基于Jina AI DeepSearch的AI驱动研究
中级
这是一个Other, AI领域的自动化工作流,包含 6 个节点。主要使用 Code, HttpRequest, ChatTrigger 等节点,结合人工智能技术实现智能自动化。 基于Jina AI深度搜索的AI驱动研究
前置要求
- •可能需要目标 API 的认证凭证
使用的节点 (6)
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": "GToc9QTzJY1h1w3y",
"meta": {
"instanceId": "cba4a4a2eb5d7683330e2944837278938831ed3c042e20da6f5049c07ad14798",
"templateCredsSetupCompleted": true
},
"name": "使用 Jina AI DeepSearch 的 AI 驱动研究",
"tags": [],
"nodes": [
{
"id": "c76a7993-e7b1-426e-bcb4-9a18d9c72b83",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-820,
-140
],
"parameters": {
"color": 6,
"width": 740,
"height": 760,
"content": ""
},
"typeVersion": 1
},
{
"id": "5620b6b5-1485-43a8-9acd-3368147bd742",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-60,
-140
],
"parameters": {
"width": 740,
"height": 300,
"content": "## 🚀 **免费版:开放深度研究 2.0**"
},
"typeVersion": 1
},
{
"id": "dbe1cc91-34b4-4e5b-b404-dd86f47d1ebf",
"name": "便签2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-60,
180
],
"parameters": {
"width": 740,
"height": 440,
"content": "## 🧠 **工作流运行原理**"
},
"typeVersion": 1
},
{
"id": "42fd2f04-7d83-44c9-a41b-48860efbcf79",
"name": "Jina AI DeepSearch 请求",
"type": "n8n-nodes-base.httpRequest",
"position": [
220,
0
],
"parameters": {
"url": "https://deepsearch.jina.ai/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"jina-deepsearch-v1\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"You are an advanced AI researcher that provides precise, well-structured, and insightful reports based on deep analysis. Your responses are factual, concise, and highly relevant.\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"Hi, how can I help you?\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Provide a deep and insightful analysis on: \\\"{{ $json.chatInput }}\\\". Ensure the response is well-structured, fact-based, and directly relevant to the topic, with no unnecessary information.\"\n }\n ],\n \"stream\": true,\n \"reasoning_effort\": \"low\"\n}",
"sendBody": true,
"specifyBody": "json"
},
"typeVersion": 4.2
},
{
"id": "1b7b3bbe-2068-4d3a-a962-134bbb6ee516",
"name": "用户研究查询输入",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
0,
0
],
"webhookId": "8a4b05af-cd63-4692-9924-e35aaed5f077",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "218cbfe2-78de-4b00-875a-51761ac9f5c7",
"name": "格式化与清理 AI 响应",
"type": "n8n-nodes-base.code",
"position": [
440,
0
],
"parameters": {
"jsCode": "function extractAndFormatMarkdown(input) {\n let extractedContent = [];\n\n // Extract raw data string from n8n input\n let rawData = input.first().json.data;\n\n // Split into individual JSON strings\n let jsonStrings = rawData.split(\"\\n\\ndata: \").map(s => s.replace(/^data: /, ''));\n\n let lastContent = \"\";\n \n // Reverse loop to find the last \"content\" field\n for (let i = jsonStrings.length - 1; i >= 0; i--) {\n try {\n let parsedChunk = JSON.parse(jsonStrings[i]);\n\n if (parsedChunk.choices && parsedChunk.choices.length > 0) {\n for (let j = parsedChunk.choices.length - 1; j >= 0; j--) {\n let choice = parsedChunk.choices[j];\n\n if (choice.delta && choice.delta.content) {\n lastContent = choice.delta.content.trim();\n break;\n }\n }\n }\n\n if (lastContent) break; // Stop once the last content is found\n } catch (error) {\n console.error(\"Failed to parse JSON string:\", jsonStrings[i], error);\n }\n }\n\n // Clean and format Markdown\n lastContent = lastContent.replace(/\\[\\^(\\d+)\\]: (.*?)\\n/g, \"[$1]: $2\\n\"); // Format footnotes\n lastContent = lastContent.replace(/\\[\\^(\\d+)\\]/g, \"[^$1]\"); // Inline footnotes\n lastContent = lastContent.replace(/(https?:\\/\\/[^\\s]+)(?=[^]]*\\])/g, \"<$1>\"); // Format links\n\n // Return formatted content as an array of objects (n8n expects this format)\n return [{ text: lastContent.trim() }];\n}\n\n// Execute function and return formatted output\nreturn extractAndFormatMarkdown($input);\n"
},
"typeVersion": 2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "e03d69b5-3304-4f28-b99f-970d6fd1225b",
"connections": {
"User Research Query Input": {
"main": [
[
{
"node": "Jina AI DeepSearch Request",
"type": "main",
"index": 0
}
]
]
},
"Format & Clean AI Response": {
"main": [
[]
]
},
"Jina AI DeepSearch Request": {
"main": [
[
{
"node": "Format & Clean AI Response",
"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?
中级 - 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
AI SEO可读性审核:检查网站对LLM的友好性
AI SEO可读性审核:检查网站对大型语言模型的友好性
Code
Http Request
Chain Llm
+3
8 节点Leonard
人工智能
开启深度研究 - AI 驱动的自主研究工作流
深度研究 - AI驱动的自主研究工作流
Code
Http Request
Split In Batches
+7
17 节点Leonard
人工智能
⚡AI驱动的YouTube播放列表和视频摘要与分析v2
AI YouTube播放列表与视频分析聊天机器人
If
Set
Code
+20
72 节点dmr
其他
我的工作流 3
基于Llama Parser、Gemini LLM和Pinecone DB的文档分析与聊天机器人创建
If
Code
Gmail
+17
36 节点pavith
其他
基于 Qdrant 和 Mistral 的食谱推荐
基于 Qdrant 和 Mistral 的食谱推荐
Set
Code
Html
+14
33 节点Jimleuk
其他
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