构建问答AI智能体
中级
这是一个Engineering, AI RAG领域的自动化工作流，包含 12 个节点。主要使用 FormTrigger, McpClientTool, McpTrigger, EmbeddingsOllama, VectorStoreQdrant 等节点。 使用Llama、RAG和Google搜索构建问答AI智能体
前置要求
- •Qdrant 服务器连接信息
使用的节点 (12)
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
{
"meta": {
"instanceId": "558d88703fb65b2d0e44613bc35916258b0f0bf983c5d4730c00c424b77ca36a",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "95fbf42b-4efb-4301-8e8f-34859156534c",
"name": "MCP 服务器触发器",
"type": "@n8n/n8n-nodes-langchain.mcpTrigger",
"position": [
0,
0
],
"webhookId": "8d7910ab-f0db-4042-9da9-f580647a8a8e",
"parameters": {
"path": "8d7910ab-f0db-4042-9da9-f580647a8a8e"
},
"typeVersion": 2
},
{
"id": "0d2f7b7c-a2e2-43ec-baf1-d0e507977bab",
"name": "Qdrant 向量存储",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
440,
140
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolDescription": "Use this tool to retrieve data from a database",
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "mcp_rag"
}
},
"credentials": {
"qdrantApi": {
"id": "sFfERYppMeBnFNeA",
"name": "Local QdrantApi database"
}
},
"typeVersion": 1.3
},
{
"id": "6c0a4301-66d6-40a6-b133-d809de367e0e",
"name": "嵌入 Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
620,
320
],
"parameters": {
"model": "mxbai-embed-large:latest"
},
"credentials": {
"ollamaApi": {
"id": "xHuYe0MDGOs9IpBW",
"name": "Local Ollama service"
}
},
"typeVersion": 1
},
{
"id": "a0c04dfe-aa62-4dae-b0e2-b7882c1c06fd",
"name": "MCP Client",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
-20,
280
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"id": "gtICJ1VBUVNpQahr",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "6b2e162e-3431-41e3-839e-5b4a206de768",
"name": "MCP 客户端 1",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
200,
280
],
"parameters": {
"toolName": "execute_tool",
"operation": "executeTool"
},
"credentials": {
"mcpClientApi": {
"id": "gtICJ1VBUVNpQahr",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "2989e6de-fe14-4215-ab7e-350b52faa011",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
-100
],
"parameters": {
"color": 5,
"width": 880,
"height": 620,
"content": "## MCP 服务器"
},
"typeVersion": 1
},
{
"id": "fb2c49d7-fa34-4ac9-b2e8-1d5dd9a73b3c",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
860,
-100
],
"parameters": {
"color": 4,
"width": 880,
"height": 620,
"content": "## RAG 摄取流水线"
},
"typeVersion": 1
},
{
"id": "34e2aafe-c627-4af8-a673-16526802fbd5",
"name": "表单提交时",
"type": "n8n-nodes-base.formTrigger",
"position": [
960,
40
],
"webhookId": "7d7ae610-42c0-4fbf-a286-df5c6b62a510",
"parameters": {
"options": {},
"formTitle": "Ingest PDF Files in semantic database",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "Upload a file",
"acceptFileTypes": ".pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "efb5839e-104c-4920-b932-34d9177a5c70",
"name": "Qdrant 向量存储1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
1180,
40
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "mcp_rag"
}
},
"credentials": {
"qdrantApi": {
"id": "sFfERYppMeBnFNeA",
"name": "Local QdrantApi database"
}
},
"typeVersion": 1.3
},
{
"id": "92f0f26c-5af6-4943-bdbf-45777267598d",
"name": "Embeddings Ollama1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
1100,
300
],
"parameters": {
"model": "mxbai-embed-large:latest"
},
"credentials": {
"ollamaApi": {
"id": "xHuYe0MDGOs9IpBW",
"name": "Local Ollama service"
}
},
"typeVersion": 1
},
{
"id": "950a0544-43c4-4423-982e-b04408e46a97",
"name": "默认数据加载器",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1400,
220
],
"parameters": {
"options": {},
"dataType": "binary",
"textSplittingMode": "custom"
},
"typeVersion": 1.1
},
{
"id": "7cd3a5f4-ffb1-4f93-9a7d-a40aea4aa64a",
"name": "递归字符文本分割器",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1300,
360
],
"parameters": {
"options": {},
"chunkSize": 400,
"chunkOverlap": 100
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"MCP Client": {
"ai_tool": [
[
{
"node": "MCP Server Trigger",
"type": "ai_tool",
"index": 0
}
]
]
},
"MCP Client1": {
"ai_tool": [
[
{
"node": "MCP Server Trigger",
"type": "ai_tool",
"index": 0
}
]
]
},
"Embeddings Ollama": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings Ollama1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"On form submission": {
"main": [
[
{
"node": "Qdrant Vector Store1",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_document",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"ai_tool": [
[
{
"node": "MCP Server Trigger",
"type": "ai_tool",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"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？
中级 - 工程, AI RAG 检索增强
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
RAG 流水线
基于检索增强生成(RAG)的本地聊天机器人
Form Trigger
Agent
Chat Trigger
+7
13 节点Thomas Janssen
工程
LLM模板
使用GPT-4o-mini和Qdrant向量数据库构建持久聊天记忆
Set
Agent
Chat Trigger
+8
25 节点Einar César Santos
工程
使用Gmail、GPT-4和向量知识库的自动化客户支持系统
使用Gmail、GPT-4和向量知识库的自动化客户支持系统
If
Set
Code
+15
32 节点Khair Ahammed
AI RAG 检索增强
自动化文档合规性验证
结合 AI 和向量数据库的自动化文档合规性验证
Code
Webhook
Http Request
+11
22 节点Thapani Sawaengsri
AI RAG 检索增强
使用Qdrant RAG和Ollama构建本地AI Kaggle竞赛助手
使用Qdrant RAG和Ollama构建本地AI Kaggle竞赛助手
Set
Merge
Switch
+16
23 节点JHH
工程
n8n本地测试
使用Llama3、Postgres、Qdrant和Google Drive创建私有文档问答系统
Set
Google Drive
Agent
+12
20 节点David Olusola
内部知识库
