基于文档的 AI 聊天机器人，带 RAG、OpenAI 和 Cohere 重排器
高级
这是一个Internal Wiki, AI RAG领域的自动化工作流，包含 18 个节点。主要使用 GoogleDrive, ManualTrigger, Agent, ExtractFromFile, ChatTrigger 等节点。 基于文档的 AI 聊天机器人，带 RAG、OpenAI 和 Cohere 重排器
前置要求
- •Google Drive API 凭证
- •OpenAI API Key
- •Supabase URL 和 API Key
使用的节点 (18)
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": "6052a1b29f061469e8139dae44556603650099c3365d7598798f132ae827fa1c"
},
"nodes": [
{
"id": "a8afd8c2-2bfd-49f3-9687-0d68c83db4ad",
"name": "聊天界面",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
80,
100
],
"webhookId": "de210796-2512-4c20-97eb-87b7f05298cb",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "00c21cda-1193-4cf5-9681-bf21ac2b269c",
"name": "RAG 智能体",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
300,
100
],
"parameters": {
"options": {
"systemMessage": "You are an intelligent assistant with access to a knowledge base. Always search for relevant information before answering questions. Be helpful, accurate, and cite your sources when providing information from the knowledge base."
}
},
"typeVersion": 2
},
{
"id": "c74d3fac-14ef-4809-b290-d0344db04c79",
"name": "AI 模型 (OpenAI)",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
180,
320
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4-mini"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "e8a473c1-4934-491b-8283-80d48982d604",
"name": "搜索嵌入向量",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
540,
460
],
"parameters": {
"options": {}
},
"typeVersion": 1.2
},
{
"id": "6fc17058-70f2-4bbe-a8b5-e35116f14853",
"name": "对话记忆",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
340,
320
],
"parameters": {
"contextWindowLength": 10
},
"typeVersion": 1.3
},
{
"id": "ba366390-61e3-4a25-8008-fb172145486a",
"name": "加载文档触发器",
"type": "n8n-nodes-base.manualTrigger",
"position": [
100,
760
],
"parameters": {},
"typeVersion": 1
},
{
"id": "f97d305b-3a96-445c-ace2-535c60055a4f",
"name": "从 Google Drive 下载 PDF",
"type": "n8n-nodes-base.googleDrive",
"position": [
320,
760
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "url",
"value": "{{GOOGLE_DRIVE_FILE_URL}}"
},
"options": {},
"operation": "download"
},
"typeVersion": 3
},
{
"id": "9eec6cb6-f445-4add-8de9-1464b61dfa7a",
"name": "文档嵌入向量",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
700,
960
],
"parameters": {
"options": {}
},
"typeVersion": 1.2
},
{
"id": "e64b2357-0238-45ca-87bd-10f8deddd6e4",
"name": "处理文档文本",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
840,
960
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "source",
"value": "={{ $node['Download PDF from Drive'].json.name }}"
},
{
"name": "type",
"value": "pdf"
}
]
}
},
"jsonData": "={{ $json.text }}",
"jsonMode": "expressionData"
},
"typeVersion": 1.1
},
{
"id": "8b0645f9-dbcb-4613-9126-9efa824615bc",
"name": "知识库搜索",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
540,
320
],
"parameters": {
"mode": "retrieve-as-tool",
"topK": 10,
"options": {
"queryName": "{{MATCH_FUNCTION_NAME}}"
},
"tableName": {
"__rl": true,
"mode": "id",
"value": "{{VECTOR_TABLE_NAME}}"
},
"useReranker": true,
"toolDescription": "Use this tool to search for information in the knowledge base. Always use this before answering questions to ensure accurate, up-to-date responses."
},
"credentials": {
"supabaseApi": {
"id": "PgMEWpeDY6PHLFXp",
"name": "Supabase Zenithon Suporte IA"
}
},
"typeVersion": 1.3
},
{
"id": "4cb8869a-de07-44f5-8f79-9b3c1207d21c",
"name": "存储到向量数据库",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
700,
760
],
"parameters": {
"mode": "insert",
"options": {
"queryName": "{{MATCH_FUNCTION_NAME}}"
},
"tableName": {
"__rl": true,
"mode": "id",
"value": "{{VECTOR_TABLE_NAME}}"
}
},
"typeVersion": 1.3
},
{
"id": "c8d8674d-ebe7-42fa-918e-ea9c5dc56b98",
"name": "提取 PDF 内容",
"type": "n8n-nodes-base.extractFromFile",
"position": [
500,
760
],
"parameters": {
"options": {
"maxPages": 500
},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "c5af8b70-bbda-4138-9598-dfd6c44a0eb5",
"name": "Cohere 重排序器",
"type": "@n8n/n8n-nodes-langchain.rerankerCohere",
"position": [
700,
460
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c3af22b6-830c-43a6-9a8f-0f38f3dec647",
"name": "注意：聊天触发器",
"type": "n8n-nodes-base.stickyNote",
"position": [
20,
-40
],
"parameters": {
"color": 5,
"width": 200,
"height": 120,
"content": "### 1️⃣ 聊天触发器"
},
"typeVersion": 1
},
{
"id": "c3655d77-d3ee-4c21-8166-da08b15175d3",
"name": "注意：RAG 代理",
"type": "n8n-nodes-base.stickyNote",
"position": [
300,
-40
],
"parameters": {
"color": 5,
"width": 200,
"height": 120,
"content": "### 2️⃣ RAG 代理"
},
"typeVersion": 1
},
{
"id": "ba9f02ea-6def-433a-9ccc-6f0ec1a1792b",
"name": "注意：知识搜索",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
180
],
"parameters": {
"color": 5,
"width": 200,
"height": 100,
"content": "### 3️⃣ 知识搜索"
},
"typeVersion": 1
},
{
"id": "ba558d29-fa87-4a2d-a63f-64a768bb2efb",
"name": "注意：重排序器",
"type": "n8n-nodes-base.stickyNote",
"position": [
820,
440
],
"parameters": {
"color": 5,
"width": 200,
"height": 100,
"content": "### 4️⃣ 重排序器"
},
"typeVersion": 1
},
{
"id": "0ff39f38-d67e-4517-8f5b-834c032383dd",
"name": "注意：配置",
"type": "n8n-nodes-base.stickyNote",
"position": [
880,
0
],
"parameters": {
"color": 4,
"width": 260,
"height": 180,
"content": "### 配置变量"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"Chat Interface": {
"main": [
[
{
"node": "RAG Agent",
"type": "main",
"index": 0
}
]
]
},
"Cohere Reranker": {
"ai_reranker": [
[
{
"node": "Knowledge Base Search",
"type": "ai_reranker",
"index": 0
}
]
]
},
"AI Model (OpenAI)": {
"ai_languageModel": [
[
{
"node": "RAG Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Search Embeddings": {
"ai_embedding": [
[
{
"node": "Knowledge Base Search",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Conversation Memory": {
"ai_memory": [
[
{
"node": "RAG Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Document Embeddings": {
"ai_embedding": [
[
{
"node": "Store in Vector Database",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract PDF Content": {
"main": [
[
{
"node": "Store in Vector Database",
"type": "main",
"index": 0
}
]
]
},
"Knowledge Base Search": {
"ai_tool": [
[
{
"node": "RAG Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Process Document Text": {
"ai_document": [
[
{
"node": "Store in Vector Database",
"type": "ai_document",
"index": 0
}
]
]
},
"Load Documents Trigger": {
"main": [
[
{
"node": "Download PDF from Drive",
"type": "main",
"index": 0
}
]
]
},
"Download PDF from Drive": {
"main": [
[
{
"node": "Extract PDF Content",
"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 - 内部知识库, 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 重排序
使用 Supabase、OpenAI 和 Cohere 重排序器从文档中回答问题
Code
Google Drive
Manual Trigger
+9
26 节点Luan Correia
内部知识库
构建集成Claude、RAG、Perplexity和Drive的全源知识助手
构建集成Claude、RAG、Perplexity和Drive的全源知识助手
Set
Switch
Google Drive
+21
38 节点Paul
内部知识库
AI知识库助手与OpenAI、Supabase及Google Drive文档同步
AI知识库助手与OpenAI、Supabase及Google Drive文档同步
Set
Limit
Switch
+16
49 节点Abdul Mir
内部知识库
基于 Webhook、Pinecone + OpenAI + n8n 的智能文档问答系统
基于OpenAI GPT、Pinecone向量数据库和Google Drive集成的文档问答系统
Webhook
Google Drive
Manual Trigger
+11
30 节点Mohan Gopal
内部知识库
文档 RAG 和聊天代理：Google Drive 到 Qdrant 与 Mistral OCR
文档 RAG 和聊天代理：Google Drive 到 Qdrant 与 Mistral OCR
If
Set
Code
+16
40 节点DIGITAL BIZ TECH
内部知识库
递归混合RAG 1
使用Google Drive、OpenAI和Gemini RAG进行递归分块的文档处理
Set
Code
Switch
+18
25 节点Mohsin Ali
内部知识库
