Microservices Engine:Use XXL-JOB and DeepSeek to push hot news and analyze financial data

Option 1: Deploy locally with Ollama

The steps below use DeepSeek as an example. The same process applies to QwQ or other Ollama-supported models.

1. Install Ollama from https://ollama.com/download.

   

2. Pull the DeepSeek-R1 model. The R1 variant focuses on complex logical reasoning and is best suited for data analysis. Choose a model size based on your hardware. For example, if your machine has 16 GB of RAM, use the 7b model: The following table lists hardware requirements for each model size.

   Model	Size	GPU memory	RAM
   deepseek-r1:1.5b	1.1 GB	4 GB+	8 GB+
   deepseek-r1:7b	4.7 GB	8 GB+	16 GB+
   deepseek-r1:8b	4.9 GB	10 GB+	18 GB+
   deepseek-r1:14b	9.0 GB	16 GB+	32 GB+
   deepseek-r1:32b	20 GB	24 GB+	64 GB+

      ollama pull deepseek-r1:7b

   

   

3. Verify the deployment by sending a request to the OpenAI-compatible API. Ollama serves on port 11434 by default: The OpenAI-compatible API simplifies integration -- the same client code works for both local and cloud-hosted models.

      curl http://localhost:11434/v1/chat/completions \
        -H "Content-Type: application/json" \
        -d '{
          "model": "deepseek-r1:7b",
          "messages": [{"role": "user", "content": "Hello"}]
        }'

   

Option 2: Use Alibaba Cloud Model Studio

Alibaba Cloud Model Studio provides hosted access to DeepSeek, QwQ, and other models. Activate the service to start making API calls immediately -- no infrastructure setup required. A free quota is included, and you can switch between models at any time.

Option 1: Deploy locally

For detailed steps, see the XXL-JOB official documentation. The general process:

1. Prepare a database and initialize the table schema.

   

2. Import the XXL-JOB source code into your IDE and configure xxl-job-admin in the application configuration file.

   

3. Run the XxlJobAdminApplication class, then open http://127.0.0.1:8080/xxl-job-admin in your browser. Default credentials: username admin, password 123456.

Option 2: Use the managed MSE XXL-JOB service

Alibaba Cloud Microservices Engine (MSE) provides a fully managed XXL-JOB service. To get started, see Create an XXL-JOB instance. A free trial is available.

Step 1: Deploy the executor application

1. Log on to the ACK console and create an ACK serverless cluster. To pull the demo image, enable SNAT on the VPC. Skip this step if SNAT is already configured.

2. In the ACK console, click the cluster name. In the left-side navigation pane, choose Workloads > Stateless. Click Create from YAML and apply the following deployment configuration: Replace the following placeholders with your actual values:

   Placeholder	Description	Example
   <your-xxljob-admin-address>	MSE XXL-JOB instance endpoint	http://xxljob-xxxxx.schedulerx.mse.aliyuncs.com
   <your-app-name>	Executor application name registered in XXL-JOB	my-news-app
   <your-access-token>	XXL-JOB access token	xxxxxxx
   <your-api-key>	Alibaba Cloud Model Studio API key	sk-xxx
   <your-dingtalk-webhook-url>	DingTalk group robot webhook URL	https://oapi.dingtalk.com/robot/send?access_token=xx

   The following is a sample YAML configuration for the application deployment:

   apiVersion: apps/v1
   kind: Deployment
   metadata:
     name: xxljob-demo
     labels:
       app: xxljob-demo
   spec:
     replicas: 2
     selector:
       matchLabels:
         app: xxljob-demo
     template:
       metadata:
         labels:
           app: xxljob-demo
       spec:
         containers:
         - name: xxljob-executor
           image: schedulerx-registry.cn-hangzhou.cr.aliyuncs.com/schedulerx3/xxljob-demo:2.4.1
           ports:
           - containerPort: 9999
           env:
             - name: JAVA_OPTS
               value: >-
                 -Dxxl.job.admin.addresses=<your-xxljob-admin-address>
                 -Dxxl.job.executor.appname=<your-app-name>
                 -Dxxl.job.accessToken=<your-access-token>
                 -Ddashscope.api.key=<your-api-key>
                 -Dwebhook.url=<your-dingtalk-webhook-url>

Step 2: Get the startup parameters

1. XXL-JOB connection parameters: Log on to the MSE XXL-JOB console and select a region. Click the target instance. On the Application Management page, click Access in the Executor Count column for the target application. Click Copy to copy the connection parameters into your YAML configuration:

      -Dxxl.job.admin.addresses=http://xxljob-xxxxx.schedulerx.mse.aliyuncs.com
      -Dxxl.job.executor.appname=xxxxx
      -Dxxl.job.accessToken=xxxxxxx

   

2. Model Studio API key: Log on to Alibaba Cloud Model Studio. Click the profile icon in the upper-right corner and select API-KEY. On the management page, create or copy an API key.

      -Ddashscope.api.key=sk-xxx

3. DingTalk webhook URL: In your DingTalk group settings, add a custom robot and copy the webhook URL.

      -Dwebhook.url=https://oapi.dingtalk.com/robot/send?access_token=xx

Step 3: Create and run the news task

Architecture

Set up a three-task dependency chain in MSE XXL-JOB:

Pull financial data --> Analyze data --> Generate report

How the pipeline runs

1. Pull financial data (sharding broadcast routing): XXL-JOB dispatches parallel sub-tasks to multiple executors. Each executor pulls data from a different source (equities, forex, commodities, and so on). Results are stored in a shared location such as a database, Redis, or Object Storage Service (OSS).

2. Analyze data: After all shards complete, this task retrieves the collected data and sends it to DeepSeek for analysis. The results are stored for the next stage.

3. Generate report: This task compiles the analysis results into a structured investment report and delivers it to stakeholders through DingTalk or email.

This pattern -- parallel data collection, centralized analysis, automated distribution -- applies to any scenario where you need to aggregate data from multiple sources and produce AI-driven insights on a schedule.