AI CV Screening Workflow
工作流概述
这是一个包含7个节点的中等工作流,主要用于自动化处理各种任务。
工作流源代码
{
"id": "ES4TSw9HacxoNhLZ",
"meta": {
"instanceId": "5219bc76ea806909b58e13e2acac1c19192522e70dc3c90467e1800e94864105",
"templateCredsSetupCompleted": true
},
"name": "AI CV Screening Workflow",
"tags": [],
"nodes": [
{
"id": "e77fbc32-5ee9-49b4-93d5-f2ffda134b08",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1230,
530
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"id": "UcdfdADI6w9nkgg5",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "9e24167f-cac6-4b98-95da-30065510d79a",
"name": "Confirmation of CV Submission",
"type": "n8n-nodes-base.gmail",
"position": [
1780,
460
],
"webhookId": "954756dc-2946-4b78-b208-06f3df612ab5",
"parameters": {
"sendTo": "={{ $('Application Form').item.json['E-mail'] }}",
"message": "=Dear {{ $('Application Form').item.json['Full Name'] }},
Thank you for submitting your CV. We have received it and will review it shortly.
Best regards,
Mediusware",
"options": {},
"subject": "We Have Received Your CV"
},
"credentials": {
"gmailOAuth2": {
"id": "taFlf0vD5S4QlOKM",
"name": "Gmail account"
}
},
"typeVersion": 2.1
},
{
"id": "ff49d370-b4eb-4426-b396-763455e647e7",
"name": "Inform HR New CV Received",
"type": "n8n-nodes-base.gmail",
"position": [
1760,
200
],
"webhookId": "e969a9f5-631b-4719-a4f6-87e6063cef6a",
"parameters": {
"sendTo": "sarfaraz@mediusaware.com",
"message": "=Hello HR,
A new CV has been successfully received in our system. Please review the candidate's details at your earliest convenience.
Candidate Name: {{ $('Application Form').item.json['Full Name'] }}
Candidate E-mail: {{ $('Application Form').item.json['E-mail'] }}
Candidate Linkedin: {{ $('Application Form').item.json.Linkedin }}
Candidate Expectation: {{ $('Application Form').item.json.Expectation }}
Candidate AI Rating: {{ $('Using AI Analysis & Rating').item.json.text }}
Thank you for your attention.
Best regards,
Automated CV Screening",
"options": {},
"subject": "New Candidate CV Awaiting Review"
},
"credentials": {
"gmailOAuth2": {
"id": "taFlf0vD5S4QlOKM",
"name": "Gmail account"
}
},
"typeVersion": 2.1
},
{
"id": "8479fa4c-10bc-4914-896d-f5b00d063fa8",
"name": "Using AI Analysis & Rating",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1320,
240
],
"parameters": {
"text": "={{ $json.text }}",
"messages": {
"messageValues": [
{
"message": "Rule 1 : Do not exceed maximum of 75 words. As an AI with advanced capabilities in talent acquisition and human resources, your task is to conduct a thorough and intricate analysis of a candidate's resume or CV against a specific job description. You will assist hiring professionals in discerning the alignment between the candidate's skills, experience, qualifications, and the requirements of the job. Your expert insights will equip employers with a lucid understanding of the candidate's suitability for the role. Very important for you to write output text in ${output_language} language. It's VERY IMPORTANT for me for text be in ${output_language} or I will be fired. Your analysis should follow this structured format: 1. **Compatibility Rating**: Propose an overall compatibility rating on a scale from 1 (not compatible) to 10 (perfect fit). Support your rating by elucidating the rationale behind it. 2. **Recommendation**: Informed by your analysis and compatibility rating, offer a recommendation on whether the employer should consider this candidate for an interview. Furnish a well-argued explanation for your recommendation. Remember, your analysis should be comprehensive, professional, and actionable. It should equip an employer with a vivid understanding of the candidate's suitability for the role. This isn't merely about ticking off boxes; it's about illustrating a comprehensive picture of how well the candidate might fit into the role and complement the existing team. Here is your task: Analyze the compatibility of the following candidate's resume with the provided job description. Endeavor to apply your deep understanding of talent evaluation to provide the most insightful analysis. Job description: \"Software Engineer\" Resume: ${resume}
No Markdown Please, only plain text. Please no double '**'"
}
]
},
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "da0fd18b-2420-471e-b930-9aabc45bc2ca",
"name": "Convert Binary to Json",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1080,
220
],
"parameters": {
"options": {},
"operation": "pdf",
"binaryPropertyName": "Your_Resume_CV"
},
"retryOnFail": false,
"typeVersion": 1
},
{
"id": "bc5480c1-d9c2-414b-8cd4-0b3e49d4dde9",
"name": "Application Form",
"type": "n8n-nodes-base.formTrigger",
"position": [
820,
380
],
"webhookId": "0cd422d3-e69f-4ec0-92ab-05362808c4da",
"parameters": {
"options": {},
"formTitle": "Application for Software Engineer Position",
"formFields": {
"values": [
{
"fieldLabel": "Full Name",
"requiredField": true
},
{
"fieldLabel": "E-mail",
"requiredField": true
},
{
"fieldLabel": "Expectation",
"placeholder": "2000-3000$",
"requiredField": true
},
{
"fieldLabel": "Linkedin",
"requiredField": true
},
{
"fieldType": "file",
"fieldLabel": "Your Resume/CV",
"requiredField": true,
"acceptFileTypes": ".pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "d2dfbf1e-8d88-49e6-940d-e1717de97b30",
"name": "Candidate Lists",
"type": "n8n-nodes-base.googleSheets",
"position": [
1540,
480
],
"parameters": {
"columns": {
"value": {
"CV": "={{ $('Application Form').item.json['Your Resume/CV'][0].filename }}",
"E-mail": "={{ $('Application Form').item.json['E-mail'] }}",
"Linkedin": "={{ $('Application Form').item.json.Linkedin }}",
"AI Rating": "={{ $json.text }}",
"Full Name": "={{ $('Application Form').item.json['Full Name'] }}",
"Expectation": "={{ $('Application Form').item.json.Expectation }}"
},
"schema": [
{
"id": "CV",
"type": "string",
"display": true,
"required": false,
"displayName": "CV",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Full Name",
"type": "string",
"display": true,
"required": false,
"displayName": "Full Name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "E-mail",
"type": "string",
"display": true,
"required": false,
"displayName": "E-mail",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Expectation",
"type": "string",
"display": true,
"required": false,
"displayName": "Expectation",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Linkedin",
"type": "string",
"display": true,
"required": false,
"displayName": "Linkedin",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "AI Rating",
"type": "string",
"display": true,
"required": false,
"displayName": "AI Rating",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": []
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1y4FFMXTuznSf2wWUraK57eBJnu4MVtgkxrGYRzRMwDQ/edit#gid=0",
"cachedResultName": "পত্রক1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1y4FFMXTuznSf2wWUraK57eBJnu4MVtgkxrGYRzRMwDQ",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1y4FFMXTuznSf2wWUraK57eBJnu4MVtgkxrGYRzRMwDQ/edit?usp=drivesdk",
"cachedResultName": "CV of Software Engineers"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "YdlTTXiu8194dEFE",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
}
],
"active": true,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "2036fff4-ab9c-4981-a8b4-44be4654630d",
"connections": {
"Candidate Lists": {
"main": [
[
{
"node": "Inform HR New CV Received",
"type": "main",
"index": 0
}
]
]
},
"Application Form": {
"main": [
[
{
"node": "Convert Binary to Json",
"type": "main",
"index": 0
}
]
]
},
"Convert Binary to Json": {
"main": [
[
{
"node": "Using AI Analysis & Rating",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Using AI Analysis & Rating",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Inform HR New CV Received": {
"main": [
[
{
"node": "Confirmation of CV Submission",
"type": "main",
"index": 0
}
]
]
},
"Using AI Analysis & Rating": {
"main": [
[
{
"node": "Candidate Lists",
"type": "main",
"index": 0
}
]
]
}
}
}
功能特点
- 自动检测新邮件
- AI智能内容分析
- 自定义分类规则
- 批量处理能力
- 详细的处理日志
技术分析
节点类型及作用
- @N8N/N8N Nodes Langchain.Lmchatgooglegemini
- Gmail
- @N8N/N8N Nodes Langchain.Chainllm
- Extractfromfile
- Formtrigger
复杂度评估
配置难度:
维护难度:
扩展性:
实施指南
前置条件
- 有效的Gmail账户
- n8n平台访问权限
- Google API凭证
- AI分类服务订阅
配置步骤
- 在n8n中导入工作流JSON文件
- 配置Gmail节点的认证信息
- 设置AI分类器的API密钥
- 自定义分类规则和标签映射
- 测试工作流执行
- 配置定时触发器(可选)
关键参数
| 参数名称 | 默认值 | 说明 |
|---|---|---|
| maxEmails | 50 | 单次处理的最大邮件数量 |
| confidenceThreshold | 0.8 | 分类置信度阈值 |
| autoLabel | true | 是否自动添加标签 |
最佳实践
优化建议
- 定期更新AI分类模型以提高准确性
- 根据邮件量调整处理批次大小
- 设置合理的分类置信度阈值
- 定期清理过期的分类规则
安全注意事项
- 妥善保管API密钥和认证信息
- 限制工作流的访问权限
- 定期审查处理日志
- 启用双因素认证保护Gmail账户
性能优化
- 使用增量处理减少重复工作
- 缓存频繁访问的数据
- 并行处理多个邮件分类任务
- 监控系统资源使用情况
故障排除
常见问题
邮件未被正确分类
检查AI分类器的置信度阈值设置,适当降低阈值或更新训练数据。
Gmail认证失败
确认Google API凭证有效且具有正确的权限范围,重新进行OAuth授权。
调试技巧
- 启用详细日志记录查看每个步骤的执行情况
- 使用测试邮件验证分类逻辑
- 检查网络连接和API服务状态
- 逐步执行工作流定位问题节点
错误处理
工作流包含以下错误处理机制:
- 网络超时自动重试(最多3次)
- API错误记录和告警
- 处理失败邮件的隔离机制
- 异常情况下的回滚操作