PDF 转向量 RAG 系统：Mistral OCR、Weaviate 数据库和 MCP 服务器
中级
这是一个Document Extraction, Multimodal AI领域的自动化工作流，包含 13 个节点。主要使用 Set, MistralAi, FormTrigger, McpTrigger, RerankerCohere 等节点。 使用Mistral OCR和Weaviate数据库构建PDF搜索系统
前置要求
- •无特殊前置要求，导入即可使用
使用的节点 (13)
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
{
"id": "rV1w47cZn1rsk7MP",
"meta": {
"instanceId": "402614e91d3374d08756ba129f83d1678d5ada16d0573bfa1398e795ef5f7589",
"templateCredsSetupCompleted": true
},
"name": "PDF 转向量 RAG 系统：Mistral OCR、Weaviate 数据库和 MCP 服务器",
"tags": [],
"nodes": [
{
"id": "d9e90589-d6b6-4601-bac8-5009b765fa78",
"name": "Cohere 嵌入",
"type": "@n8n/n8n-nodes-langchain.embeddingsCohere",
"position": [
160,
336
],
"parameters": {
"modelName": "embed-multilingual-v3.0"
},
"typeVersion": 1
},
{
"id": "5e7c6668-64a4-4cc2-b519-ab75f07ecab5",
"name": "文档加载器",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
-144,
336
],
"parameters": {
"options": {},
"textSplittingMode": "custom"
},
"typeVersion": 1.1
},
{
"id": "b808993d-a6b9-497f-88b5-271c16abc185",
"name": "Cohere 重排序器",
"type": "@n8n/n8n-nodes-langchain.rerankerCohere",
"position": [
304,
336
],
"parameters": {},
"typeVersion": 1
},
{
"id": "117948ee-4be7-4869-b35b-d0c58a66fcd5",
"name": "MCP 知识服务器",
"type": "@n8n/n8n-nodes-langchain.mcpTrigger",
"position": [
192,
-80
],
"webhookId": "4f3bebe7-f088-4131-b3ad-c4e300f74517",
"parameters": {
"path": "c74c97f5-0197-45e3-b4dd-f3efbd4bab22",
"authentication": "headerAuth"
},
"typeVersion": 2
},
{
"id": "700afe32-2bcc-4f31-a680-cdce710861e2",
"name": "搜索知识库",
"type": "@n8n/n8n-nodes-langchain.vectorStoreWeaviate",
"position": [
256,
128
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"useReranker": true,
"toolDescription": "Use this tool to search and retrieve information from the knowledge base containing various documents and resources",
"weaviateCollection": {
"__rl": true,
"mode": "list",
"value": "KnowledgeDocuments",
"cachedResultName": "KnowledgeDocuments"
},
"includeDocumentMetadata": false
},
"typeVersion": 1.3
},
{
"id": "4075cf1b-e9f6-44cc-b827-29fa5eb1ee97",
"name": "上传说明",
"type": "n8n-nodes-base.stickyNote",
"position": [
-880,
-16
],
"parameters": {
"color": 5,
"width": 688,
"height": 304,
"content": "## 手动文档（PDF）上传部分"
},
"typeVersion": 1
},
{
"id": "bf763fa9-03f4-4010-a6a9-63b6bb104fa1",
"name": "文本分割器",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
-144,
480
],
"parameters": {
"options": {
"splitCode": "markdown"
},
"chunkSize": 600,
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "d1fe1c74-d9bc-4040-8446-47e90365c5f7",
"name": "上传 PDF",
"type": "n8n-nodes-base.formTrigger",
"position": [
-832,
112
],
"webhookId": "ff827d70-a596-4f81-a99e-63bf42189fd0",
"parameters": {
"options": {
"ignoreBots": true,
"buttonLabel": "Upload Document",
"appendAttribution": true
},
"formTitle": "Upload Documents to Knowledge Base",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "PDF File",
"multipleFiles": false,
"requiredField": true,
"acceptFileTypes": ".pdf"
}
]
},
"responseMode": "lastNode",
"formDescription": "Upload PDF files to the knowledge base for AI-powered search and retrieval"
},
"typeVersion": 2.2
},
{
"id": "1f04ecce-0277-4a88-9514-fec6b45ba1cf",
"name": "从 PDF 提取文本",
"type": "n8n-nodes-base.mistralAi",
"position": [
-608,
112
],
"parameters": {
"options": {},
"binaryProperty": "file"
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "53c82051-ce9b-432e-b90e-d5eb83483e49",
"name": "准备文档数据",
"type": "n8n-nodes-base.set",
"position": [
-384,
112
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "518ae17b-b486-4438-8151-f49afb3b68eb",
"name": "filename",
"type": "string",
"value": "={{ $('Upload PDF').item.json.file.filename }}"
},
{
"id": "a574ee4d-6341-4fd5-ac8e-9452eff70aa1",
"name": "content",
"type": "string",
"value": "={{ $json.extractedText }}"
},
{
"id": "metadata-source",
"name": "source",
"type": "string",
"value": "uploaded_pdf"
},
{
"id": "metadata-timestamp",
"name": "upload_timestamp",
"type": "string",
"value": "={{ new Date().toISOString() }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "d465c50a-87e9-4824-83ca-d5662630590c",
"name": "存储到向量数据库",
"type": "@n8n/n8n-nodes-langchain.vectorStoreWeaviate",
"position": [
-112,
112
],
"parameters": {
"mode": "insert",
"options": {},
"weaviateCollection": {
"__rl": true,
"mode": "list",
"value": ""
}
},
"typeVersion": 1.3
},
{
"id": "5a5e4028-3764-4bb2-8900-df77c0c47bde",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
112,
304
],
"parameters": {
"color": 4,
"width": 320,
"height": 288,
"content": "## 嵌入与重排序"
},
"typeVersion": 1
},
{
"id": "f0ecfbb5-e9ce-49fd-a921-672b12b7ef13",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
112,
-240
],
"parameters": {
"width": 336,
"height": 288,
"content": "## MCP 服务器触发器"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "8b3d2e49-d84f-4fca-bdda-298f3da3c15b",
"connections": {
"Upload PDF": {
"main": [
[
{
"node": "Extract Text from PDF",
"type": "main",
"index": 0
}
]
]
},
"Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Document Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Cohere Reranker": {
"ai_reranker": [
[
{
"node": "Search Knowledge Base",
"type": "ai_reranker",
"index": 0
}
]
]
},
"Document Loader": {
"ai_document": [
[
{
"node": "Store in Vector Database",
"type": "ai_document",
"index": 0
}
]
]
},
"Cohere Embeddings": {
"ai_embedding": [
[
{
"node": "Search Knowledge Base",
"type": "ai_embedding",
"index": 0
},
{
"node": "Store in Vector Database",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract Text from PDF": {
"main": [
[
{
"node": "Prepare Document Data",
"type": "main",
"index": 0
}
]
]
},
"Prepare Document Data": {
"main": [
[
{
"node": "Store in Vector Database",
"type": "main",
"index": 0
}
]
]
},
"Search Knowledge Base": {
"ai_tool": [
[
{
"node": "MCP Knowledge Server",
"type": "ai_tool",
"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 - 文档提取, 多模态 AI
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
基于Weaviate和OpenAI的RAG文档问答
基于RAG的文档问答：使用Weaviate和OpenAI查询PDF内容
Set
Form Trigger
Extract From File
+9
17 节点Mary Newhauser
文档提取
商业AI指挥中心：Google Workspace模块化代理、向量搜索与多渠道报告
商业AI指挥中心：Google Workspace模块化代理、向量搜索与多渠道报告
Set
Gmail
Slack
+35
80 节点Paul
文档提取
具有增强检索、过滤器和记忆功能的智能 RAG 代理 - 由 ascuncia 开发
具备增强检索和模块化工作流的智能 RAG 代理
Set
Wait
Merge
+16
32 节点Alejandro Scuncia
AI RAG 检索增强
基于 Danelfin、TwelveData 和 Alpha Vantage 的 AI 股票分析
集成 Danelfin、TwelveData 和 Alpha Vantage 的 AI 股票分析系统
Set
Code
Gmail
+23
74 节点Paul
加密货币交易
使用Google Maps、GPT-4和WhatsApp自动化商业合作伙伴拓展
使用Google Maps、GPT-4和WhatsApp自动化商业合作伙伴拓展
If
Set
Code
+23
64 节点Khairul Muhtadin
AI 聊天机器人
重新排名 #1
通过网页爬取、GPT-4o和WhatsApp自动化电话营销
Set
Code
Webhook
+18
48 节点Khaisa Studio
客户培育
工作流信息
难度等级
中级
节点数量13
分类2
节点类型10
作者
Dietmar
@docdMedical specialist in internal medicine, gastroenterology, and infectious diseases. Building innovative healthcare automation workflows with n8n, integrating AI, speech-to-text, and medical data standards for efficient clinical documentation and analysis.
外部链接
在 n8n.io 查看 →
分享此工作流