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": "Local RAG AI Agent with Knowledge Management",
"nodes": [
{
"parameters": {},
"id": "local-rag-ai-agent-postgres-chat-memory",
"name": "Local RAG AI Agent 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": "local-rag-ai-agent-ollama-chat-model",
"name": "Local RAG AI Agent 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": "local-rag-ai-agent-ollama-model",
"name": "Local RAG AI Agent Ollama Model",
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"typeVersion": 1,
"position": [
1960,
500
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"name": "knowledge_base",
"description": "Search through the integrated knowledge base including AppFlowy pages, Affine documents, Google Drive files, and other synced content.",
"topK": 5
},
"id": "knowledge-base-vector-tool",
"name": "Knowledge Base Vector Tool",
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"typeVersion": 1,
"position": [
1740,
340
]
},
{
"parameters": {
"name": "appflowy_query",
"description": "Query AppFlowy databases and pages directly. Use this to get the latest information from AppFlowy workspaces."
},
"id": "appflowy-query-tool",
"name": "AppFlowy Query Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
180
]
},
{
"parameters": {
"name": "affine_query",
"description": "Query Affine documents and workspaces directly. Use this to get the latest information from Affine collaborative workspaces."
},
"id": "affine-query-tool",
"name": "Affine Query Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
240
]
},
{
"parameters": {
"name": "cross_platform_search",
"description": "Search across all knowledge management platforms (AppFlowy, Affine, Google Drive) for specific topics or keywords."
},
"id": "cross-platform-search-tool",
"name": "Cross-Platform Search Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"typeVersion": 1.1,
"position": [
1740,
300
]
},
{
"parameters": {
"model": "nomic-embed-text:latest"
},
"id": "local-rag-ai-agent-embeddings-ollama",
"name": "Local RAG AI Agent Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"typeVersion": 1,
"position": [
1840,
600
],
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"id": "local-rag-ai-agent-chat-trigger",
"name": "Local RAG AI Agent 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": "local-rag-ai-agent-qdrant-vector-store",
"name": "Local RAG AI Agent Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"typeVersion": 1,
"position": [
1560,
480
],
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"options": {}
},
"id": "local-rag-ai-agent-respond-to-webhook",
"name": "Local RAG AI Agent Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1340,
340
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "local-rag-ai-agent-rag-agent",
"responseMode": "responseNode",
"options": {}
},
"id": "local-rag-ai-agent-webhook",
"name": "Local RAG AI Agent Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
620,
520
]
},
{
"parameters": {
"promptType": "define",
"text": "You are an Local RAG AI Agent AI assistant with access to a comprehensive knowledge management system. You can access information from:\n\n1. **AppFlowy**: Project management, notes, databases, and wikis\n2. **Affine**: Collaborative documents, whiteboards, and workspaces \n3. **Google Drive**: Files, documents, and meeting notes\n4. **Vector Database**: Semantic search across all integrated content\n\nWhen answering questions:\n- Use the most relevant and up-to-date information from all available sources\n- Cite your sources when providing information (e.g., \"According to the AppFlowy project database...\")\n- If information is available in multiple sources, provide a comprehensive view\n- Suggest relevant actions or next steps when appropriate\n- If you need more specific information, use the appropriate query tools\n\nAlways be helpful, accurate, and provide context about where information comes from.",
"options": {
"systemMessage": "You are an Local RAG AI Agent knowledge management AI assistant with access to AppFlowy, Affine, Google Drive, and a comprehensive vector database. Always provide helpful, accurate responses with proper source attribution."
}
},
"id": "local-rag-ai-agent-ai-agent",
"name": "Local RAG AI Agent AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.6,
"position": [
1000,
340
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "local-rag-ai-agent-chat-input",
"name": "chatInput",
"value": "={{ $json?.chatInput || $json.body?.chatInput || $json.body?.message || $json.message }}",
"type": "string"
},
{
"id": "local-rag-ai-agent-session-id",
"name": "sessionId",
"value": "={{ $json?.sessionId || $json.body?.sessionId || 'default-session' }}",
"type": "string"
},
{
"id": "knowledge-context",
"name": "knowledgeContext",
"value": "={{ $json?.knowledge_context || $json.body?.knowledge_context || null }}",
"type": "object"
},
{
"id": "user-preferences",
"name": "userPreferences",
"value": "={{ { preferredSources: ['appflowy', 'affine', 'google_drive'], searchDepth: 'comprehensive', includeMetadata: true } }}",
"type": "object"
}
]
},
"options": {}
},
"id": "local-rag-ai-agent-edit-fields",
"name": "Local RAG AI Agent Edit Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
820,
340
]
},
{
"parameters": {
"operation": "insert",
"table": {
"__rl": true,
"value": "chat_sessions",
"mode": "list"
},
"data": {
"insert": [
{
"column": "session_id",
"value": "={{ $('Local RAG AI Agent Edit Fields').item.json.sessionId }}"
},
{
"column": "user_input",
"value": "={{ $('Local RAG AI Agent Edit Fields').item.json.chatInput }}"
},
{
"column": "knowledge_context",
"value": "={{ $('Local RAG AI Agent Edit Fields').item.json.knowledgeContext }}"
},
{
"column": "timestamp",
"value": "={{ $now }}"
},
{
"column": "response",
"value": "={{ $('Local RAG AI Agent AI Agent').item.json.output }}"
}
]
},
"options": {}
},
"id": "log-chat-session",
"name": "Log Chat Session",
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.5,
"position": [
1200,
520
],
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "## Local RAG AI Agent RAG AI Agent with Knowledge Management\n\n**Purpose:** Advanced AI assistant with integrated access to AppFlowy, Affine, Google Drive, and vector database.\n\n**Key Features:**\n- Semantic search across all knowledge sources\n- Direct query tools for AppFlowy and Affine\n- Cross-platform content correlation\n- Source attribution and metadata\n- Local RAG AI Agent context awareness\n- Session logging and analytics\n\n**Tools Available:**\n1. Knowledge Base Vector Search\n2. AppFlowy Direct Query\n3. Affine Direct Query \n4. Cross-Platform Search\n5. Google Drive Integration\n\n**Usage:**\n- Chat interface with natural language queries\n- Webhook API for integration with other systems\n- Supports complex multi-source research queries",
"height": 600,
"width": 700,
"color": 6
},
"id": "local-rag-ai-agent-workflow-documentation",
"name": "Local RAG AI Agent Workflow Documentation",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
200,
100
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "query-classification",
"name": "queryType",
"value": "={{ $json.chatInput.toLowerCase().includes('appflowy') ? 'appflowy' : $json.chatInput.toLowerCase().includes('affine') ? 'affine' : $json.chatInput.toLowerCase().includes('document') || $json.chatInput.toLowerCase().includes('file') ? 'document' : 'general' }}",
"type": "string"
},
{
"id": "search-keywords",
"name": "searchKeywords",
"value": "={{ $json.chatInput.split(' ').filter(word => word.length > 3 && !['what', 'when', 'where', 'how', 'why', 'which', 'this', 'that', 'with', 'from', 'they', 'them', 'their', 'there', 'then'].includes(word.toLowerCase())) }}",
"type": "array"
},
{
"id": "requires-realtime",
"name": "requiresRealtime",
"value": "={{ $json.chatInput.toLowerCase().includes('latest') || $json.chatInput.toLowerCase().includes('current') || $json.chatInput.toLowerCase().includes('now') || $json.chatInput.toLowerCase().includes('today') }}",
"type": "boolean"
}
]
},
"options": {}
},
"id": "analyze-query-intent",
"name": "Analyze Query Intent",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
620,
680
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "knowledge-update-trigger",
"responseMode": "responseNode",
"options": {}
},
"id": "knowledge-update-webhook",
"name": "Knowledge Update Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
800
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "update-source",
"name": "source",
"value": "={{ $json.body.source }}",
"type": "string"
},
{
"id": "update-type",
"name": "updateType",
"value": "={{ $json.body.updateType }}",
"type": "string"
},
{
"id": "document-id-update",
"name": "documentId",
"value": "={{ $json.body.documentId }}",
"type": "string"
},
{
"id": "trigger-resync",
"name": "triggerResync",
"value": "={{ $json.body.triggerResync || false }}",
"type": "boolean"
}
]
},
"options": {}
},
"id": "process-knowledge-update",
"name": "Process Knowledge Update",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
450,
800
]
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "resync-condition",
"leftValue": "={{ $json.triggerResync }}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "check-resync-needed",
"name": "Check Resync Needed",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
700,
800
]
},
{
"parameters": {
"url": "https://n8n.{{ $vars.domain_name }}/webhook/trigger-knowledge-sync",
"options": {
"timeout": 60000
},
"sendBody": true,
"contentType": "json",
"body": {
"source": "={{ $json.source }}",
"documentId": "={{ $json.documentId }}",
"updateType": "={{ $json.updateType }}",
"timestamp": "={{ $now }}"
}
},
"id": "trigger-knowledge-resync",
"name": "Trigger Knowledge Resync",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
950,
700
]
},
{
"parameters": {
"options": {}
},
"id": "respond-to-knowledge-update",
"name": "Respond to Knowledge Update",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1200,
800
]
}
],
"connections": {
"Local RAG AI Agent Postgres Chat Memory": {
"ai_memory": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Local RAG AI Agent Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Local RAG AI Agent 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
}
]
]
},
"Local RAG AI Agent Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Local RAG AI Agent Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Local RAG AI Agent Chat Trigger": {
"main": [
[
{
"node": "Local RAG AI Agent Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Local RAG AI Agent Qdrant Vector Store": {
"ai_vectorStore": [
[
{
"node": "Knowledge Base Vector Tool",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Local RAG AI Agent Webhook": {
"main": [
[
{
"node": "Local RAG AI Agent Edit Fields",
"type": "main",
"index": 0
},
{
"node": "Analyze Query Intent",
"type": "main",
"index": 0
}
]
]
},
"Local RAG AI Agent AI Agent": {
"main": [
[
{
"node": "Local RAG AI Agent Respond to Webhook",
"type": "main",
"index": 0
},
{
"node": "Log Chat Session",
"type": "main",
"index": 0
}
]
]
},
"Local RAG AI Agent Edit Fields": {
"main": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Knowledge Base Vector Tool": {
"ai_tool": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"AppFlowy Query Tool": {
"ai_tool": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_tool",
"index": 1
}
]
]
},
"Affine Query Tool": {
"ai_tool": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_tool",
"index": 2
}
]
]
},
"Cross-Platform Search Tool": {
"ai_tool": [
[
{
"node": "Local RAG AI Agent AI Agent",
"type": "ai_tool",
"index": 3
}
]
]
},
"Knowledge Update Webhook": {
"main": [
[
{
"node": "Process Knowledge Update",
"type": "main",
"index": 0
}
]
]
},
"Process Knowledge Update": {
"main": [
[
{
"node": "Check Resync Needed",
"type": "main",
"index": 0
}
]
]
},
"Check Resync Needed": {
"main": [
[
{
"node": "Trigger Knowledge Resync",
"type": "main",
"index": 0
}
],
[
{
"node": "Respond to Knowledge Update",
"type": "main",
"index": 0
}
]
]
},
"Trigger Knowledge Resync": {
"main": [
[
{
"node": "Respond to Knowledge Update",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "local-rag-ai-agent-rag-v1",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "Local RAG AI AgentRAGAgent",
"tags": [
"ai-agent",
"rag",
"knowledge-management",
"Local RAG AI Agent",
"appflowy",
"affine"
]
}
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
Local RAG AI Agent with Knowledge Management. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Chat trigger; 22 nodes.
Source: https://github.com/161sam/n8n-installer/blob/main/modularium/ai-workspace/Local-RAG-AI-Agent.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
RAG Agent Integration Hub mit Knowledge Management. Uses memoryPostgresChat, lmChatOllama, lmOllama, toolVectorStore. Chat trigger; 27 nodes.
Memory Postgres Chat, Ollama Chat, Lm Ollama +8
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