Skip to content

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NKAIOps-SoftwareChange

Repository of SCELM, SoftwareChange Project from AIOps Lab, Nankai University.

Maintained by Weihua Kuang, Guided by Yongqian Sun and Shenglin Zhang.

feel free to email weihua.kwong@mail.nankai.edu.cn if you have any function problems.

News

⭐️ 2025/03/25: Our Paper A Multimodal Intelligent Change Assessment Framework for Microservice Systems Based on Large Language Models (SCELM) accepted by FSE 2025 Industry (45/165)!

2025/03/10: Test & Deploy SCELM on ByteDance enterprise data.

2025/01/23: Paper submission to FSE 2025.

2025/01/10: Refactor code.

... : more detailed depolyment tutorials comming soon!

About

Using Large Language Model to improve efficiency of software change maintainance.

Our method achieved SOTA performance on the business scenario:

  • Yun Zhanghu Technology
  • preliminary tests on ByteDance

示意图

Environment

Tools

  • Ollama, deploy models on local server
    • version 0.5.1
    • recommended model: gemma2-9b, qwen2.5-7b,llama3.1-7b
  • Redis, vector database
    • version 7.2.5

Models

download the model files from the web and place them under the /model folder

How to run

1. Run Ollama server

ollama serve

(optional) Test ollama model chat

models supported according to: Ollama Models

ollama pull <model_name>
<input chat content>

2. Run Redis server

redis-server

more detailed command according to Redis tutorials,

(recommended) Use Redis Insight to visually manage data, mind your connection port.

3. Run SCELM function code

  1. Part1_AreaText-Generate

    Generate areatext according to change information.

  2. Part2_LLM-Generate

    Change analysis by LLM using Retriever-Augmented Generation.

4. Evaluate results

according to codes in /utils

Contributions

Any function problems connect Weihua Kuang by weihua.kwong@mail.nankai.edu.cn

Any baseline experiments connect Chao Shen by 2213404@mail.nankai.edu.cn

  • RAG functional code, experiment design & Paper script by Weihua Kuang,
  • Baseline experiment by Chao Shen,
  • Co-guided & Mainly paper writing by other writers.

Thanks

  • Tinghua Zheng, his intern experience in Yun Zhanghu Technology leads to this project.
  • Guangba Yu helps for one baseline experiment about his work ChangeRCA.
  • Hailin Zhang helps run our SCELM on preliminary data of Bytedance.

About

Using LLM to improve efficiency of software change maintainance. Paper accepted by FSE 2025 Industry.

Resources

Stars

1 star

Watchers

2 watching

Forks

Releases

Packages

Used by

Contributors

Languages