internal',\n timestamp: data.modifiedTime || new Date().toISOString()\n });\n }\n \n // Process academic papers\n if (data.message && data.message.items) {\n data.message.items.forEach(paper => {\n if (paper.title && paper.abstract) {\n aggregatedData.sources.push({\n type: 'academic_paper',\n title: Array.isArray(paper.title) ? paper.title[0] : paper.title,\n content: paper.abstract || '',\n url: paper.URL || '',\n relevance_score: 0.95,\n source_quality: 'academic',\n authors: paper.author ? paper.author.map(a => `${a.given || ''} ${a.family || ''}`).join(', ') : '',\n timestamp: paper.published ? (paper.published['date-parts'] ? paper.published['date-parts'][0].join('-') : new Date().toISOString()) : new Date().toISOString()\n });\n }\n });\n }\n \n // Process news articles\n if (data.articles && Array.isArray(data.articles)) {\n data.articles.forEach(article => {\n aggregatedData.sources.push({\n type: 'news_article',\n title: article.title || 'News Article',\n content: article.description || article.content || '',\n url: article.url || '',\n relevance_score: 0.85,\n source_quality: 'news',\n author: article.author || '',\n timestamp: article.publishedAt || new Date().toISOString()\n });\n });\n }\n});\n\n// Calculate quality metrics\naggregatedData.total_results = aggregatedData.sources.length;\naggregatedData.quality_score = aggregatedData.sources.reduce((sum, source) => \n sum + source.relevance_score, 0) / Math.max(aggregatedData.total_results, 1);\n\n// Sort sources by relevance\naggregatedData.sources.sort((a, b) => b.relevance_score - a.relevance_score);\n\n// Limit to top 15 most relevant sources\naggregatedData.sources = aggregatedData.sources.slice(0, 15);\n\n// Add processing metadata\naggregatedData.processing_time = Date.now() - aggregatedData.processing_time;\naggregatedData.aggregation_timestamp = new Date().toISOString();\n\nconsole.log(`Aggregated ${aggregatedData.total_results} sources with quality score: ${aggregatedData.quality_score.toFixed(2)}`);\n\nreturn [{ json: aggregatedData }];"
},
"typeVersion": 2
},
{
"id": "52fe7489-732b-4610-afc0-2c55d4b8f535",
"name": "\ud83e\udde0 Context Builder",
"type": "n8n-nodes-base.code",
"position": [
-96,
160
],
"parameters": {
"jsCode": "// Advanced context preparation for LLM\nconst data = $input.all()[0].json;\n\n// Build comprehensive context\nlet contextSections = [];\n\n// Add query information\ncontextSections.push(`## QUERY INFORMATION\\nOriginal Query: ${data.query_info.original_query}\\nCleaned Query: ${data.query_info.cleaned_query}\\nSearch Scope: ${data.query_info.search_scope}\\nResponse Style: ${data.query_info.response_style}\\nLanguage: ${data.query_info.language}`);\n\n// Add sources with structured formatting\nif (data.sources && data.sources.length > 0) {\n contextSections.push('## RETRIEVED SOURCES');\n \n data.sources.forEach((source, index) => {\n const sourceSection = `\\n### Source ${index + 1}: ${source.title}\\n**Type**: ${source.type}\\n**Relevance**: ${(source.relevance_score * 100).toFixed(1)}%\\n**Quality**: ${source.source_quality}\\n**URL**: ${source.url}\\n${source.author ? `**Author**: ${source.author}` : ''}\\n**Timestamp**: ${source.timestamp}\\n\\n**Content**:\\n${source.content.substring(0, 1500)}${source.content.length > 1500 ? '...' : ''}\\n`;\n \n contextSections.push(sourceSection);\n });\n}\n\n// Add metadata\ncontextSections.push(`## METADATA\\nTotal Sources: ${data.total_results}\\nQuality Score: ${(data.quality_score * 100).toFixed(1)}%\\nProcessing Time: ${data.processing_time}ms\\nSession ID: ${data.session_id}`);\n\n// Create comprehensive context\nconst fullContext = contextSections.join('\\n\\n');\n\n// Prepare messages for LLM based on response style\nconst stylePrompts = {\n 'comprehensive': 'Provide a complete and detailed response, using all relevant information from the sources. Include specific examples and citations.',\n 'concise': 'Provide a brief and direct response, keeping only the most important information.',\n 'technical': 'Provide a detailed technical response with specific terminology and implementation details.',\n 'executive_summary': 'Provide an executive summary with key points, recommendations and next steps.',\n 'bullet_points': 'Organize the response in clear and structured bullet points.',\n 'detailed_analysis': 'Provide an in-depth analysis with pros/cons, implications and multiple considerations.'\n};\n\nconst stylePrompt = stylePrompts[data.query_info.response_style] || stylePrompts['comprehensive'];\n\n// Language-specific instructions\nconst languageInstructions = {\n 'italian': 'Respond in Italian',\n 'english': 'Respond in English',\n 'spanish': 'Respond in Spanish',\n 'french': 'Respond in French',\n 'german': 'Respond in German'\n};\n\nconst langInstruction = languageInstructions[data.query_info.language] || languageInstructions['english'];\n\n// Create system message\nconst systemMessage = `You are an advanced AI assistant specialized in RAG (Retrieval-Augmented Generation). \\n\\nINSTRUCTIONS:\\n1. ${langInstruction}\\n2. ${stylePrompt}\\n3. ALWAYS use information from the provided sources\\n4. Cite sources using [Source X] when appropriate\\n5. If information is insufficient, clearly indicate what is missing\\n6. Maintain accuracy and objectivity\\n7. Structure the response logically and readably\\n\\nCONTEXT AND SOURCES:\\n${fullContext}`;\n\n// Create user message\nconst userMessage = `Based exclusively on the sources provided in the context, ${data.query_info.original_query}`;\n\nconst result = {\n messages: [\n {\n role: 'system',\n content: systemMessage\n },\n {\n role: 'user', \n content: userMessage\n }\n ],\n context_length: fullContext.length,\n sources_count: data.sources.length,\n session_id: data.session_id,\n query_info: data.query_info,\n context_prepared_at: new Date().toISOString()\n};\n\nconsole.log(`Context prepared: ${result.context_length} chars, ${result.sources_count} sources`);\n\nreturn [{ json: result }];"
},
"typeVersion": 2
},
{
"id": "172349cf-ce97-46d0-bb69-f679605e89c2",
"name": "\ud83e\udd16 Advanced LLM Processor",
"type": "n8n-nodes-base.openAi",
"position": [
224,
160
],
"parameters": {
"model": "gpt-4-turbo-preview",
"options": {
"topP": 0.9,
"maxTokens": 2048,
"temperature": 0.3
},
"requestOptions": {}
},
"typeVersion": 1
},
{
"id": "b34adec5-1506-485e-a671-8ee862a0fa7d",
"name": "\u2728 Response Enhancer",
"type": "n8n-nodes-base.code",
"position": [
544,
160
],
"parameters": {
"jsCode": "// Post-processing and response enhancement\nconst llmResponse = $input.all()[0].json;\nconst contextData = $('Context Builder').first().json;\n\n// Extract the AI response\nconst aiResponse = llmResponse.choices?.[0]?.message?.content || llmResponse.content || '';\n\n// Build comprehensive response object\nconst enhancedResponse = {\n // Core response\n response: aiResponse,\n \n // Metadata\n session_id: contextData.session_id,\n query: contextData.query_info.original_query,\n response_style: contextData.query_info.response_style,\n language: contextData.query_info.language,\n \n // Quality metrics\n response_length: aiResponse.length,\n sources_used: contextData.sources_count,\n context_length: contextData.context_length,\n \n // Processing info\n generated_at: new Date().toISOString(),\n model_used: 'gpt-4-turbo-preview',\n \n // Usage statistics\n tokens_used: llmResponse.usage?.total_tokens || 0,\n prompt_tokens: llmResponse.usage?.prompt_tokens || 0,\n completion_tokens: llmResponse.usage?.completion_tokens || 0,\n \n // Source summary\n source_breakdown: {\n web_content: contextData.query_info.search_scope === 'web_general' ? contextData.sources_count : 0,\n internal_docs: contextData.query_info.search_scope === 'company_internal' ? contextData.sources_count : 0,\n academic_papers: contextData.query_info.search_scope === 'academic_papers' ? contextData.sources_count : 0,\n news_articles: contextData.query_info.search_scope === 'news_articles' ? contextData.sources_count : 0\n },\n \n // Response quality indicators\n quality_indicators: {\n has_citations: aiResponse.includes('[Source') || aiResponse.includes('fonte'),\n response_completeness: aiResponse.length > 200 ? 'complete' : 'partial',\n source_integration: contextData.sources_count > 0 ? 'good' : 'limited',\n estimated_accuracy: contextData.sources_count >= 3 ? 'high' : 'medium'\n }\n};\n\n// Format response based on output format preference\nconst outputFormat = contextData.query_info.output_format || 'markdown';\n\nswitch (outputFormat) {\n case 'html':\n enhancedResponse.formatted_response = `\n<!DOCTYPE html>\n<html>\n<head>\n <title>RAG Response - ${contextData.query_info.original_query}</title>\n <style>\n body { font-family: Arial, sans-serif; max-width: 800px; margin: 0 auto; padding: 20px; }\n .header { background: #f5f5f5; padding: 15px; border-radius: 5px; margin-bottom: 20px; }\n .response { line-height: 1.6; }\n .metadata { background: #e9f4ff; padding: 10px; border-radius: 5px; margin-top: 20px; font-size: 0.9em; }\n </style>\n</head>\n<body>\n <div class=\"header\">\n <h1>RAG Response</h1>\n <p><strong>Query:</strong> ${contextData.query_info.original_query}</p>\n <p><strong>Generated:</strong> ${enhancedResponse.generated_at}</p>\n </div>\n <div class=\"response\">\n ${aiResponse.replace(/\\n/g, '<br>')}\n </div>\n <div class=\"metadata\">\n <strong>Sources Used:</strong> ${enhancedResponse.sources_used} | \n <strong>Tokens:</strong> ${enhancedResponse.tokens_used} | \n <strong>Session:</strong> ${enhancedResponse.session_id}\n </div>\n</body>\n</html>`;\n break;\n \n case 'json_structured':\n enhancedResponse.formatted_response = JSON.stringify({\n query: contextData.query_info.original_query,\n response: aiResponse,\n metadata: {\n sources_count: enhancedResponse.sources_used,\n tokens_used: enhancedResponse.tokens_used,\n quality_score: enhancedResponse.quality_indicators,\n session_id: enhancedResponse.session_id\n }\n }, null, 2);\n break;\n \n default: // markdown\n enhancedResponse.formatted_response = `# RAG Response\\n\\n**Query:** ${contextData.query_info.original_query}\\n\\n---\\n\\n${aiResponse}\\n\\n---\\n\\n**Metadata:**\\n- Sources Used: ${enhancedResponse.sources_used}\\n- Tokens Used: ${enhancedResponse.tokens_used}\\n- Generated: ${enhancedResponse.generated_at}\\n- Session ID: ${enhancedResponse.session_id}`;\n}\n\nconsole.log(`Response generated: ${enhancedResponse.response_length} chars, ${enhancedResponse.tokens_used} tokens`);\n\nreturn [{ json: enhancedResponse }];"
},
"typeVersion": 2
},
{
"id": "e720959c-0c8a-40b9-b608-7b6c5835f6e7",
"name": "\ud83d\udce4 Webhook Response",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
864,
160
],
"parameters": {
"options": {},
"respondWith": "allIncomingData"
},
"typeVersion": 1
},
{
"id": "sticky-query-preprocessor",
"name": "Query Preprocessor Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1376,
-200
],
"parameters": {
"color": 3,
"width": 500,
"height": 400,
"content": "# \ud83d\udd0d Query Preprocessor\n\n**Purpose:** Validates and preprocesses user input for optimal search performance.\n\n**Key Functions:**\n- Input validation (minimum 3 characters)\n- Query cleaning and normalization\n- Keyword extraction for search optimization\n- Search strategy determination based on scope\n- Session ID generation for tracking\n\n**Output:** Structured query object with metadata for downstream processing."
},
"typeVersion": 1
},
{
"id": "sticky-search-router",
"name": "Search Router Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1056,
-200
],
"parameters": {
"color": 4,
"width": 500,
"height": 400,
"content": "# \ud83d\udd04 Search Router\n\n**Purpose:** Routes queries to appropriate search sources based on scope selection.\n\n**Routing Logic:**\n- **Web General**: Google, Bing, DuckDuckGo\n- **Academic Papers**: Scholar, arXiv, PubMed\n- **News Articles**: News API, RSS feeds\n- **Technical Docs**: GitHub, Stack Overflow\n- **Company Internal**: Drive, Confluence, Notion\n- **Multi Source**: Combined approach\n\n**Benefits:** Optimized search results for specific use cases."
},
"typeVersion": 1
},
{
"id": "sticky-context-builder",
"name": "Context Builder Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
-200
],
"parameters": {
"color": 5,
"width": 500,
"height": 450,
"content": "# \ud83e\udde0 Context Builder\n\n**Purpose:** Prepares comprehensive context for GPT-4 Turbo processing.\n\n**Context Elements:**\n- Query information and metadata\n- Retrieved sources with relevance scores\n- Source quality indicators\n- Processing metadata and session tracking\n\n**AI Instructions:**\n- Language-specific prompts\n- Response style customization\n- Source citation requirements\n- Quality and accuracy guidelines\n\n**Output:** Structured messages for LLM processing."
},
"typeVersion": 1
},
{
"id": "sticky-llm-processor",
"name": "LLM Processor Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
224,
-200
],
"parameters": {
"color": 6,
"width": 500,
"height": 400,
"content": "# \ud83e\udd16 Advanced LLM Processor\n\n**Model:** GPT-4 Turbo (gpt-4-turbo-preview)\n\n**Configuration:**\n- Max Tokens: 2048\n- Temperature: 0.3 (balanced creativity/accuracy)\n- Top P: 0.9\n\n**Processing:**\n- Receives structured context from Context Builder\n- Generates source-grounded responses\n- Maintains citation integrity\n- Follows style and language preferences\n\n**Output:** Raw AI-generated response with usage statistics."
},
"typeVersion": 1
},
{
"id": "sticky-response-enhancer",
"name": "Response Enhancer Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
544,
-200
],
"parameters": {
"color": 7,
"width": 500,
"height": 450,
"content": "# \u2728 Response Enhancer\n\n**Purpose:** Formats and enhances AI responses for multiple output formats.\n\n**Format Options:**\n- **Markdown**: Default structured format\n- **HTML**: Web-ready with styling\n- **JSON**: API-friendly structured data\n- **PDF**: Document generation (optional)\n\n**Enhancements:**\n- Quality indicators and metrics\n- Source breakdown and citations\n- Usage statistics and performance data\n- Session tracking and metadata\n\n**Output:** Formatted response ready for delivery."
},
"typeVersion": 1
},
{
"id": "sticky-webhook-response",
"name": "Webhook Response Info",
"type": "n8n-nodes-base.stickyNote",
"position": [
864,
-200
],
"parameters": {
"color": 2,
"width": 500,
"height": 400,
"content": "# \ud83d\udce4 Webhook Response\n\n**Purpose:** Delivers formatted responses back to the user interface.\n\n**Response Types:**\n- Complete response data\n- Formatted output (MD/HTML/JSON)\n- Metadata and quality metrics\n- Session information\n\n**Integration:**\n- Webhook endpoint for real-time responses\n- Email notifications (optional)\n- Slack integration (optional)\n- Analytics tracking\n\n**Benefits:** Immediate feedback and comprehensive data delivery."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "552ac041-e7ae-4695-9b21-47675446cff0",
"connections": {
"\ud83d\udd04 Search Router": {
"main": [
[
{
"node": "\ud83c\udf93 Academic Papers Search",
"type": "main",
"index": 0
},
{
"node": "\ud83d\udcf0 News Search API",
"type": "main",
"index": 0
}
]
]
},
"\ud83d\udcca Data Aggregator": {
"main": [
[
{
"node": "\ud83e\udde0 Context Builder",
"type": "main",
"index": 0
}
]
]
},
"\ud83d\udcf0 News Search API": {
"main": [
[
{
"node": "\ud83d\udcca Data Aggregator",
"type": "main",
"index": 0
}
]
]
},
"\ud83e\udde0 Context Builder": {
"main": [
[
{
"node": "\ud83e\udd16 Advanced LLM Processor",
"type": "main",
"index": 0
}
]
]
},
"\u2728 Response Enhancer": {
"main": [
[
{
"node": "\ud83d\udce4 Webhook Response",
"type": "main",
"index": 0
}
]
]
},
"\ud83d\ude80 Advanced RAG Form": {
"main": [
[
{
"node": "\ud83d\udd0d Query Preprocessor",
"type": "main",
"index": 0
}
]
]
},
"\ud83d\udd0d Query Preprocessor": {
"main": [
[
{
"node": "\ud83d\udd04 Search Router",
"type": "main",
"index": 0
}
]
]
},
"\ud83c\udf93 Academic Papers Search": {
"main": [
[
{
"node": "\ud83d\udcca Data Aggregator",
"type": "main",
"index": 0
}
]
]
},
"\ud83e\udd16 Advanced LLM Processor": {
"main": [
[
{
"node": "\u2728 Response Enhancer",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow provides an enterprise-grade RAG (Retrieval-Augmented Generation) system that intelligently searches multiple sources and generates AI-powered responses using GPT-4 Turbo.
Source: https://n8n.io/workflows/6691/ — 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.
This workflow provides an enterprise-grade RAG (Retrieval-Augmented Generation) system that intelligently searches multiple sources and generates AI-powered responses using GPT-4 Turbo.
Form Trigger, Google Drive Search, Web Search +2
Analyze incoming support requests, classify intent and priority with AI, create Jira tickets, assign the correct team, send Slack notifications, and track SLA deadlines. Supports Gmail, WhatsApp, form
Gmail Trigger, HTTP Request, Form Trigger +4
Note: Now includes an Apify alternative for Rapid API (Some users can't create new accounts on Rapid API, so I have added an alternative for you. But immediately you are able to get access to Rapid AP
Form Trigger, Google Sheets Trigger, OpenAI +2
This system automates LinkedIn lead generation and enrichment in six clear stages: Lead Collection (via Apollo.io) Automatically pulls leads based on keywords, roles, or industries using Apollo’s API.
Form Trigger, OpenAI, Google Sheets Trigger +2
Automated Lead Generation. Uses formTrigger, openAi, googleSheetsTrigger, googleSheets. Event-driven trigger; 55 nodes.
Form Trigger, OpenAI, Google Sheets Trigger +2