This workflow follows the Agent → Chat Trigger 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 →
{
"name": "RAG Agent Integration Hub mit Knowledge Management",
"nodes": [
{
"parameters": {},
"id": "enhanced-postgres-chat-memory",
"name": "Enhanced Postgres Chat Memory",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"typeVersion": 1.1,
"position": [
1040,
560
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "llama3.1:latest",
"options": {}
},
"id": "enhanced-ollama-chat-model",
"name": "Enhanced Ollama Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"typeVersion": 1,
"position": [
920,
560
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": "llama3.1:latest",
"options": {}
},
"id": "enhanced-ollama-model",
"name": "Enhanced Ollama Model",
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"typeVersion": 1,
"position": [
1960,
500
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "knowledge_base_search",
"description": "Search through the integrated knowledge base including AppFlowy pages, Affine documents, Google Drive files, and vector database content. Use this for semantic similarity search across all platforms.",
"topK": 5
},
"id": "knowledge-base-vector-tool",
"name": "Knowledge Base Vector Tool",
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
1740,
200
]
},
{
"parameters": {
"name": "appflowy_direct_query",
"description": "Query AppFlowy databases and pages directly using semantic search or direct database queries. Best for getting latest AppFlowy content and specific database information.",
"workflowId": {
"__rl": true,
"value": "AppFlowyQueryTool",
"mode": "list",
"cachedResultName": "AppFlowy Direct Query Tool"
}
},
"id": "appflowy-query-tool",
"name": "AppFlowy Query Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
280
]
},
{
"parameters": {
"name": "affine_direct_query",
"description": "Query Affine documents, whiteboards, and workspaces directly using GraphQL API and semantic search. Best for getting latest Affine content and collaborative workspace information.",
"workflowId": {
"__rl": true,
"value": "AffineQueryTool",
"mode": "list",
"cachedResultName": "Affine Direct Query Tool"
}
},
"id": "affine-query-tool",
"name": "Affine Query Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
360
]
},
{
"parameters": {
"name": "cross_platform_search",
"description": "Comprehensive search across all knowledge management platforms (AppFlowy, Affine, Google Drive, Vector DB) with intelligent deduplication and result ranking. Use for broad searches across multiple systems.",
"workflowId": {
"__rl": true,
"value": "CrossPlatformSearch",
"mode": "list",
"cachedResultName": "Cross-Platform Knowledge Search Tool"
}
},
"id": "cross-platform-search-tool",
"name": "Cross-Platform Search Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
440
]
},
{
"parameters": {
"name": "knowledge_orchestrator",
"description": "Trigger knowledge management system orchestration, health monitoring, and sync operations. Use when you need to check system health, trigger syncs, or perform maintenance operations.",
"workflowId": {
"__rl": true,
"value": "KnowledgeOrchestrator",
"mode": "list",
"cachedResultName": "Central Knowledge Management Orchestrator"
}
},
"id": "orchestrator-tool",
"name": "Orchestrator Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
520
]
},
{
"parameters": {
"name": "conflict_resolution",
"description": "Detect and resolve conflicts between synchronized content across different platforms. Use when there are data inconsistencies or synchronization issues.",
"workflowId": {
"__rl": true,
"value": "ConflictResolution",
"mode": "list",
"cachedResultName": "Knowledge Management Conflict Resolution"
}
},
"id": "conflict-resolution-tool",
"name": "Conflict Resolution Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
600
]
},
{
"parameters": {
"name": "backup_system",
"description": "Manage backup and recovery operations for the knowledge management system. Use for creating backups, checking backup status, or performing recovery operations.",
"workflowId": {
"__rl": true,
"value": "BackupRecovery",
"mode": "list",
"cachedResultName": "Automated Knowledge Management Backup & Recovery"
}
},
"id": "backup-recovery-tool",
"name": "Backup Recovery Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
680
]
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"id": "enhanced-embeddings-ollama",
"name": "Enhanced Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
1840,
800
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"id": "enhanced-chat-trigger",
"name": "Enhanced Chat Trigger",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
620,
340
]
},
{
"parameters": {
"qdrantCollection": {
"__rl": true,
"value": "knowledge_base",
"mode": "list",
"cachedResultName": "knowledge_base"
},
"options": {}
},
"id": "enhanced-qdrant-vector-store",
"name": "Enhanced Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1,
"position": [
1560,
680
],
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"id": "enhanced-respond-to-webhook",
"name": "Enhanced Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1340,
340
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "rag-agent-hub",
"responseMode": "responseNode",
"options": {}
},
"id": "enhanced-webhook",
"name": "Enhanced Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
620,
520
]
},
{
"parameters": {
"promptType": "define",
"text": "You are an advanced AI assistant with comprehensive access to a sophisticated knowledge management ecosystem. You have access to multiple specialized tools and can help users with:\n\n## Available Knowledge Sources:\n1. **AppFlowy**: Project management, notes, databases, and wikis\n2. **Affine**: Collaborative documents, whiteboards, and workspaces\n3. **Google Drive**: Files, documents, and shared resources\n4. **Vector Database**: Semantic search across all ingested content\n\n## Specialized Tools at Your Disposal:\n\n**Search & Query Tools:**\n- `knowledge_base_search`: Semantic similarity search across all platforms\n- `appflowy_direct_query`: Direct AppFlowy database and page queries\n- `affine_direct_query`: Direct Affine workspace and document queries\n- `cross_platform_search`: Comprehensive multi-platform search with deduplication\n\n**System Management Tools:**\n- `knowledge_orchestrator`: System health monitoring and sync operations\n- `conflict_resolution`: Detect and resolve data conflicts between platforms\n- `backup_system`: Backup and recovery management\n\n## How to Help Users:\n\n**For Information Requests:**\n1. Determine the best search strategy based on the user's needs\n2. Use appropriate tools to gather relevant information\n3. Provide comprehensive answers with source attribution\n4. Suggest related information when helpful\n\n**For System Operations:**\n1. Use orchestrator tool for health checks and sync operations\n2. Use conflict resolution when data inconsistencies are reported\n3. Use backup tools for data protection needs\n\n**Response Guidelines:**\n- Always cite your sources (\"According to AppFlowy project database...\", \"From Affine workspace...\", etc.)\n- Provide actionable insights and next steps when appropriate\n- Use multiple tools when necessary for comprehensive answers\n- Explain which tools you're using and why\n- If information conflicts exist, note the discrepancies and suggest resolution\n\n**Example Tool Usage:**\n- For project status: Use `appflowy_direct_query` for structured data\n- For document searches: Use `cross_platform_search` for comprehensive results\n- For system issues: Use `knowledge_orchestrator` for diagnostics\n- For broad topics: Combine `knowledge_base_search` with specific platform queries\n\nAlways be helpful, accurate, and transparent about your information sources and limitations.",
"options": {
"systemMessage": "You are an advanced knowledge management AI assistant with access to comprehensive tools for searching, managing, and maintaining a multi-platform knowledge ecosystem."
}
},
"id": "enhanced-ai-agent",
"name": "Enhanced AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.6,
"position": [
1000,
340
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "enhanced-chat-input",
"name": "chatInput",
"value": "={{ $json?.chatInput || $json.body?.chatInput || $json.body?.message || $json.message || $json.body?.query }}",
"type": "string"
},
{
"id": "enhanced-session-id",
"name": "sessionId",
"value": "={{ $json?.sessionId || $json.body?.sessionId || 'rag-hub-' + $moment().format('YYYY-MM-DD-HH-mm') }}",
"type": "string"
},
{
"id": "user-context",
"name": "userContext",
"value": "={{ $json?.userContext || $json.body?.userContext || {} }}",
"type": "object"
},
{
"id": "search-preferences",
"name": "searchPreferences",
"value": "={{ $json?.searchPreferences || $json.body?.searchPreferences || { preferredSources: ['vector_db', 'appflowy', 'affine'], searchDepth: 'comprehensive', enableCrossPlatform: true, includeMetadata: true } }}",
"type": "object"
},
{
"id": "operation-mode",
"name": "operationMode",
"value": "={{ $json?.operationMode || $json.body?.operationMode || 'standard' }}",
"type": "string"
},
{
"id": "enable-system-tools",
"name": "enableSystemTools",
"value": "={{ $json?.enableSystemTools || $json.body?.enableSystemTools || true }}",
"type": "boolean"
}
]
},
"options": {}
},
"id": "enhanced-edit-fields",
"name": "Enhanced Edit Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
820,
340
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "query-analysis",
"name": "queryAnalysis",
"value": "={{ {\n queryType: (() => {\n const input = $json.chatInput.toLowerCase();\n if (input.includes('appflowy') || input.includes('project') || input.includes('task')) return 'appflowy_focused';\n if (input.includes('affine') || input.includes('whiteboard') || input.includes('collaborate')) return 'affine_focused';\n if (input.includes('system') || input.includes('health') || input.includes('sync')) return 'system_management';\n if (input.includes('backup') || input.includes('restore') || input.includes('recovery')) return 'backup_management';\n if (input.includes('conflict') || input.includes('error') || input.includes('inconsistent')) return 'conflict_resolution';\n return 'general_knowledge';\n })(),\n searchKeywords: $json.chatInput.split(' ').filter(word => word.length > 3 && !['what', 'when', 'where', 'how', 'why', 'which', 'this', 'that', 'with', 'from', 'they', 'them', 'their', 'there', 'then', 'about'].includes(word.toLowerCase())),\n requiresRealtime: $json.chatInput.toLowerCase().includes('latest') || $json.chatInput.toLowerCase().includes('current') || $json.chatInput.toLowerCase().includes('now') || $json.chatInput.toLowerCase().includes('today'),\n complexity: $json.chatInput.split(' ').length > 10 ? 'high' : ($json.chatInput.split(' ').length > 5 ? 'medium' : 'low'),\n timestamp: $now\n} }}",
"type": "object"
}
]
},
"options": {}
},
"id": "analyze-query-intent",
"name": "Analyze Query Intent",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
620,
680
]
},
{
"parameters": {
"operation": "insert",
"table": {
"__rl": true,
"value": "enhanced_chat_sessions",
"mode": "list"
},
"data": {
"insert": [
{
"column": "session_id",
"value": "={{ $('Enhanced Edit Fields').item.json.sessionId }}"
},
{
"column": "user_input",
"value": "={{ $('Enhanced Edit Fields').item.json.chatInput }}"
},
{
"column": "user_context",
"value": "={{ $('Enhanced Edit Fields').item.json.userContext }}"
},
{
"column": "search_preferences",
"value": "={{ $('Enhanced Edit Fields').item.json.searchPreferences }}"
},
{
"column": "query_analysis",
"value": "={{ $('Analyze Query Intent').item.json.queryAnalysis }}"
},
{
"column": "operation_mode",
"value": "={{ $('Enhanced Edit Fields').item.json.operationMode }}"
},
{
"column": "timestamp",
"value": "={{ $now }}"
},
{
"column": "response",
"value": "={{ $('Enhanced AI Agent').item.json.output }}"
},
{
"column": "tools_used",
"value": "{{ [] }}"
},
{
"column": "processing_time_ms",
"value": "={{ $now - $('Analyze Query Intent').item.json.queryAnalysis.timestamp }}"
}
]
},
"options": {}
},
"id": "log-enhanced-chat-session",
"name": "Log Enhanced Chat Session",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1200,
520
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "system-management-query",
"leftValue": "={{ $json.queryAnalysis.queryType }}",
"rightValue": "system_management",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "check-system-management-query",
"name": "Check System Management Query",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
900,
680
]
},
{
"parameters": {
"url": "https://n8n.{{ $vars.domain_name }}/webhook/knowledge-orchestrator",
"options": {
"timeout": 30000
},
"sendBody": true,
"contentType": "json",
"body": {
"mode": "health_check",
"enableAnalytics": true,
"timestamp": "={{ $now }}"
}
},
"id": "trigger-system-health-check",
"name": "Trigger System Health Check",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1150,
600
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "system-status-summary",
"name": "systemStatusSummary",
"value": "={{ {\n healthCheckTriggered: true,\n timestamp: $now,\n orchestrationResponse: $json || 'System health check initiated',\n queryType: $('Analyze Query Intent').item.json.queryAnalysis.queryType\n} }}",
"type": "object"
}
]
},
"options": {}
},
"id": "process-system-status",
"name": "Process System Status",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1400,
600
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "google-drive-integration",
"responseMode": "responseNode",
"options": {}
},
"id": "google-drive-integration-webhook",
"name": "Google Drive Integration Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
800
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "drive-integration-request",
"name": "integrationRequest",
"value": "={{ {\n action: $json.body.action || 'sync',\n fileId: $json.body.fileId,\n folderId: $json.body.folderId,\n triggerFullSync: $json.body.triggerFullSync || false,\n timestamp: $now\n} }}",
"type": "object"
}
]
},
"options": {}
},
"id": "process-drive-integration",
"name": "Process Drive Integration",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
450,
800
]
},
{
"parameters": {
"url": "https://n8n.{{ $vars.domain_name }}/webhook/google-drive-webhook-sync",
"options": {
"timeout": 60000
},
"sendBody": true,
"contentType": "json",
"body": {
"fileId": "={{ $json.integrationRequest.fileId }}",
"action": "={{ $json.integrationRequest.action }}"
}
},
"id": "trigger-google-drive-sync",
"name": "Trigger Google Drive Sync",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
700,
800
]
},
{
"parameters": {
"options": {}
},
"id": "respond-to-drive-integration",
"name": "Respond to Drive Integration",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
950,
800
]
},
{
"parameters": {
"content": "## RAG Agent Integration Hub mit Knowledge Management\n\n**Zweck:** Erweiterte Integration des urspr\u00fcnglichen Local RAG AI Agent mit allen neuen Knowledge Management Workflows und Tools.\n\n## Erweiterte Funktionalit\u00e4ten\n\n**Urspr\u00fcngliche RAG-Funktionen (erweitert):**\n- Postgres Chat Memory f\u00fcr Konversationshistorie\n- Ollama LLM Integration (llama3.1:latest)\n- Vector Store Integration mit Qdrant\n- Google Drive Integration f\u00fcr Dokumente\n\n**Neue Tool-Integration:**\n1. **AppFlowy Direct Query**: Direkte Abfragen von AppFlowy Datenbanken\n2. **Affine Direct Query**: GraphQL-basierte Affine Workspace-Abfragen\n3. **Cross-Platform Search**: Plattform\u00fcbergreifende intelligente Suche\n4. **Knowledge Orchestrator**: System-Gesundheit und Sync-Operationen\n5. **Conflict Resolution**: Automatische Konfliktl\u00f6sung zwischen Plattformen\n6. **Backup & Recovery**: Backup-Management und Wiederherstellung\n\n## Intelligente Query-Analyse\n\n**Query-Typen:**\n- `appflowy_focused`: AppFlowy-spezifische Anfragen\n- `affine_focused`: Affine-spezifische Anfragen\n- `system_management`: System-Gesundheit und Wartung\n- `backup_management`: Backup und Recovery\n- `conflict_resolution`: Konfliktl\u00f6sung\n- `general_knowledge`: Allgemeine Wissensanfragen\n\n**Adaptive Tool-Auswahl:**\n- Automatische Bestimmung der besten Such-Strategie\n- Kontextbasierte Tool-Auswahl\n- Multi-Tool-Koordination f\u00fcr komplexe Anfragen\n\n## Enhanced Features\n\n**Session Management:**\n- Erweiterte Chat-Session-Protokollierung\n- User-Kontext und Pr\u00e4ferenzen\n- Query-Analyse und Performance-Tracking\n\n**System Integration:**\n- Automatische System-Gesundheitschecks\n- Google Drive Integration Webhook\n- Real-time Sync-Trigger\n\n**Response Enhancement:**\n- Source Attribution f\u00fcr alle Antworten\n- Multi-Platform-Kontext\n- Conflict Detection und Resolution\n\n## API Endpoints\n\n**Haupt-Chat-Interface:**\n- Chat-Trigger: Interaktives Chat-Interface\n- POST /webhook/rag-agent-hub: API-basierte Anfragen\n\n**Google Drive Integration:**\n- POST /webhook/google-drive-integration: Drive-Sync-Trigger\n\n**Parameter:**\n- `chatInput/message/query`: Benutzeranfrage\n- `sessionId`: Session-Identifikation\n- `searchPreferences`: Such-Pr\u00e4ferenzen\n- `operationMode`: Betriebsmodus (standard, system, maintenance)\n- `enableSystemTools`: System-Tools aktivieren\n\n## Integration mit Original RAG Agent\n\n**Kompatibilit\u00e4t:**\n- Beh\u00e4lt alle urspr\u00fcnglichen Google Drive Trigger\n- Erweitert Vector Store Funktionalit\u00e4t\n- Verbessert Chat Memory Management\n- Integriert alle neuen Knowledge Management Tools\n\n**Migration:**\n- Nahtlose Erweiterung des bestehenden Workflows\n- R\u00fcckw\u00e4rtskompatibilit\u00e4t mit urspr\u00fcnglichen Webhooks\n- Erweiterte Tool-Suite ohne Breaking Changes",
"height": 900,
"width": 1000,
"color": 6
},
"id": "rag-hub-documentation",
"name": "RAG Hub Documentation",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2200,
100
]
}
],
"connections": {
"Enhanced Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Enhanced Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Enhanced Ollama Model": {
"ai_languageModel": [
[
{
"node": "Knowledge Base Vector Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "AppFlowy Query Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Affine Query Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Cross-Platform Search Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Orchestrator Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Conflict Resolution Tool",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Backup Recovery Tool",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Enhanced Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Enhanced Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Enhanced Chat Trigger": {
"main": [
[
{
"node": "Enhanced Edit Fields",
"type": "main",
"index": 0
},
{
"node": "Analyze Query Intent",
"type": "main",
"index": 0
}
]
]
},
"Enhanced Qdrant Vector Store": {
"ai_vectorStore": [
[
{
"node": "Knowledge Base Vector Tool",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Enhanced Webhook": {
"main": [
[
{
"node": "Enhanced Edit Fields",
"type": "main",
"index": 0
},
{
"node": "Analyze Query Intent",
"type": "main",
"index": 0
}
]
]
},
"Enhanced AI Agent": {
"main": [
[
{
"node": "Enhanced Respond to Webhook",
"type": "main",
"index": 0
},
{
"node": "Log Enhanced Chat Session",
"type": "main",
"index": 0
}
]
]
},
"Enhanced Edit Fields": {
"main": [
[
{
"node": "Enhanced AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Analyze Query Intent": {
"main": [
[
{
"node": "Check System Management Query",
"type": "main",
"index": 0
}
]
]
},
"Check System Management Query": {
"main": [
[
{
"node": "Trigger System Health Check",
"type": "main",
"index": 0
}
]
]
},
"Trigger System Health Check": {
"main": [
[
{
"node": "Process System Status",
"type": "main",
"index": 0
}
]
]
},
"Knowledge Base Vector Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"AppFlowy Query Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 1
}
]
]
},
"Affine Query Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 2
}
]
]
},
"Cross-Platform Search Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 3
}
]
]
},
"Orchestrator Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 4
}
]
]
},
"Conflict Resolution Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 5
}
]
]
},
"Backup Recovery Tool": {
"ai_tool": [
[
{
"node": "Enhanced AI Agent",
"type": "ai_tool",
"index": 6
}
]
]
},
"Google Drive Integration Webhook": {
"main": [
[
{
"node": "Process Drive Integration",
"type": "main",
"index": 0
}
]
]
},
"Process Drive Integration": {
"main": [
[
{
"node": "Trigger Google Drive Sync",
"type": "main",
"index": 0
}
]
]
},
"Trigger Google Drive Sync": {
"main": [
[
{
"node": "Respond to Drive Integration",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "rag-hub-integration-v1",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "RAGAgentIntegrationHub",
"tags": [
"rag-agent",
"integration",
"knowledge-management",
"enhanced",
"hub"
]
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
ollamaApipostgresqdrantApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
RAG Agent Integration Hub mit Knowledge Management. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Chat trigger; 27 nodes.
Source: https://github.com/161sam/n8n-installer/blob/main/modularium/ai-workspace/RAG-Agent-Integration-Hub.json — 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 acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowle
Chat Trigger, Memory Postgres Chat, Tool Workflow +20
WooCommerce AI Chatbot Workflow for Post-Sales Support. Uses chatTrigger, memoryBufferWindow, wooCommerceTool, toolCalculator. Chat trigger; 31 nodes.
Chat Trigger, Memory Buffer Window, Woo Commerce Tool +13
This WooCommerce-integrated chatbot is designed to transform post-sales customer support by combining automation and artificial intelligence to deliver fast, secure, and personalized assistance.
Chat Trigger, Memory Buffer Window, Woo Commerce Tool +13
This workflow transforms your n8n instance into a fully automated AI sales assistant for WooCommerce stores. It detects customer intent from chat, searches products, answers FAQs, generates Stripe pay
Chat Trigger, Memory Buffer Window, Information Extractor +13
V2 Supabase RAG AI Agent. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Chat trigger; 23 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +10