我的工作流 3
高级
这是一个Other, AI领域的自动化工作流，包含 36 个节点。主要使用 If, Code, Gmail, Markdown, Aggregate 等节点，结合人工智能技术实现智能自动化。 基于Llama Parser、Gemini LLM和Pinecone DB的文档分析与聊天机器人创建
前置要求
- •Google 账号和 Gmail API 凭证
- •可能需要目标 API 的认证凭证
- •Google Gemini API Key
- •Pinecone API Key
使用的节点 (36)
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": "cGNK44mkCzIh4113",
"meta": {
"instanceId": "44c282b5a828cd0d7dda8a13c9168fe32406aaef7e8faa5a847408311387e400"
},
"name": "我的工作流 3",
"tags": [],
"nodes": [
{
"id": "4db348cf-bd5a-408e-b212-d75b792460b4",
"name": "表单提交时",
"type": "n8n-nodes-base.formTrigger",
"position": [
-1720,
20
],
"webhookId": "34a4ae98-8eb8-486b-8d7e-dd5fdde15cd5",
"parameters": {
"options": {},
"formTitle": "form which gets multiple files",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "file1",
"requiredField": true
},
{
"fieldType": "file",
"fieldLabel": "file2"
},
{
"fieldLabel": "provide your mail Id",
"requiredField": true
}
]
}
},
"typeVersion": 2.2
},
{
"id": "6a1f197f-310e-4eb1-926f-60cfbae60a49",
"name": "遍历项目1",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-380,
20
],
"parameters": {
"options": {}
},
"typeVersion": 3,
"alwaysOutputData": false
},
{
"id": "7eb210e4-687c-4e9d-b2e7-50d0b85da8dc",
"name": "如果2",
"type": "n8n-nodes-base.if",
"position": [
700,
100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "1edbcd59-130d-4053-9db3-cb8dec068fe0",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "SUCCESS"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e76b9523-3f87-4ad3-87df-1e4e93ead090",
"name": "聚合",
"type": "n8n-nodes-base.aggregate",
"position": [
0,
0
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "markdown"
}
]
}
},
"typeVersion": 1
},
{
"id": "21234dcf-52dc-4ae0-975e-36a1a18ed456",
"name": "Google Gemini 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1060,
180
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "52fcaca7-c49d-4004-96a3-0094ed0e510f",
"name": "拆分二进制项",
"type": "n8n-nodes-base.code",
"position": [
-1000,
20
],
"parameters": {
"jsCode": "// Get the input data\nconst items = $input.all()\n\n// Initialize an array to hold the split items\nconst splitItems = [];\n\n// Iterate over each item\nitems.forEach(item => {\n // Check if the item has binary data\n if (item.binary) {\n // Iterate over each binary field\n for (const [key, value] of Object.entries(item.binary)) {\n // Create a new item for each binary file\n splitItems.push({\n json: {},\n binary: {\n data: value\n }\n });\n }\n }\n});\n\n// Return the split items\nreturn splitItems;"
},
"typeVersion": 2,
"alwaysOutputData": true
},
{
"id": "4660eef4-de62-4b13-9f51-05000b1afa33",
"name": "解析文档",
"type": "n8n-nodes-base.httpRequest",
"position": [
260,
100
],
"parameters": {
"url": "https://api.cloud.llamaindex.ai/api/parsing/upload",
"method": "POST",
"options": {
"redirect": {
"redirect": {}
}
},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "=file",
"parameterType": "formBinaryData",
"inputDataFieldName": "=data"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "07e76215-b9d4-4adb-b8f3-f8c8615abb56",
"name": "检查解析状态",
"type": "n8n-nodes-base.httpRequest",
"position": [
480,
100
],
"parameters": {
"url": "=https://api.cloud.llamaindex.ai/api/parsing/job/{{ $json.id }}",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "3909a632-7002-4d60-a53b-3f73e4958c27",
"name": "提供 Markdown",
"type": "n8n-nodes-base.httpRequest",
"position": [
1180,
400
],
"parameters": {
"url": "=https://api.cloud.llamaindex.ai/api/parsing/job/{{ $json.id }}/result/markdown",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer $secret token"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "89c25b95-8bc6-4bb5-82d2-1f870416c4af",
"name": "Google Gemini 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1600,
300
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "8ddf6e94-6da0-4ef9-a6dc-0db8967914a6",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
2140,
0
],
"parameters": {
"mode": "markdownToHtml",
"options": {},
"markdown": "={{ $json.output }}",
"destinationKey": "html"
},
"typeVersion": 1
},
{
"id": "59c33f95-6f8f-4992-8421-dc3a0b668861",
"name": "Gmail",
"type": "n8n-nodes-base.gmail",
"position": [
4540,
0
],
"webhookId": "35fdc2a2-b8f8-4217-be0b-66ed98a548f1",
"parameters": {
"sendTo": "={{ $('On form submission4').item.json['provide your mail Id'] }}",
"message": "=Hi user,\nThe below document contains the detailed analysis of the provided document.\n\nYou can also use the below link to interact with the assistant regarding your doubts on the analysis\nhttps://pavithranvh28.app.n8n.cloud/webhook/8c5c9e83-f595-4e4b-b45c-544a9a0840c4/chat\n\n\n",
"options": {
"attachmentsUi": {
"attachmentsBinary": [
{}
]
}
},
"subject": "Analysis of the documents provided",
"emailType": "text"
},
"typeVersion": 2.1
},
{
"id": "b9bb8338-d52e-4f5b-bd2f-d517851b6014",
"name": "代码",
"type": "n8n-nodes-base.code",
"position": [
3200,
0
],
"parameters": {
"jsCode": "const items = $input.first().json.html;\n\n// Ensure items is an array\nconst htmlArray = Array.isArray(items) ? items : [items];\n\nfunction htmlToFormattedText(html) {\n // Replace heading tags (h1-h6) with bold text\n html = html.replace(/<h[1-6]>(.*?)<\\/h[1-6]>/gi, \"\\n**$1**\\n\");\n\n // Replace paragraph tags with spacing\n html = html.replace(/<p>(.*?)<\\/p>/gi, \"\\n$1\\n\");\n\n // Replace line breaks with newline characters\n html = html.replace(/<br\\s*\\/?>/gi, \"\\n\");\n\n // Remove all other HTML tags\n html = html.replace(/<[^>]+>/g, \"\").trim();\n\n // Remove extra newlines\n return html.replace(/\\n{2,}/g, \"\\n\").trim();\n}\n\nconst updatedItems = htmlArray.map((item) => {\n const htmlContent = item?.json?.html || item;\n const textContent = htmlToFormattedText(htmlContent);\n return { textContent };\n});\n\nreturn updatedItems;\n"
},
"typeVersion": 2
},
{
"id": "e8176d99-3625-47a5-8989-80fdce053ba7",
"name": "转换为文件",
"type": "n8n-nodes-base.convertToFile",
"position": [
3840,
0
],
"parameters": {
"options": {},
"operation": "toText",
"sourceProperty": "textContent"
},
"typeVersion": 1.1
},
{
"id": "9fb1a6a0-c49f-48f5-93bc-f0c6e9b8a138",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2600,
460
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemMessage": "You are a helpful assistant.\nObjective:\nThe agent must process the input content to enhance readability, apply structured formatting, and bold necessary text elements while preserving the original meaning.\n\nProcessing Rules:\nApply Text Formatting:\n\nConvert any text enclosed with * (asterisks) into bold.\nStructurize the Content:\n\nOrganize the content using clear section headers.\nSeparate sections with line breaks for readability.\nEnsure proper indentation and bullet point usage for clarity.\nMaintain Clarity & Coherence:\n\nReformat the text without changing the core meaning.\nRemove redundancy while ensuring key details remain intact.\nText File Compatibility:\n\nResponse NEEDS TO BE A TEXT FILE"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "9995921a-ca41-40c5-9159-350908ca8213",
"name": "Google Gemini聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2780,
740
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "bd281ef9-bc33-4b3a-9d3f-41d00521b14e",
"name": "信息提取器",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
2820,
880
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemPromptTemplate": "You are an expert extraction algorithm.\nOnly extract relevant information from the text.\nIf you do not know the value of an attribute asked to extract, you may omit the attribute's value."
},
"attributes": {
"attributes": [
{
"name": "Project Overview",
"description": "overview of the content extracted"
},
{
"name": "System and prerequisites",
"description": "=which contains the information about the system and the prerequisites needed"
}
]
}
},
"typeVersion": 1
},
{
"id": "2f1c4efb-6885-48c9-b2a6-a13d2e9b4f66",
"name": "Google Gemini 聊天模型1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
3140,
1100
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "b7a0276a-d253-43a8-a7f3-fb3b83599d7f",
"name": "转换为文件",
"type": "n8n-nodes-base.convertToFile",
"position": [
1840,
740
],
"parameters": {
"options": {},
"operation": "toText",
"sourceProperty": "output"
},
"typeVersion": 1.1
},
{
"id": "7441e1ff-1966-4535-abaa-ee565db787de",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
2080,
980
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "samuraichamploo",
"cachedResultName": "samuraichamploo"
}
},
"typeVersion": 1.1
},
{
"id": "82d9d9fb-6f8c-4c86-9287-d5e7e73f58a7",
"name": "Embeddings Mistral Cloud",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
2140,
1200
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "3a3332f7-3fda-4898-999e-c5020c0ea02e",
"name": "默认数据加载器",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
2240,
1280
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "4a625913-5c98-4075-9022-058e863af326",
"name": "递归字符文本分割器",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
2320,
1460
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "5e38e72b-390f-433f-a638-522537bf1369",
"name": "当收到聊天消息时",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1820,
660
],
"webhookId": "8c5c9e83-f595-4e4b-b45c-544a9a0840c4",
"parameters": {
"public": true,
"options": {}
},
"typeVersion": 1.1
},
{
"id": "77ea1fd6-73a9-42f6-835f-b945ce7fd294",
"name": "问答链",
"type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
"position": [
-1400,
680
],
"parameters": {
"options": {
"systemPromptTemplate": "You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question.\nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\nContext: {context}"
}
},
"typeVersion": 1.5
},
{
"id": "d71b0efe-7e27-44f8-beb4-370c02ef1d5f",
"name": "Google Gemini聊天模型2",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-1380,
1020
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "eb967c9d-415f-4992-bacd-517b7dddd6bf",
"name": "向量存储检索器",
"type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
"position": [
-1220,
900
],
"parameters": {},
"typeVersion": 1
},
{
"id": "690eacb5-1d47-430b-8914-4c474833be0b",
"name": "Pinecone 向量存储",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-900,
1060
],
"parameters": {
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "samuraichamploo",
"cachedResultName": "samuraichamploo"
}
},
"typeVersion": 1.1
},
{
"id": "6d289625-ca46-49d7-8ee2-5996dc645ebe",
"name": "Mistral Cloud1 嵌入",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
-780,
1460
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "dcc8bb20-e5f3-428e-93be-dc4081e1463c",
"name": "AI Agent1",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-460,
680
],
"parameters": {
"text": "={{ $json.response }}",
"options": {
"systemMessage": "You are a helpful assistant.rephrase the prompt provided and Provide ONLY the response in a text format"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "777b4e63-7a0a-42fa-9069-83ab006e19a9",
"name": "Google Gemini 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-400,
980
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-flash"
},
"typeVersion": 1
},
{
"id": "f5d69ecd-9cdc-4bef-a8ae-7477dfc3f7c7",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1900,
440
],
"parameters": {
"width": 360,
"content": "## 我是一个注释"
},
"typeVersion": 1
},
{
"id": "7140d564-a636-4937-b2c6-811b48dde851",
"name": "翻译代理",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1060,
0
],
"parameters": {
"text": "={{ $('Aggregate1').item.json.markdown }}",
"options": {
"systemMessage": "You are a helpful assistant. Kindly check the prompt fed and find the language of the prompt you receive and if the prompt is in other language except english translate it and provide that as a response and also ATTACH THE REMAINING PROMPT WHICH IS IN ENGLISH WITH THE RESPONSE"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "496d49f1-5b7f-48ab-b759-2facd8fade8d",
"name": "分析代理",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1420,
0
],
"parameters": {
"text": "={{ $json.output }}",
"options": {
"systemMessage": "=You are a helpful assistant. \n1️⃣ Comprehensive Prompt Analysis\n\nCarefully examine the entire prompt provided by the user.\nEnsure all details are considered before formulating a response.\n2️⃣ Interactive and Clear Breakdown\n\nStructure the response in a well-organized manner with clear topic separation.\nPresent insights in a way that enhances understanding and usability.\n3️⃣ Duplicate Check and Handling\n\nIdentify and highlight any repeated information within the prompt.\nIf duplicates exist, consolidate the relevant details to avoid redundancy.\n4️⃣ Reliable and Actionable Resolutions\n\nProvide resolutions that are dependable and practical.\nEnsure the solutions align with the context and user’s intent.\nWhere applicable, offer alternative approaches for flexibility.\nAlso make sure not to add too much of star or hash to indicate the difference"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "4218f320-c580-41ae-91ca-134bd2cc8128",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
2880,
640
],
"parameters": {
"content": "## 我是一个注释"
},
"typeVersion": 1
},
{
"id": "bc0a3e52-1259-4651-bbe4-9ba727d8e46a",
"name": "便签2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1420,
700
],
"parameters": {
"content": "## 我是一个注释"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "7c6e0b7c-dfbb-45e5-bc16-038ff6175cdc",
"connections": {
"If2": {
"main": [
[
{
"node": "Provide the markdown",
"type": "main",
"index": 0
}
],
[
{
"node": "Check the parsing status",
"type": "main",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[]
]
},
"Markdown": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Aggregate1": {
"main": [
[
{
"node": "Translator Agent",
"type": "main",
"index": 0
}
]
]
},
"Analyzer Agent": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
},
{
"node": "AI Agent",
"type": "main",
"index": 0
},
{
"node": "Information Extractor",
"type": "main",
"index": 0
},
{
"node": "Convert to File4",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Gmail",
"type": "main",
"index": 0
}
]
]
},
"Convert to File4": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items1": {
"main": [
[
{
"node": "Aggregate1",
"type": "main",
"index": 0
}
],
[
{
"node": "Parsing the document",
"type": "main",
"index": 0
}
]
]
},
"Translator Agent": {
"main": [
[
{
"node": "Analyzer Agent",
"type": "main",
"index": 0
},
{
"node": "Convert to File4",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"On form submission4": {
"main": [
[
{
"node": "split the binary item",
"type": "main",
"index": 0
}
]
]
},
"Parsing the document": {
"main": [
[
{
"node": "Check the parsing status",
"type": "main",
"index": 0
}
]
]
},
"Provide the markdown": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"split the binary item": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"Pinecone Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Retriever",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Vector Store Retriever": {
"ai_retriever": [
[
{
"node": "Question and Answer Chain",
"type": "ai_retriever",
"index": 0
}
]
]
},
"Check the parsing status": {
"main": [
[
{
"node": "If2",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud1": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "Information Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model2": {
"ai_languageModel": [
[
{
"node": "Question and Answer Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model3": {
"ai_languageModel": [
[
{
"node": "AI Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model5": {
"ai_languageModel": [
[
{
"node": "Translator Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model6": {
"ai_languageModel": [
[
{
"node": "Analyzer Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Question and Answer Chain": {
"main": [
[
{
"node": "AI Agent1",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Question and Answer Chain",
"type": "main",
"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？
高级 - 其他, 人工智能
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
在可视化参考库中探索n8n节点
在可视化参考库中探索n8n节点
If
Ftp
Set
+93
113 节点I versus AI
其他
基于AI的MIS代理
基于AI的管理信息系统代理
If
Set
Code
+29
129 节点Kumar Shivam
客户支持
高级AI演示（在AI开发者第14次聚会中展示）
高级AI演示（在AI开发者第14次聚会中展示）
If
Code
Gmail
+19
39 节点Max Tkacz
构建模块
生成考试题目
基于Google文档和Gemini的AI驱动自动生成考试题目与答案
Code
Google Docs
Http Request
+17
37 节点Davide
其他
AI 代理餐厅 [模板]
🤖 WhatsApp、Instagram 和 Messenger 的 AI 餐厅助手
If
N8n
Set
+37
239 节点Amanda Benks
其他
使用 Qdrant 的完整 RAG 系统，带自动来源引用
使用Qdrant、Gemini和OpenAI构建带自动引用的RAG系统
Set
Code
Wait
+15
29 节点Davide
人工智能
