Back to articles
AI & Cloud

Configure AI Log Parser with Qwen 2.5 Coder on VPS for Automatic System Error Classification

A detailed guide on configuring an AI log parser using Qwen 2.5 Coder on a VPS to automatically classify system errors and provide detailed repair suggestions, enhancing system...

DPTCloud Engineering4 min read
Configure AI Log Parser with Qwen 2.5 Coder on VPS for Automatic System Error Classification

Image credit: ClickerHappy · Pixabay Content License

Introduction to AI Log Parser with Qwen 2.5 Coder

In modern system environments, monitoring and analyzing logs are critical for ensuring system stability and performance. With the advancement of AI, automated log analysis tools like Qwen 2.5 Coder enable users to automate system error classification and provide detailed repair suggestions. This guide explains how to configure an AI log parser on a high-RAM Cloud VPS to leverage the power of this AI model effectively.

Requirements and Environment Setup

To deploy an AI log parser with Qwen 2.5 Coder, ensure the following prerequisites are met:

  • Run on a high-RAM Cloud VPS (minimum 8GB RAM, preferably 16GB or more).
  • Operating system: Ubuntu 20.04/22.04 or Debian 11/12.
  • Python 3.9 or higher.
  • Docker and Docker Compose installed.
  • Qwen 2.5 Coder API key (available from Qwen AI).

Configuration on VPS

Begin by installing necessary tools and setting up the working environment.

1. Install Docker and Docker Compose

sudo apt update
sudo apt install -y docker.io docker-compose
sudo systemctl enable docker
sudo systemctl start docker
sudo usermod -aG docker $USER

2. Create Project Directory

mkdir -p ~/ai-log-parser && cd ~/ai-log-parser

3. Create Docker Compose Configuration

Generate a docker-compose.yml file with the following content:

version: '3.8'
services:
  log-parser:
    image: python:3.9-slim
    container_name: ai-log-parser
    volumes:
      - ./logs:/logs
      - ./output:/output
    working_dir: /app
    command: >
      sh -c "pip install requests && python parse_logs.py"
    environment:
      - QWEN_API_KEY=your_qwen_api_key_here
      - LOG_DIR=/logs
      - OUTPUT_DIR=/output

4. Write Log Analysis Script

Create a file named parse_logs.py:

import os
import requests
import json
import glob
from datetime import datetime

# Qwen API configuration
QWEN_API_URL = "https://qwen.aliyun.com/api/v1"
API_KEY = os.getenv("QWEN_API_KEY")

def send_to_qwen(log_text):
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    payload = {
        "model": "qwen-2.5-coder",
        "messages": [
            {"role": "system", "content": "You are a system expert. Analyze the log error and provide detailed repair suggestions."},
            {"role": "user", "content": log_text}
        ]
    }
    try:
        response = requests.post(QWEN_API_URL, headers=headers, json=payload)
        return response.json()
    except Exception as e:
        return {"error": str(e)}

def process_logs():
    log_files = glob.glob("/logs/*.log")
    for log_file in log_files:
        with open(log_file, "r") as f:
            log_content = f.read()
        if log_content.strip():
            result = send_to_qwen(log_content)
            output_file = f"/output/{os.path.basename(log_file)}_parsed.json"
            with open(output_file, "w") as f:
                json.dump(result, f, indent=2)
            print(f"Processed: {log_file}")

if __name__ == "__main__":
    process_logs()

Execution and Verification

Run the application using Docker:

docker-compose up -d

Ensure logs are stored in the /logs directory, and results will be output to /output.

Result Explanation and Validation

Qwen 2.5 Coder will analyze log content and return results in JSON format with the following fields:

  • error: If an API call fails.
  • content: Detailed repair suggestions.
  • classification: Error type (e.g., "System Error", "Network Issue").

Troubleshooting

  • No response from Qwen API: Verify the API key, network connectivity, and access permissions.
  • Logs not processed: Check the log directory path, read permissions, and file format.
  • Long processing time: Optimize log input, split large log files, or use a more powerful VPS.

References

DPTCloud Tier III Infrastructure

High-RAM Cloud VPS Plans Optimized for AI, Databases & Cache

Enterprise RAID 10 NVMe SSDs, CMC & FPT District 9 uplinks with Anycast Anti-DDoS and 99.99% SLA.

View 22 VPS Plans
ECO · vn-02Recommended

VPS-4E

297.000 ₫ / mo

10% VAT included

  • CPU: 4 vCPU
  • RAM: 8 GB
  • SSD: 50 GB NVMe
ECO · vn-02

VPS-5E

614.900 ₫ / mo

10% VAT included

  • CPU: 8 vCPU
  • RAM: 16 GB
  • SSD: 100 GB NVMe
ADVANCED · vn-03Recommended

VPS-4T

548.900 ₫ / mo

10% VAT included

  • CPU: 4 vCPU
  • RAM: 8 GB
  • SSD: 50 GB NVMe

Related Articles

View all
ZaloZalo SupportDiscord0384 753 478