SUSE Hack Week: Create language model based on Uyuni documentation

Project Description

The goal is to have a language model, that is able to answer technical questions on Uyuni. Uyuni documentation is too large for in-context processing, so finetuning is the way to go.

Goal for this Hackweek

Finetune a model based on llama-2-7b.

Resources

github repo

No Hackers yet

Join this project Leave this project

Looking for hackers with the skills:

ai uyuni

This project is part of:

Hack Week 23

Activity

about 2 years ago: nadvornik added keyword "ai" to this project.

about 2 years ago: nadvornik added keyword "uyuni" to this project.

about 2 years ago: nadvornik originated this project.

Comments

Be the first to comment!

Similar Projects

ai

Song Search with CLAP by gcolangiuli

Description

Contrastive Language-Audio Pretraining (CLAP) is an open-source library that enables the training of a neural network on both Audio and Text descriptions, making it possible to search for Audio using a Text input. Several pre-trained models for song search are already available on huggingface

Goals

Evaluate how CLAP can be used for song searching and determine which types of queries yield the best results by developing a Minimum Viable Product (MVP) in Python. Based on the results of this MVP, future steps could include:

Music Tagging;
Free text search;
Integration with an LLM (for example, with MCP or the OpenAI API) for music suggestions based on your own library.

The code for this project will be entirely written using AI to better explore and demonstrate AI capabilities.

Result

In this MVP we implemented:

Async Song Analysis with Clap model
Free Text Search of the songs
Similar song search based on vector representation
Containerised version with web interface

We also documented what went well and what can be improved in the use of AI.

You can have a look at the result here:

Future implementation can be related to performance improvement and stability of the analysis.

References

CLAP: The main model being researched;
huggingface: Pre-trained models for CLAP;
Free Music Archive: Creative Commons songs that can be used for testing;

AI-Powered Unit Test Automation for Agama by joseivanlopez

The Agama project is a multi-language Linux installer that leverages the distinct strengths of several key technologies:

Rust: Used for the back-end services and the core HTTP API, providing performance and safety.
TypeScript (React/PatternFly): Powers the modern web user interface (UI), ensuring a consistent and responsive user experience.
Ruby: Integrates existing, robust YaST libraries (e.g., yast-storage-ng) to reuse established functionality.

The Problem: Testing Overhead

Developing and maintaining code across these three languages requires a significant, tedious effort in writing, reviewing, and updating unit tests for each component. This high cost of testing is a drain on developer resources and can slow down the project's evolution.

The Solution: AI-Driven Automation

This project aims to eliminate the manual overhead of unit testing by exploring and integrating AI-driven code generation tools. We will investigate how AI can:

Automatically generate new unit tests as code is developed.
Intelligently correct and update existing unit tests when the application code changes.

By automating this crucial but monotonous task, we can free developers to focus on feature implementation and significantly improve the speed and maintainability of the Agama codebase.

Goals

Proof of Concept: Successfully integrate and demonstrate an authorized AI tool (e.g., gemini-cli) to automatically generate unit tests.
Workflow Integration: Define and document a new unit test automation workflow that seamlessly integrates the selected AI tool into the existing Agama development pipeline.
Knowledge Sharing: Establish a set of best practices for using AI in code generation, sharing the learned expertise with the broader team.

Contribution & Resources

We are seeking contributors interested in AI-powered development and improving developer efficiency. Whether you have previous experience with code generation tools or are eager to learn, your participation is highly valuable.

If you want to dive deep into AI for software quality, please reach out and join the effort!

Authorized AI Tools: Tools supported by SUSE (e.g., gemini-cli)
Focus Areas: Rust, TypeScript, and Ruby components within the Agama project.

Interesting Links

goose

Enable more features in mcp-server-uyuni by j_renner

Description

I would like to contribute to mcp-server-uyuni, the MCP server for Uyuni / Multi-Linux Manager) exposing additional features as tools. There is lots of relevant features to be found throughout the API, for example:

At the end of the week I managed to enable basic system group operations:

List all system groups visible to the user
Create new system groups
List systems assigned to a group
Add and remove systems from groups

Goals

Set up test environment locally with the MCP server and client + a recent MLM server [DONE]
Identify features and use cases offering a benefit with limited effort required for enablement [DONE]
Create a PR to the repo [DONE]

Resources

Try AI training with ROCm and LoRA by bmwiedemann

Description

I want to setup a Radeon RX 9600 XT 16 GB at home with ROCm on Slowroll.

Goals

I want to test how fast AI inference can get with the GPU and if I can use LoRA to re-train an existing free model for some task.

Resources

https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html
https://build.opensuse.org/project/show/science:GPU:ROCm
https://src.opensuse.org/ROCm/
https://www.suse.com/c/lora-fine-tuning-llms-for-text-classification/

Results

got inference working with llama.cpp:

export LLAMACPP_ROCM_ARCH=gfx1200
HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$LLAMACPP_ROCM_ARCH \
-DCMAKE_BUILD_TYPE=Release -DLLAMA_CURL=ON \
-Dhipblas_DIR=/usr/lib64/cmake/hipblaslt/ \
&amp;&amp; cmake --build build --config Release -j8
m=models/gpt-oss-20b-mxfp4.gguf
cd $P/llama.cpp &amp;&amp; build/bin/llama-server --model $m --threads 8 --port 8005 --host 0.0.0.0 --device ROCm0 --n-gpu-layers 999

Without the --device option it faulted. Maybe because my APU also appears there?

I updated/fixed various related packages: https://src.opensuse.org/ROCm/rocm-examples/pulls/1 https://src.opensuse.org/ROCm/hipblaslt/pulls/1 SR 1320959

benchmark

I benchmarked inference with llama.cpp + gpt-oss-20b-mxfp4.gguf and ROCm offloading to a Radeon RX 9060 XT 16GB. I varied the number of layers that went to the GPU:

0 layers 14.49 tokens/s (8 CPU cores)
9 layers 17.79 tokens/s 34% VRAM
15 layers 22.39 tokens/s 51% VRAM
20 layers 27.49 tokens/s 64% VRAM
24 layers 41.18 tokens/s 74% VRAM
25+ layers 86.63 tokens/s 75% VRAM (only 200% CPU load)

So there is a significant performance-boost if the whole model fits into the GPU's VRAM.

"what is it" file and directory analysis via MCP and local LLM, for console and KDE by rsimai

Description

Users sometimes wonder what files or directories they find on their local PC are good for. If they can't determine from the filename or metadata, there should an easy way to quickly analyze the content and at least guess the meaning. An LLM could help with that, through the use of a filesystem MCP and to-text-converters for typical file types. Ideally this is integrated into the desktop environment but works as well from a console. All data is processed locally or "on premise", no artifacts remain or leave the system.

Goals

The user can run a command from the console, to check on a file or directory
The filemanager contains the "analyze" feature within the context menu
The local LLM could serve for other use cases where privacy matters

TBD

Find or write capable one-shot and interactive MCP client
Find or write simple+secure file access MCP server
Create local LLM service with appropriate footprint, containerized
Shell command with options
KDE integration (Dolphin)
Package
Document

Resources

uyuni

Uyuni Saltboot rework by oholecek

Description

When Uyuni switched over to the containerized proxies we had to abandon salt based saltboot infrastructure we had before. Uyuni already had integration with a Cobbler provisioning server and saltboot infra was re-implemented on top of this Cobbler integration.

What was not obvious from the start was that Cobbler, having all it's features, woefully slow when dealing with saltboot size environments. We did some improvements in performance, introduced transactions, and generally tried to make this setup usable. However the underlying slowness remained.

Goals

This project is not something trying to invent new things, it is just finally implementing saltboot infrastructure directly with the Uyuni server core.

Instead of generating grub and pxelinux configurations by Cobbler for all thousands of systems and branches, we will provide a GET access point to retrieve grub or pxelinux file during the boot:

/saltboot/group/grub/$fqdn and similar for systems /saltboot/system/grub/$mac

Next we adapt our tftpd translator to query these points when asked for default or mac based config.

Lastly similar thing needs to be done on our apache server when HTTP UEFI boot is used.

Resources

mgr-ansible-ssh - Intelligent, Lightweight CLI for Distributed Remote Execution by deve5h

Description

By the end of Hack Week, the target will be to deliver a minimal functional version 1 (MVP) of a custom command-line tool named mgr-ansible-ssh (a unified wrapper for BOTH ad-hoc shell & playbooks) that allows operators to:

Execute arbitrary shell commands on thousand of remote machines simultaneously using Ansible Runner with artifacts saved locally.
Pass runtime options such as inventory file, remote command string/ playbook execution, parallel forks, limits, dry-run mode, or no-std-ansible-output.
Leverage existing SSH trust relationships without additional setup.
Provide a clean, intuitive CLI interface with --help for ease of use. It should provide consistent UX & CI-friendly interface.
Establish a foundation that can later be extended with advanced features such as logging, grouping, interactive shell mode, safe-command checks, and parallel execution tuning.

The MVP should enable day-to-day operations to efficiently target thousands of machines with a single, consistent interface.

Goals

Primary Goals (MVP):

Build a functional CLI tool (mgr-ansible-ssh) capable of executing shell commands on multiple remote hosts using Ansible Runner. Test the tool across a large distributed environment (1000+ machines) to validate its performance and reliability.

Looking forward to significantly reducing the zypper deployment time across all 351 RMT VM servers in our MLM cluster by eliminating the dependency on the taskomatic service, bringing execution down to a fraction of the current duration. The tool should also support multiple runtime flags, such as:

mgr-ansible-ssh: Remote command execution wrapper using Ansible Runner

Usage: mgr-ansible-ssh [--help] [--version] [--inventory INVENTORY]
                   [--run RUN] [--playbook PLAYBOOK] [--limit LIMIT]
                   [--forks FORKS] [--dry-run] [--no-ansible-output]

Required Arguments
--inventory, -i      Path to Ansible inventory file to use

Any One of the Arguments Is Required
--run, -r            Execute the specified shell command on target hosts
--playbook, -p       Execute the specified Ansible playbook on target hosts

Optional Arguments
--help, -h           Show the help message and exit
--version, -v        Show the version and exit
--limit, -l          Limit execution to specific hosts or groups
--forks, -f          Number of parallel Ansible forks
--dry-run            Run in Ansible check mode (requires -p or --playbook)
--no-ansible-output  Suppress Ansible stdout output

Secondary/Stretched Goals (if time permits):

Add pretty output formatting (success/failure summary per host).
Implement basic logging of executed commands and results.
Introduce safety checks for risky commands (shutdown, rm -rf, etc.).
Package the tool so it can be installed with pip or stored internally.

Resources

Collaboration is welcome from anyone interested in CLI tooling, automation, or distributed systems. Skills that would be particularly valuable include:

Python especially around CLI dev (argparse, click, rich)

Enhance setup wizard for Uyuni by PSuarezHernandez

Description

This project wants to enhance the intial setup on Uyuni after its installation, so it's easier for a user to start using with it.

Uyuni currently uses "uyuni-tools" (mgradm) as the installation entrypoint, to trigger the installation of Uyuni in the given host, but does not really perform an initial setup, for instance:

user creation
adding products / channels
generating bootstrap repos
create activation keys
...

Goals

Provide initial setup wizard as part of mgradm uyuni installation

Resources

Move Uyuni Test Framework from Selenium to Playwright + AI by oscar-barrios

Description

This project aims to migrate the existing Uyuni Test Framework from Selenium to Playwright. The move will improve the stability, speed, and maintainability of our end-to-end tests by leveraging Playwright's modern features. We'll be rewriting the current Selenium code in Ruby to Playwright code in TypeScript, which includes updating the test framework runner, step definitions, and configurations. This is also necessary because we're moving from Cucumber Ruby to CucumberJS.

If you're still curious about the AI in the title, it was just a way to grab your attention. Thanks for your understanding.

Nah, let's be honest AI helped a lot to vibe code a good part of the Ruby methods of the Test framework, moving them to Typescript, along with the migration from Capybara to Playwright. I've been using "Cline" as plugin for WebStorm IDE, using Gemini API behind it.

Goals

Migrate Core tests including Onboarding of clients
Improve test reliabillity: Measure and confirm a significant reduction of flakiness.
Implement a robust framework: Establish a well-structured and reusable Playwright test framework using the CucumberJS

Resources

Enable more features in mcp-server-uyuni by j_renner

Description

At the end of the week I managed to enable basic system group operations:

List all system groups visible to the user
Create new system groups
List systems assigned to a group
Add and remove systems from groups

Goals

Set up test environment locally with the MCP server and client + a recent MLM server [DONE]
Identify features and use cases offering a benefit with limited effort required for enablement [DONE]
Create a PR to the repo [DONE]