From 8ae983d191faeeaeeab1ac2c110399eeaf9e79cd Mon Sep 17 00:00:00 2001 From: root Date: Thu, 26 Feb 2026 14:35:04 +0800 Subject: [PATCH] =?UTF-8?q?add=20workflow=20=E6=8B=9B=E8=81=98=E4=BF=A1?= =?UTF-8?q?=E6=81=AF=E5=AF=BC=E5=85=A5,dev?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../批量处理招聘数据/batch_gen_recruiment.py | 361 ++++++++++++++++++ .../招聘信息导入/wf_dag_agent_recruitment.py | 53 +++ 2 files changed, 414 insertions(+) create mode 100644 dev/workflow/TK_Cust/agent_recruitment/批量处理招聘数据/batch_gen_recruiment.py create mode 100644 dev/workflow/TK_Cust/agent_recruitment/招聘信息导入/wf_dag_agent_recruitment.py diff --git a/dev/workflow/TK_Cust/agent_recruitment/批量处理招聘数据/batch_gen_recruiment.py b/dev/workflow/TK_Cust/agent_recruitment/批量处理招聘数据/batch_gen_recruiment.py new file mode 100644 index 0000000..60852b2 --- /dev/null +++ b/dev/workflow/TK_Cust/agent_recruitment/批量处理招聘数据/batch_gen_recruiment.py @@ -0,0 +1,361 @@ +import requests +import json +import psycopg2 +from psycopg2.extras import RealDictCursor +import time +from typing import List, Dict, Any +import logging + +# 配置日志 +logging.basicConfig( + level=logging.INFO, + format='%(asctime)s - %(levelname)s - %(message)s' +) +logger = logging.getLogger(__name__) + +class APIClient: + """简化的API客户端类""" + + def __init__(self, api_url: str, auth_token: str): + self.api_url = api_url + self.headers = { + 'Authorization': auth_token, + 'Content-Type': 'application/json' + } + + def call_api_with_inputs(self, inputs: Dict[str, Any]) -> Dict[str, Any]: + """直接调用带inputs参数的API + + Args: + inputs: inputs参数字典 + + Returns: + API响应数据 + """ + payload = json.dumps({ + "inputs": inputs, + "response_mode": "blocking", + "user": "admin" + }) + + try: + logger.info("调用带inputs参数的API") + response = requests.post( + self.api_url, + headers=self.headers, + data=payload, + timeout=1200 + ) + + response.raise_for_status() + logger.info(f"API调用成功，状态码: {response.status_code}") + + return { + "success": True, + "status_code": response.status_code, + "data": response.json() + } + + except requests.exceptions.RequestException as e: + logger.error(f"API调用失败: {e}") + return { + "success": False, + "error": str(e) + } + + def call_api_without_inputs(self, other_params: Dict[str, Any] = None) -> Dict[str, Any]: + """直接调用不带inputs参数的API + + Args: + other_params: 其他参数字典 + + Returns: + API响应数据 + """ + payload = { + "inputs": {}, + "response_mode": "blocking", + "user": "admin" + } + + # 添加其他参数 + if other_params: + payload.update(other_params) + + try: + logger.info("调用不带inputs参数的API") + response = requests.post( + self.api_url, + headers=self.headers, + data=json.dumps(payload), + timeout=1200 + ) + + response.raise_for_status() + logger.info(f"API调用成功，状态码: {response.status_code}") + + return { + "success": True, + "status_code": response.status_code, + "data": response.json() + } + + except requests.exceptions.RequestException as e: + logger.error(f"API调用失败: {e}") + return { + "success": False, + "error": str(e) + } + + + def call_api_with_query(self, query: str = None) -> Dict[str, Any]: + """直接调用带inputs参数的API + + Args: + query: 查询语句 + + Returns: + API响应数据 + """ + payload = json.dumps({ + "inputs": {}, + "query" : query, + "response_mode": "streaming", + "user": "admin" + }) + + try: + logger.info("调用带inputs参数的API") + response = requests.post( + self.api_url, + headers=self.headers, + data=payload, + timeout=2400 + ) + + response.raise_for_status() + logger.info(f"API调用成功，状态码: {response.status_code}") + + return { + "success": True, + "status_code": response.status_code, + "data": response.json() + } + + except requests.exceptions.RequestException as e: + logger.error(f"API调用失败: {e}") + return { + "success": False, + "error": str(e) + } + + def call_api_without_query(self, other_params: Dict[str, Any] = None) -> Dict[str, Any]: + """直接调用不带inputs参数的API + + Args: + other_params: 其他参数字典 + + Returns: + API响应数据 + """ + payload = { + "inputs": {}, + "query":"", + "response_mode": "streaming", + "user": "admin" + } + + # 添加其他参数 + if other_params: + payload.update(other_params) + + try: + logger.info("调用不带inputs参数的API") + response = requests.post( + self.api_url, + headers=self.headers, + data=json.dumps(payload), + timeout=2400 + ) + + response.raise_for_status() + logger.info(f"API调用成功，状态码: {response.status_code}") + + return { + "success": True, + "status_code": response.status_code, + "data": response.json() + } + + except requests.exceptions.RequestException as e: + logger.error(f"API调用失败: {e}") + return { + "success": False, + "error": str(e) + } + +class DatabaseManager: + """数据库管理类""" + + def __init__(self, db_config: Dict[str, str]): + self.db_config = db_config + self.connection = None + + def connect(self): + """连接数据库""" + try: + self.connection = psycopg2.connect( + host=self.db_config.get('host', 'localhost'), + port=self.db_config.get('port', '5432'), + database=self.db_config.get('database', 'postgres'), + user=self.db_config.get('user', 'postgres'), + password=self.db_config.get('password', ''), + cursor_factory=RealDictCursor + ) + logger.info("数据库连接成功") + except Exception as e: + logger.error(f"数据库连接失败: {e}") + raise + + def disconnect(self): + """断开数据库连接""" + if self.connection: + self.connection.close() + logger.info("数据库连接已关闭") + + def get_urls_from_database(self, query: str = None) -> List[str]: + """从数据库获取URL列表""" + if not self.connection: + self.connect() + + # 默认查询语句，根据实际情况修改 + if query is None: + query = "SELECT 1" + + try: + with self.connection.cursor() as cursor: + cursor.execute(query) + results = cursor.fetchall() + + # 处理结果，返回字符串列表 + datas = [list(row.values())[0] for row in results] + return datas + + except Exception as e: + logger.error(f"查询数据库失败: {e}") + return [] +#DATABASE_URL=postgresql://dbuser_dba:EmBRxnmmjnE3@124.221.232.219:5432/daas_mpp +#DATABASE_SCHEMA=p70_ai_intelligence +def main(): + """主函数""" + # 数据库配置 + db_config = { + 'host': '124.221.232.219', + 'port': '5432', + 'database': 'dify', + 'user': 'dbuser_dba', + 'password': 'EmBRxnmmjnE3', + 'schema': 'p70_ai_intelligence' + } + + # API配置 + api_config = { + 'url': 'http://tk-agent.idgvalue.com/v1/workflows/run', + 'auth_token': 'Bearer app-siNKLRExkzO9IM81P8hHuBx2' + } + + api_client = APIClient(api_config['url'], api_config['auth_token']) + + type = 'agent' + type = 'workflow' + + try: + flag = True + + if flag: + # 初始化 + db_manager = DatabaseManager(db_config) + custom_query = """ SELECT + ds.document_id, + MIN(ds.created_at) AS doc_time, + string_agg(ds.content, '' ORDER BY ds.position) AS full_text +FROM public.document_segments ds +WHERE ds.dataset_id = '33d1b946-acd2-4538-b6cc-e0cd77824aba' + AND ds.enabled + AND ds.created_at >= NOW() - INTERVAL '24 hours' +GROUP BY ds.document_id +ORDER BY doc_time DESC """ + + try: + # 从数据库获取URL列表 + list = db_manager.get_urls_from_database(custom_query) + + if not list: + logger.warning("未获取到URL") + return + + # 遍历每个URL调用API + for i, text in enumerate(list, 1): + logger.info(f"处理第 {i}/{len(list)} 个数据: {text}") + + if type is 'workflow': + # 方法1: 使用带inputs参数的调用 + inputs_data = { + "content": f"{text}", + "type":"招聘信息汇总" + } + + result = api_client.call_api_with_inputs(inputs_data) + + if result['success']: + logger.info(f"URL {text} 处理成功") + else: + logger.error(f"URL {text} 处理失败: {result.get('error')}") + + + else: + #agent + query = text + result = api_client.call_api_with_query(query) + + if result['success']: + logger.info(f"URL {text} 处理成功") + else: + logger.error(f"URL {text} 处理失败: {result.get('error')}") + + # 可选：添加延迟避免请求过于频繁 + if i < len(text): + time.sleep(1) + + except Exception as e: + logger.error(f"程序执行失败: {e}") + + finally: + db_manager.disconnect() + + else: + logger.info("调用不带inputs参数的API示例") + if type is 'workflow': + result2 = api_client.call_api_without_inputs() + + if result2['success']: + logger.info("不带inputs参数的API调用成功") + else: + logger.error(f"不带inputs参数的API调用失败: {result2.get('error')}") + + else: + #agent + result2 = api_client.call_api_without_query() + + if result2['success']: + logger.info("不带inputs参数的API调用成功") + else: + logger.error(f"不带inputs参数的API调用失败: {result2.get('error')}") + + except Exception as e: + logger.error(f"初始化失败: {e}") + + + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/dev/workflow/TK_Cust/agent_recruitment/招聘信息导入/wf_dag_agent_recruitment.py b/dev/workflow/TK_Cust/agent_recruitment/招聘信息导入/wf_dag_agent_recruitment.py new file mode 100644 index 0000000..842bc05 --- /dev/null +++ b/dev/workflow/TK_Cust/agent_recruitment/招聘信息导入/wf_dag_agent_recruitment.py @@ -0,0 +1,53 @@ +#!/usr/bin/python +# -*- encoding=utf-8 -*- +from airflow import DAG +from datetime import datetime, timedelta +from airflow.contrib.hooks.ssh_hook import SSHHook +from airflow.contrib.operators.ssh_operator import SSHOperator +from airflow.sensors.external_task_sensor import ExternalTaskSensor +import json + +from airflow.operators.trigger_dagrun import TriggerDagRunOperator +from airflow.operators.email_operator import EmailOperator +from airflow.utils.trigger_rule import TriggerRule + + +sshHook = SSHHook(ssh_conn_id ='ssh_air') +default_args = { +'owner': 'tek_newsletter@163.com', +'email_on_failure': True, +'email_on_retry':True, +'start_date': datetime(2024, 1, 1), +'depends_on_past': False, +'retries': 6, +'retry_delay': timedelta(minutes=10), +} + +dag = DAG('wf_dag_agent_recruitment', default_args=default_args, +schedule_interval="0 1 * * 5", +catchup=False, +dagrun_timeout=timedelta(minutes=600), +max_active_runs=3, +tags=['64cbd1bbced14209b5e3a879f89e8ab1','TK_Cust','招聘信息导入'] +) + +task_failed = EmailOperator ( + dag=dag, + trigger_rule=TriggerRule.ONE_FAILED, + task_id="task_failed", + to=["tek_newsletter@163.com"], + cc=[""], + subject="agent_recruitment_failed", + html_content='

您好，agent_recruitment作业失败，请及时处理"

') + + +batch_gen_recruiment = SSHOperator( +ssh_hook=sshHook, +task_id='batch_gen_recruiment', +command='cd /data/airflow/etl/agents && python batch_gen_recruiment.py', +params={'my_param':"batch_gen_recruiment"}, +depends_on_past=False, +retries=1, +dag=dag) + +batch_gen_recruiment >> task_failed