COOTWbot by ngetahun

Project Description

At SCC, we have a rotating task of COOTW (Commanding Office of the Week). This task involves responding to customer requests from jira and slack help channels, monitoring production systems and doing small chores. Usually, we have documentation to help the COOTW answer questions and quickly find fixes. Most of these are distributed across github, trello and SUSE Support documentation. The aim of this project is to explore the magic of LLMs and create a conversational bot.

Goal for this Hackweek

• Build data ingestion Data source:
  • SUSE KB docs
  • scc github docs
  • scc trello knowledge board

• Test out new RAG architecture

• https://gitlab.suse.de/ngetahun/cootwbot

---

Drag Race - comparative performance testing for pull requests by balanza

Description

«Sophia, a backend developer, submitted a pull request with optimizations for a critical database query. Once she pushed her code, an automated load test ran, comparing her query against the main branch. Moments later, she saw a new comment automatically added to her PR: the comparison results showed reduced execution time and improved efficiency. Smiling, Sophia messaged her team, “Performance gains confirmed!”»

Goals

• To have a convenient and ergonomic framework to describe test scenarios, including environment and seed;
• to compare results from different tests
• to have a GitHub action that executes such tests on a CI environment

Resources

The MVP will be built on top of Preevy and K6.

---

Yearly Quality Engineering Ask me Anything - AMA for not-engineering by szarate

Goal

Get a closer look at how developers work on the Engineering team (R & D) of SUSE, and close the collaboration gap between GSI and Engineering

Why?

Santiago can go over different development workflows, and can do a deepdive into how Quality Engineering works (think of my QE Team, the advocates for your customers), The idea of this session is to help open the doors to opportunities for collaboration, and broaden our understanding of SUSE as a whole.

Objectives

• Give $audience a small window on how to get some questions answered either on the spot or within days of how some things at engineering are done
• Give Santiago Zarate from Quality Engineering a look into how $audience sees the engineering departments, and find out possibilities of further collaboration

How?

By running an "Ask me Anything" session, which is a format of a kind of open Q & A session, where participants ask the host multiple questions.

How to make it happen?

I'm happy to help joining a call or we can do it async (online/in person is more fun). Ping me over email-slack and lets make the magic happen!. Doesn't need to be during hackweek, but we gotta kickstart the idea during hackweek ;)

Rules

The rules are simple, the more questions the more fun it will be; while this will be only a window into engineering, it can also be the place to help all of us get to a similar level of understanding of the processes that are behind our respective areas of the organization.

Dynamics

The host will be monitoring the questions on some pre-agreed page, and try to answer to the best of their knowledge, if a question is too difficult or the host doesn't have the answer, he will do his best to provide an answer at a later date.

Atendees are encouraged to add questions beforehand; in the case there aren't any, we would be looking at how Quality Engineering tests new products or performs regression tests

Agenda

• Introduction of Santiago Zarate, Product Owner of Quality Engineering Core team
• Introduction of the Group/Team/Persons interested
• Ice breaker
• AMA time! Add your questions $PAGE
• Looking at QE Workflows: How is
  • A maintenance update being tested before being released to our customers
  • Products in development are tested before making it generally available
• Engineering Opportunity Board

---

Gen-AI chatbots and test-automation of generated responses by mdati

Description

Start experimenting the generative SUSE-AI chat bot, asking questions on different areas of knowledge or science and possibly analyze the quality of the LLM model response, specific and comparative, checking the answers provided by different LLM models to a same query, using proper quality metrics or tools or methodologies.

Try to define basic guidelines and requirements for quality test automation of AI-generated responses.

First approach of investigation can be based on manual testing: methodologies, findings and data can be useful then to organize valid automated testing.

Goals

• Identify criteria and measuring scales for assessment of a text content.
• Define quality of an answer/text based on defined criteria .
• Identify some knowledge sectors and a proper list of problems/questions per sector.
• Manually run query session and apply evaluation criteria to answers.
• Draft requirements for test automation of AI answers.

Resources

• Announcement of SUSE-AI for Hack Week in Slack
• Openplatform and related 3 LLM models gemma:2b, llama3.1:8b, qwen2.5-coder:3b.

Notes

• Foundation models (FMs):
  are large deep learning neural networks, trained on massive datasets, that have changed the way data scientists approach machine learning (ML). Rather than develop artificial intelligence (AI) from scratch, data scientists use a foundation model as a starting point to develop ML models that power new applications more quickly and cost-effectively.

• Large language models (LLMs):
  are a category of foundation models pre-trained on immense amounts of data acquiring abilities by learning statistical relationships from vast amounts of text during a self- and semi-supervised training process, making them capable of understanding and generating natural language and other types of content , to perform a wide range of tasks.
  LLMs can be used for generative AI (artificial intelligence) to produce content based on input prompts in human language.

Validation of a AI-generated answer is not an easy task to perform, as manually as automated.
An LLM answer text shall contain a given level of informations: correcness, completeness, reasoning description etc.
We shall rely in properly applicable and measurable criteria of validation to get an assessment in a limited amount of time and resources.

---

Run local LLMs with Ollama and explore possible integrations with Uyuni by PSuarezHernandez

Description

Using Ollama you can easily run different LLM models in your local computer. This project is about exploring Ollama, testing different LLMs and try to fine tune them. Also, explore potential ways of integration with Uyuni.

Goals

• Explore Ollama
• Test different models
• Fine tuning
• Explore possible integration in Uyuni

Resources

• https://ollama.com/
• https://huggingface.co/
• https://apeatling.com/articles/part-2-building-your-training-data-for-fine-tuning/

---

Use AI tools to convert legacy perl scripts to bash by nadvornik

Description

Use AI tools to convert legacy perl scripts to bash

Goals

Uyuni project contains legacy perl scripts used for setup. The perl dependency could be removed, to reduce the container size. The goal of this project is to research use of AI tools for this task.

Resources

Aider

Results:

Aider is not the right tool for this. It works ok for small changes, but not for complete rewrite from one language to another.

I got better results with direct API use from script.

---

AI for product management by a_jaeger

Description

Learn about AI and how it can help myself

What are the jobs that a PM does where AI can help - and how?

Goals

• Investigate how AI can help with different tasks
• Check out different AI tools, which one is best for which job
• Summarize learning

Resources

• Reading some blog posts by PMs that looked into it
• Popular and less popular AI tools

Work is done SUSE internally at https://confluence.suse.com/display/~a_jaeger/Hackweek+25+-+AI+for+a+PM and subpages.

---

Research how LLMs could help to Linux developers and/or users by anicka

Description

Large language models like ChatGPT have demonstrated remarkable capabilities across a variety of applications. However, their potential for enhancing the Linux development and user ecosystem remains largely unexplored. This project seeks to bridge that gap by researching practical applications of LLMs to improve workflows in areas such as backporting, packaging, log analysis, system migration, and more. By identifying patterns that LLMs can leverage, we aim to uncover new efficiencies and automation strategies that can benefit developers, maintainers, and end users alike.

Goals

• Evaluate Existing LLM Capabilities: Research and document the current state of LLM usage in open-source and Linux development projects, noting successes and limitations.
• Prototype Tools and Scripts: Develop proof-of-concept scripts or tools that leverage LLMs to perform specific tasks like automated log analysis, assisting with backporting patches, or generating packaging metadata.
• Assess Performance and Reliability: Test the tools' effectiveness on real-world Linux data and analyze their accuracy, speed, and reliability.
• Identify Best Use Cases: Pinpoint which tasks are most suitable for LLM support, distinguishing between high-impact and impractical applications.
• Document Findings and Recommendations: Summarize results with clear documentation and suggest next steps for potential integration or further development.

Resources

• Local LLM Implementations: Access to locally hosted LLMs such as LLaMA, GPT-J, or similar open-source models that can be run and fine-tuned on local hardware.
• Computing Resources: Workstations or servers capable of running LLMs locally, equipped with sufficient GPU power for training and inference.
• Sample Data: Logs, source code, patches, and packaging data from openSUSE or SUSE repositories for model training and testing.
• Public LLMs for Benchmarking: Access to APIs from platforms like OpenAI or Hugging Face for comparative testing and performance assessment.
• Existing NLP Tools: Libraries such as spaCy, Hugging Face Transformers, and PyTorch for building and interacting with local LLMs.
• Technical Documentation: Tutorials and resources focused on setting up and optimizing local LLMs for tasks relevant to Linux development.
• Collaboration: Engagement with community experts and teams experienced in AI and Linux for feedback and joint exploration.

---