JSON架构师 - 为任何AI智能体动态生成JSON输出格式
高级
这是一个Engineering, Multimodal AI领域的自动化工作流，包含 34 个节点。主要使用 If, Set, StopAndError, ManualTrigger, SplitInBatches 等节点。 使用Mistral为AI智能体生成动态JSON输出格式
前置要求
- •无特殊前置要求，导入即可使用
使用的节点 (34)
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": "ITJwpEvX9Zijl4Xe",
"meta": {
"instanceId": "c8661626eeda758e004fa6cdc30e89de83810c1ff0923b0bb91a200abd0100f3",
"templateCredsSetupCompleted": true
},
"name": "JSON 架构师 - 为任何 AI Agent 动态生成 JSON 输出格式",
"tags": [
{
"id": "JK3I68rY6cIlUP5Z",
"name": "V1.0",
"createdAt": "2025-06-20T18:01:10.400Z",
"updatedAt": "2025-06-20T18:01:10.400Z"
},
{
"id": "in8l539iu2Ha3BD8",
"name": "JSON Architect",
"createdAt": "2025-07-07T01:55:29.343Z",
"updatedAt": "2025-07-08T22:56:33.698Z"
},
{
"id": "nEQ2nHALSQN4jgJ0",
"name": "Free",
"createdAt": "2025-06-25T21:55:38.353Z",
"updatedAt": "2025-06-25T21:55:38.353Z"
}
],
"nodes": [
{
"id": "d8b4728f-23bb-42cf-aff4-128e61d141ad",
"name": "Mistral Cloud Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud",
"position": [
1020,
80
],
"parameters": {
"model": "mistral-small-latest",
"options": {
"safeMode": true,
"maxRetries": 2
}
},
"credentials": {
"mistralCloudApi": {
"id": "i9fED0hhcQnPZBi6",
"name": "Blank Account"
}
},
"typeVersion": 1
},
{
"id": "66103c5a-f12d-4505-a1b5-2e294bb3f827",
"name": "JSON 输出解析器",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1020,
-140
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"data\": {\n \"type\": \"object\",\n \"properties\": {\n \"json_format_name\": {\n \"type\": \"string\",\n \"description\": \"A proper identification for this JSON format structure. Use snake_case.\"\n },\n \"json_format_usage\": {\n \"type\": \"string\",\n \"description\": \"How are subsequent AI Agents supposed to use the information in the JSON and its parameters.\"\n },\n \"json_format_structure\": {\n \"type\": \"object\",\n \"description\": \"The expected JSON object format for the necessary use-case.\"\n }\n },\n \"required\": [\"json_format_name\", \"json_format_usage\", \"json_format_structure\"],\n \"additionalProperties\": false\n }\n },\n \"required\": [\"data\"],\n \"additionalProperties\": false\n}"
},
"typeVersion": 1.2
},
{
"id": "608baf6f-daa5-4f8c-8edb-643decee6197",
"name": "JSON 生成器",
"type": "@n8n/n8n-nodes-langchain.agent",
"maxTries": 2,
"position": [
740,
-280
],
"parameters": {
"text": "={{ $json.input }}\n\n-----\n\nLast JSON Format Attempt (If it Already Exists): \n\"\"\"\n{{ $json.last_json_format_attempt }}\n\"\"\"\n\nCorrection Needed (In The Last JSON Format Attempt):\n\"\"\"\n{{ $json.correction_required }}\n\"\"\"",
"options": {
"systemMessage": "=You are a senior data engineer, tasked with creating the best possible JSON structure for the use-case informed in the prompt. Do not let any relevant information out of the JSON Structure. Here is an example of what is expected:\n\n\"\"\"\n{\n \"type\": \"object\",\n \"properties\": {\n \"data\": {\n \"type\": \"object\",\n \"properties\": {\n \"property_name_1\": {\n \"type\": \"string\",\n \"description\": \"...\"\n },\n \"property_name_2\": {\n \"type\": \"object\",\n \"description\": \"...\"\n },\n ...,\n \"property_name_N\": {\n \"type\": \"array\",\n \"description\": \"...\"\n }\n },\n \"required\": [\"property_name_1\", \"property_name_2\", ..., \"property_name_N\"],\n \"additionalProperties\": false\n }\n },\n \"required\": [\"data\"],\n \"additionalProperties\": false\n}\n\"\"\"\n\nRemember to consider the possibility of a property nesting other structures inside it: in that case the pattern provided above will repeat itself.\nRemember to be succint with your proposed JSON structure. Avoid pointless redundancy, unnecessary repetitions as much as possible."
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6,
"waitBetweenTries": 3000
},
{
"id": "53456018-4071-4442-a132-83eb1fad40f7",
"name": "JSON 验证器",
"type": "@n8n/n8n-nodes-langchain.agent",
"maxTries": 2,
"position": [
1240,
-280
],
"parameters": {
"text": "=JSON Format Name:\n{{ $json.output.data.json_format_name }}\n\nContext:\n{{ $json.output.data.json_format_usage }}\n\nInput used to generate the JSON:\n{{ $('Loop Until it Works').item.json.input }}\n\nJSON Format Structure:\n\"\"\"\n{{ $json.output.data.json_format_structure.toJsonString() }}\n\"\"\"\n",
"options": {
"systemMessage": "=You are an expert Data Analyst. Your ability to understand and validate data structures is unmatched.\nYou are tasked with reading a JSON format generated for an specific purpose.\nYou will assure the JSON is following the best practices.\nIf it isn't, then you must mark it as an invalid JSON.\n\nFor a JSON format to be considered valid, just having a proper structure isn't enough. The context must align with the JSON format itself."
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6,
"waitBetweenTries": 3000
},
{
"id": "5eaac98d-84b9-4e03-8ea0-980a375f4cae",
"name": "JSON 输出解析器 2",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1400,
-20
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"data\": {\n \"type\": \"object\",\n \"properties\": {\n \"json_format_valid\": {\n \"type\": \"boolean\",\n \"description\": \"The AI Agent's final veridict over the received JSON's format. It will be 'true' if it is a valid format, otherwise it will be 'false'.\"\n },\n \"json_format_valid_reason\": {\n \"type\": \"string\",\n \"description\": \"The AI Agent's reason for its veridict.\"\n }\n },\n \"required\": [\"json_format_valid\", \"json_format_valid_reason\"],\n \"additionalProperties\": false\n }\n },\n \"required\": [\"data\"],\n \"additionalProperties\": false\n}"
},
"typeVersion": 1.2
},
{
"id": "8f1dbe6a-d35e-43bd-b5d1-6553f223bf89",
"name": "当点击\"执行工作流\"时",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-500,
-140
],
"parameters": {},
"typeVersion": 1
},
{
"id": "426b7257-a0b3-4ce3-a8f9-c02222d5582f",
"name": "准备输入",
"type": "n8n-nodes-base.set",
"position": [
-240,
-140
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0bebc801-88ee-48b6-9fdf-26124a3d2712",
"name": "input",
"type": "string",
"value": "=A scenario where two characters are speaking with each other. It is during the night. They are talking about their respective magical powers: the ability to see the future and the ability to use alchemy."
},
{
"id": "a7b62d3e-7171-4fb6-a6d0-7cffb33b21b9",
"name": "correction_required",
"type": "string",
"value": ""
},
{
"id": "39435221-2a3c-4b50-be83-a6035cca75b4",
"name": "last_json_format_attempt",
"type": "string",
"value": ""
},
{
"id": "cfff3d04-a827-4a50-8d61-04778b75dc7d",
"name": "max_rounds",
"type": "number",
"value": 10
},
{
"id": "d2e8c5ce-7242-4596-92cc-5dc76befe6ab",
"name": "rounds",
"type": "number",
"value": 0
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "f9de1d71-8da8-4a5a-a8d3-9aad4f0b6821",
"name": "循环直到成功",
"type": "n8n-nodes-base.splitInBatches",
"position": [
420,
-80
],
"parameters": {
"options": {
"reset": true
}
},
"typeVersion": 3
},
{
"id": "733867ee-9d1a-4cca-a82f-51d87ee53b35",
"name": "更新输入",
"type": "n8n-nodes-base.set",
"position": [
1820,
280
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0bebc801-88ee-48b6-9fdf-26124a3d2712",
"name": "input",
"type": "string",
"value": "={{ $('Loop Until it Works').item.json.input }}"
},
{
"id": "a7b62d3e-7171-4fb6-a6d0-7cffb33b21b9",
"name": "correction_required",
"type": "string",
"value": "={{ $json.output.data.json_format_valid_reason }}"
},
{
"id": "39435221-2a3c-4b50-be83-a6035cca75b4",
"name": "last_json_format_attempt",
"type": "string",
"value": "={{ $('JSON Generator').item.json.output.data.json_format_structure.toJsonString() }}"
},
{
"id": "9f360b45-e90f-46e7-99aa-f7997bdab87e",
"name": "rounds",
"type": "number",
"value": "={{ $('Guarantee Input').item.json.rounds + 1}}"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "397a0c82-fab4-43c4-bbc6-7716cc087738",
"name": "如果有效 JSON",
"type": "n8n-nodes-base.if",
"position": [
1580,
-100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "4f15c457-d790-468f-9468-177378348593",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.output.data.json_format_valid }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "60d59670-4f1e-43a4-ab88-80db611fd810",
"name": "JSON 审查器",
"type": "@n8n/n8n-nodes-langchain.agent",
"onError": "continueErrorOutput",
"maxTries": 3,
"position": [
1900,
-240
],
"parameters": {
"text": "=Input to fit in the JSON:\n{{ $('Guarantee Input').item.json.input }}",
"agent": "conversationalAgent",
"options": {
"systemMessage": "You are an expert Data Scientist. Your ability to work with data structures is unmatched.\nYou are tasked with testing the performance a JSON format generated for an specific purpose.\nYou will assure the JSON is working for its purpose by trying to fit in the input as best as you can in the JSON.\nIf you cannot do it, then it is an invalid JSON and the informed JSON structure should be ignored.\n\nFor a JSON format to be used in a valid manner, just having a proper structure isn't enough. The context must functionally work with the JSON format itself.\nIf the JSON is valid, then you must structure the input using the JSON.\n\n"
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6,
"waitBetweenTries": 3000
},
{
"id": "051fa8d6-aef4-49c9-8e3b-55f2781bba53",
"name": "保证输入",
"type": "n8n-nodes-base.set",
"position": [
20,
-100
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0ac8a4d1-15e0-4e32-84a4-66776d35eff9",
"name": "input",
"type": "string",
"value": "={{ $json.input }}"
},
{
"id": "fabe83a4-0ad5-477a-a91d-dc88987e510b",
"name": "correction_required",
"type": "string",
"value": "={{ $json.correction_required }}"
},
{
"id": "4aef78c1-b422-40cc-8e38-505cd55eac2e",
"name": "last_json_format_attempt",
"type": "string",
"value": "={{ $json.last_json_format_attempt }}"
},
{
"id": "a015a41b-7ed2-4259-bcdc-28120b7111e4",
"name": "rounds",
"type": "number",
"value": "={{ $json.rounds }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "b202d5ce-5386-42ce-8825-5562a56fff55",
"name": "Mistral Cloud Chat Model 2",
"type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud",
"position": [
1900,
-20
],
"parameters": {
"model": "mistral-small-latest",
"options": {
"safeMode": true,
"maxRetries": 2
}
},
"credentials": {
"mistralCloudApi": {
"id": "i9fED0hhcQnPZBi6",
"name": "Blank Account"
}
},
"typeVersion": 1
},
{
"id": "d013093a-da21-433c-8a27-57cca6a4439e",
"name": "高级 JSON 输出解析器",
"type": "n8n-nodes-advanced-output-parser.advancedOutputParser",
"position": [
2060,
-20
],
"parameters": {
"jsonSchema": "={{ $('JSON Generator').item.json.output.data.json_format_structure.toJsonString() }}",
"schemaMode": "dynamic"
},
"typeVersion": 1
},
{
"id": "cce477a7-a9d6-4427-abbd-39812c18dbfa",
"name": "更新输入 2",
"type": "n8n-nodes-base.set",
"position": [
2280,
340
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0bebc801-88ee-48b6-9fdf-26124a3d2712",
"name": "input",
"type": "string",
"value": "={{ $('Loop Until it Works').item.json.input }}"
},
{
"id": "a7b62d3e-7171-4fb6-a6d0-7cffb33b21b9",
"name": "correction_required",
"type": "string",
"value": "={{ $json.error }}"
},
{
"id": "39435221-2a3c-4b50-be83-a6035cca75b4",
"name": "last_json_format_attempt",
"type": "string",
"value": "={{ $('JSON Generator').item.json.output.data.json_format_structure.toJsonString() }}"
},
{
"id": "42881de4-54be-4647-8500-7b6d0ef11006",
"name": "rounds",
"type": "number",
"value": "={{ $('Guarantee Input').item.json.rounds + 1}}"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "c744a93e-2f1c-4695-85e5-e33bf7bd133c",
"name": "JSON 格式有效！",
"type": "n8n-nodes-base.noOp",
"position": [
2600,
-260
],
"parameters": {},
"typeVersion": 1
},
{
"id": "d252e5ee-a4f0-488c-9af7-fd72941425fa",
"name": "准备输出",
"type": "n8n-nodes-base.set",
"notes": "Adding a time string in the json_format_name for the sake of uniqueness.",
"position": [
2820,
-260
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "9eb037d0-83be-417c-8dcf-346860d9fdff",
"name": "input",
"type": "string",
"value": "={{ $('Guarantee Input').item.json.input }}"
},
{
"id": "0db22777-79cf-4cc8-acf4-0c548c7b9070",
"name": "json_format_name",
"type": "string",
"value": "={{ $('JSON Generator').item.json.output.data.json_format_name }}_{{ $now.format('yyyy-MM-dd_HH_mm_ss') }}"
},
{
"id": "853f31e7-fede-474f-a077-e30cd6ab1629",
"name": "json_format_usage",
"type": "string",
"value": "={{ $('JSON Generator').item.json.output.data.json_format_usage }}"
},
{
"id": "1177b5ee-b661-49dd-8d53-acc21c349715",
"name": "json_format_valid_reason",
"type": "string",
"value": "={{ $('If Valid JSON').item.json.output.data.json_format_valid_reason }}"
},
{
"id": "a870a989-2485-48c9-a248-f2da1ba16643",
"name": "json_format_structure",
"type": "object",
"value": "={{ $('JSON Generator').item.json.output.data.json_format_structure }}"
},
{
"id": "552aea6f-da3e-4a0a-b97a-14323751a6df",
"name": "json_format_input",
"type": "object",
"value": "={{ $('JSON Reviewer').item.json.output.conversation }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2be9cb84-bc58-4d3d-8768-7bd2cf4d6e10",
"name": "如果没有更多轮次",
"type": "n8n-nodes-base.if",
"position": [
200,
-100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "e5534ac9-e0b4-473f-9525-bd9ede7b6128",
"operator": {
"type": "number",
"operation": "equals"
},
"leftValue": "={{ $json.rounds }}",
"rightValue": "={{ $('Prepare Input').item.json.max_rounds }}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "2f70e3b8-18b3-47cb-9edd-de4bb3c327ac",
"name": "便签 12",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1440,
-600
],
"parameters": {
"color": 7,
"width": 840,
"height": 820,
"content": "## JSON 架构师 - 为任何 AI Agent 动态生成 JSON 输出格式"
},
"typeVersion": 1
},
{
"id": "b4a5da69-fb3e-4db6-b41a-cae237c1523c",
"name": "便签6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-780,
-520
],
"parameters": {
"color": 7,
"width": 150,
"content": "![Hybroht](https://hybroht.com/assets/favicon.png \"Hybroht Logo\")"
},
"typeVersion": 1
},
{
"id": "06e1b233-f22c-4219-8367-24c18921404b",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-60,
-680
],
"parameters": {
"width": 2560,
"height": 1240,
"content": "# JSON 构建"
},
"typeVersion": 1
},
{
"id": "4a528b75-cf8e-4534-8bc4-7f875047bd03",
"name": "便签 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
660,
-500
],
"parameters": {
"color": 5,
"width": 1080,
"height": 720,
"content": "## JSON 生成与验证"
},
"typeVersion": 1
},
{
"id": "110676e0-1bcd-431b-bb3b-b62709e675a9",
"name": "便签 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1800,
-400
],
"parameters": {
"color": 5,
"width": 660,
"height": 560,
"content": "## JSON 测试"
},
"typeVersion": 1
},
{
"id": "80045779-5409-4662-8b89-1a142e750f7a",
"name": "便签 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
660,
240
],
"parameters": {
"color": 2,
"width": 1800,
"height": 300,
"content": "## 验证或测试失败"
},
"typeVersion": 1
},
{
"id": "8815f509-8644-4a1b-991e-6213efa58d26",
"name": "达到轮次限制",
"type": "n8n-nodes-base.stopAndError",
"position": [
420,
-280
],
"parameters": {
"errorMessage": "Round Limit Reached!"
},
"typeVersion": 1
},
{
"id": "ade7be68-4ad1-4884-b38a-2abdf52c80fe",
"name": "便签 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-40,
-400
],
"parameters": {
"color": 5,
"width": 680,
"height": 560,
"content": "## 轮次开始"
},
"typeVersion": 1
},
{
"id": "240025e4-8d07-406f-bb96-c1ec875d8c23",
"name": "便签 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
2540,
-440
],
"parameters": {
"color": 6,
"width": 580,
"height": 820,
"content": "## JSON 架构师结果"
},
"typeVersion": 1
},
{
"id": "b3659bca-2065-4b12-b065-4e02a63bc626",
"name": "便签 13",
"type": "n8n-nodes-base.stickyNote",
"position": [
-560,
-400
],
"parameters": {
"color": 4,
"width": 480,
"height": 720,
"content": "## 设置和启动"
},
"typeVersion": 1
},
{
"id": "992d3320-5cfd-4a61-8924-75461afb6778",
"name": "便签8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-560,
-680
],
"parameters": {
"color": 7,
"width": 480,
"height": 260,
"content": "### 信息 - n8N 设置"
},
"typeVersion": 1
},
{
"id": "0fa743a0-19f7-4999-b023-85bee0edc506",
"name": "便签15",
"type": "n8n-nodes-base.stickyNote",
"position": [
-520,
60
],
"parameters": {
"color": 7,
"width": 380,
"height": 220,
"content": "**预期输入**："
},
"typeVersion": 1
},
{
"id": "4abd3949-dec0-4292-a6fd-5b4d815f9896",
"name": "便签 16",
"type": "n8n-nodes-base.stickyNote",
"position": [
2580,
-60
],
"parameters": {
"color": 7,
"width": 480,
"height": 360,
"content": "**预期输出**："
},
"typeVersion": 1
},
{
"id": "33a162fa-5031-4443-814b-12e120ea3787",
"name": "便签 17",
"type": "n8n-nodes-base.stickyNote",
"position": [
100,
200
],
"parameters": {
"color": 7,
"width": 380,
"height": 220,
"content": "**轮次参数**："
},
"typeVersion": 1
},
{
"id": "47f5a6d6-7405-49e2-89a2-91d62518b56b",
"name": "便签7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1420,
340
],
"parameters": {
"color": 3,
"width": 1340,
"height": 1980,
"content": "### 输入和输出示例"
},
"typeVersion": 1
},
{
"id": "fa3c77db-ff57-435b-94fc-8ac91011a249",
"name": "便签9",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
700
],
"parameters": {
"color": 3,
"width": 1000,
"height": 1620,
"content": "- **json_format_structure**："
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "e6abb899-a1db-43cc-8548-45c5848bc4f4",
"connections": {
"Update Input": {
"main": [
[
{
"node": "Guarantee Input",
"type": "main",
"index": 0
}
]
]
},
"If Valid JSON": {
"main": [
[
{
"node": "JSON Reviewer",
"type": "main",
"index": 0
}
],
[
{
"node": "Update Input",
"type": "main",
"index": 0
}
]
]
},
"JSON Reviewer": {
"main": [
[
{
"node": "JSON Format Works!",
"type": "main",
"index": 0
}
],
[
{
"node": "Update Input 2",
"type": "main",
"index": 0
}
]
]
},
"Prepare Input": {
"main": [
[
{
"node": "Guarantee Input",
"type": "main",
"index": 0
}
]
]
},
"JSON Generator": {
"main": [
[
{
"node": "JSON Validator",
"type": "main",
"index": 0
}
]
]
},
"JSON Validator": {
"main": [
[
{
"node": "If Valid JSON",
"type": "main",
"index": 0
}
]
]
},
"Update Input 2": {
"main": [
[
{
"node": "Guarantee Input",
"type": "main",
"index": 0
}
]
]
},
"Guarantee Input": {
"main": [
[
{
"node": "If No More Rounds",
"type": "main",
"index": 0
}
]
]
},
"If No More Rounds": {
"main": [
[
{
"node": "Round Limit Reached",
"type": "main",
"index": 0
}
],
[
{
"node": "Loop Until it Works",
"type": "main",
"index": 0
}
]
]
},
"JSON Format Works!": {
"main": [
[
{
"node": "Prepare Output",
"type": "main",
"index": 0
}
]
]
},
"JSON Output Parser": {
"ai_outputParser": [
[
{
"node": "JSON Generator",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Loop Until it Works": {
"main": [
[],
[
{
"node": "JSON Generator",
"type": "main",
"index": 0
}
]
]
},
"JSON Output Parser 2": {
"ai_outputParser": [
[
{
"node": "JSON Validator",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Mistral Cloud Chat Model": {
"ai_languageModel": [
[
{
"node": "JSON Generator",
"type": "ai_languageModel",
"index": 0
},
{
"node": "JSON Validator",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Mistral Cloud Chat Model 2": {
"ai_languageModel": [
[
{
"node": "JSON Reviewer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Advanced JSON Output Parser": {
"ai_outputParser": [
[
{
"node": "JSON Reviewer",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"When clicking ‘Execute workflow’": {
"main": [
[
{
"node": "Prepare Input",
"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 - 工程, 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
AI Arena - AI 代理辩论以优化答案并模拟场景
使用 Mistral 模拟 AI 代理间辩论以优化答案
If
Set
Wait
+13
38 节点Hybroht
工程
灵活新闻聚合器 - 多源集成、AI分析和可设置频道
多源新闻策展系统，集成Mistral AI分析、摘要和自定义频道
If
Set
Xml
+32
120 节点Hybroht
内容创作
基于 YouTube 视频的自主博客发布
使用 ChatGPT、Sheets、Apify、Pexels 和 WordPress 从 YouTube 视频自主发布博客
If
Set
Code
+18
80 节点Oriol Seguí
内容创作
使用正则表达式和 AI 发现隐藏的网站 API 端点
使用正则表达式和人工智能发现隐藏的网站API端点
If
Set
Html
+19
58 节点Yulia
工程
使用Gemini AI视觉分析与Telegram警报监控X平台品牌提及
使用Gemini AI视觉分析与Telegram警报监控X平台品牌提及
If
Set
Code
+13
24 节点Atta
杂项
AI智能助手：与Supabase存储和Google Drive文件对话
AI智能助手：与Supabase存储和Google Drive文件对话
If
Set
Wait
+20
62 节点Mark Shcherbakov
工程
工作流信息
难度等级
高级
节点数量34
分类2
节点类型11
作者
Hybroht
@hybrohtCompany dedicated to delivering tailored software solutions and data-driven experiences through effective technology. We develop workflows leveraging AI agents to maximize the productive benefits of artificial intelligence.
外部链接
在 n8n.io 查看 →
分享此工作流