a project 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/
This project is part of:
Hack Week 24
Activity
Comments
-
3 months ago by PSuarezHernandez | Reply
Some conclusions after Hackweek 24:
- ollama + open-webui is a nice combo to allow running LLMs locally (tried also Local AI)
- open-webui allows you to add custom knoweldge bases (collections) to feed models.
- Uyuni documentation, Salt documentation can be used on this collections to make models to learn.
- Using a tailored documentation works better to feed models.
- Tried different models: llama3.1, mistral, mistral-nemo, gemma2, phi3,..
- Getting promising results, particularly with
mistral-nemo.. but also getting model hallutinations - model parameters can be adjusted to reduce them.
Takeaways
- Small models runs fairly well with CPU only.
- Making an expert assistance on Uyuni, with an extensive knowledge based on documentation, might be something to keep exploring.
Next steps
- Make the model to understand Uyuni API, so it is able to translate user requests to actual call to Uyuni API.
Similar Projects
Enable the containerized Uyuni server to run on different host OS by j_renner
Description
The Uyuni server is provided as a container, but we still require it to run on Leap Micro? This is not how people expect to use containerized applications, so it would be great if we tested other host OSs and enabled them by providing builds of necessary tools for (e.g. mgradm). Interesting candidates should be:
- openSUSE Leap
- Cent OS 7
- Ubuntu
- ???
Goals
Make it really easy for anyone to run the Uyuni containerized server on whatever OS they want (with support for containers of course).
Improve Development Environment on Uyuni by mbussolotto
Description
Currently create a dev environment on Uyuni might be complicated. The steps are:
- add the correct repo
- download packages
- configure your IDE (checkstyle, format rules, sonarlint....)
- setup debug environment
- ...
The current doc can be improved: some information are hard to be find out, some others are completely missing.
Dev Container might solve this situation.
Goals
Uyuni development in no time:
- using VSCode:
- setting.json should contains all settings (for all languages in Uyuni, with all checkstyle rules etc...)
- dev container should contains all dependencies
- setup debug environment
- implement a GitHub Workspace solution
- re-write documentation
Lots of pieces are already implemented: we need to connect them in a consistent solution.
Resources
- https://github.com/uyuni-project/uyuni/wiki
Uyuni developer-centric documentation by deneb_alpha
Description
While we currently have extensive documentation on user-oriented tasks such as adding minions, patching, fine-tuning, etc, there is a notable gap when it comes to centralizing and documenting core functionalities for developers.
The number of functionalities and side tools we have in Uyuni can be overwhelming. It would be nice to have a centralized place with descriptive list of main/core functionalities.
Goals
Create, aggregate and review on the Uyuni wiki a set of resources, focused on developers, that include also some known common problems/troubleshooting.
The documentation will be helpful not only for everyone who is trying to learn the functionalities with all their inner processes like newcomer developers or community enthusiasts, but also for anyone who need a refresh.
Resources
The resources are currently aggregated here: https://github.com/uyuni-project/uyuni/wiki
Install Uyuni on Kubernetes in cloud-native way by cbosdonnat
Description
For now installing Uyuni on Kubernetes requires running mgradm on a cluster node... which is not what users would do in the Kubernetes world. The idea is to implement an installation based only on helm charts and probably an operator.
Goals
Install Uyuni from Rancher UI.
Resources
mgradmcode: https://github.com/uyuni-project/uyuni-tools- Uyuni operator: https://github.com/cbosdo/uyuni-operator
Edge Image Builder and mkosi for Uyuni by oholecek
Description
One part of Uyuni system management tool is ability to build custom images. Currently Uyuni supports only Kiwi image builder.
Kiwi however is not the only image building system out there and with the goal to also become familiar with other systems, this projects aim to add support for Edge Image builder and systemd's mkosi systems.
Goals
Uyuni is able to
- provision EIB and mkosi build hosts
- build EIB and mkosi images and store them
Resources
- Uyuni - https://github.com/uyuni-project/uyuni
- Edge Image builder - https://github.com/suse-edge/edge-image-builder
- mkosi - https://github.com/systemd/mkosi
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
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.
Use local/private LLM for semantic knowledge search by digitaltomm
Description
Use a local LLM, based on SUSE AI (ollama, openwebui) to power geeko search (public instance: https://geeko.port0.org/).
Goals
Build a SUSE internal instance of https://geeko.port0.org/ that can operate on internal resources, crawling confluence.suse.com, gitlab.suse.de, etc.
Resources
Repo: https://github.com/digitaltom/semantic-knowledge-search
Public instance: https://geeko.port0.org/
Results
Internal instance:
I have an internal test instance running which has indexed a couple of internal wiki pages from the SCC team. It's using the ollama (llama3.1:8b) backend of suse-ai.openplatform.suse.com to create embedding vectors for indexed resources and to create a chat response. The semantic search for documents is done with a vector search inside of sqlite, using sqlite-vec.
Learn how to integrate Elixir and Phoenix Liveview with LLMs by ninopaparo
Description
Learn how to integrate Elixir and Phoenix Liveview with LLMs by building an application that can provide answers to user queries based on a corpus of custom-trained data.
Goals
Develop an Elixir application via the Phoenix framework that:
- Employs Retrieval Augmented Generation (RAG) techniques
- Supports the integration and utilization of various Large Language Models (LLMs).
- Is designed with extensibility and adaptability in mind to accommodate future enhancements and modifications.
Resources
- https://elixir-lang.org/
- https://www.phoenixframework.org/
- https://github.com/elixir-nx/bumblebee
- https://ollama.com/
SUSE AI Meets the Game Board by moio
Use tabletopgames.ai’s open source TAG and PyTAG frameworks to apply Statistical Forward Planning and Deep Reinforcement Learning to two board games of our own design. On an all-green, all-open source, all-AWS stack!
Results: Infrastructure Achievements
We successfully built and automated a containerized stack to support our AI experiments. This included:
- a Fully-Automated, One-Command, GPU-accelerated Kubernetes setup: we created an OpenTofu based script, tofu-tag, to deploy SUSE's RKE2 Kubernetes running on CUDA-enabled nodes in AWS, powered by openSUSE with GPU drivers and gpu-operator
- Containerization of the TAG and PyTAG frameworks: TAG (Tabletop AI Games) and PyTAG were patched for seamless deployment in containerized environments. We automated the container image creation process with GitHub Actions. Our forks (PRs upstream upcoming):
./deploy.sh and voilà - Kubernetes running PyTAG (k9s, above) with GPU acceleration (nvtop, below)
Results: Game Design Insights
Our project focused on modeling and analyzing two card games of our own design within the TAG framework:
- Game Modeling: We implemented models for Dario's "Bamboo" and Silvio's "Totoro" and "R3" games, enabling AI agents to play thousands of games ...in minutes!
- AI-driven optimization: By analyzing statistical data on moves, strategies, and outcomes, we iteratively tweaked the game mechanics and rules to achieve better balance and player engagement.
- Advanced analytics: Leveraging AI agents with Monte Carlo Tree Search (MCTS) and random action selection, we compared performance metrics to identify optimal strategies and uncover opportunities for game refinement .
- more about Bamboo on Dario's site
- more about R3 on Silvio's site (italian, translation coming)
- more about Totoro on Silvio's site
A family picture of our card games in progress. From the top: Bamboo, Totoro, R3
Results: Learning, Collaboration, and Innovation
Beyond technical accomplishments, the project showcased innovative approaches to coding, learning, and teamwork:
- "Trio programming" with AI assistance: Our "trio programming" approach—two developers and GitHub Copilot—was a standout success, especially in handling slightly-repetitive but not-quite-exactly-copypaste tasks. Java as a language tends to be verbose and we found it to be fitting particularly well.
- AI tools for reporting and documentation: We extensively used AI chatbots to streamline writing and reporting. (Including writing this report! ...but this note was added manually during edit!)
- GPU compute expertise: Overcoming challenges with CUDA drivers and cloud infrastructure deepened our understanding of GPU-accelerated workloads in the open-source ecosystem.
- Game design as a learning platform: By blending AI techniques with creative game design, we learned not only about AI strategies but also about making games fun, engaging, and balanced.
Last but not least we had a lot of fun! ...and this was definitely not a chatbot generated line!
The Context: AI + Board Games
Testing and adding GNU/Linux distributions on Uyuni by juliogonzalezgil
Join the Gitter channel! https://gitter.im/uyuni-project/hackweek
Uyuni is a configuration and infrastructure management tool that saves you time and headaches when you have to manage and update tens, hundreds or even thousands of machines. It also manages configuration, can run audits, build image containers, monitor and much more!
Currently there are a few distributions that are completely untested on Uyuni or SUSE Manager (AFAIK) or just not tested since a long time, and could be interesting knowing how hard would be working with them and, if possible, fix whatever is broken.
For newcomers, the easiest distributions are those based on DEB or RPM packages. Distributions with other package formats are doable, but will require adapting the Python and Java code to be able to sync and analyze such packages (and if salt does not support those packages, it will need changes as well). So if you want a distribution with other packages, make sure you are comfortable handling such changes.
No developer experience? No worries! We had non-developers contributors in the past, and we are ready to help as long as you are willing to learn. If you don't want to code at all, you can also help us preparing the documentation after someone else has the initial code ready, or you could also help with testing :-)
The idea is testing Salt and Salt-ssh clients, but NOT traditional clients, which are deprecated.
To consider that a distribution has basic support, we should cover at least (points 3-6 are to be tested for both salt minions and salt ssh minions):
- Reposync (this will require using spacewalk-common-channels and adding channels to the .ini file)
- Onboarding (salt minion from UI, salt minion from bootstrap scritp, and salt-ssh minion) (this will probably require adding OS to the bootstrap repository creator)
- Package management (install, remove, update...)
- Patching
- Applying any basic salt state (including a formula)
- Salt remote commands
- Bonus point: Java part for product identification, and monitoring enablement
- Bonus point: sumaform enablement (https://github.com/uyuni-project/sumaform)
- Bonus point: Documentation (https://github.com/uyuni-project/uyuni-docs)
- Bonus point: testsuite enablement (https://github.com/uyuni-project/uyuni/tree/master/testsuite)
If something is breaking: we can try to fix it, but the main idea is research how supported it is right now. Beyond that it's up to each project member how much to hack :-)
- If you don't have knowledge about some of the steps: ask the team
- If you still don't know what to do: switch to another distribution and keep testing.
This card is for EVERYONE, not just developers. Seriously! We had people from other teams helping that were not developers, and added support for Debian and new SUSE Linux Enterprise and openSUSE Leap versions :-)
Pending
FUSS
FUSS is a complete GNU/Linux solution (server, client and desktop/standalone) based on Debian for managing an educational network.
https://fuss.bz.it/
Seems to be a Debian 12 derivative, so adding it could be quite easy.
[W]Reposync (this will require using spacewalk-common-channels and adding channels to the .ini file)[W]Onboarding (salt minion from UI, salt minion from bootstrap script, and salt-ssh minion) (this will probably require adding OS to the bootstrap repository creator) --> Working for all 3 options (salt minion UI, salt minion bootstrap script and salt-ssh minion from the UI).[W]Package management (install, remove, update...) --> Installing a new package works, needs to test the rest.[I]Patching (if patch information is available, could require writing some code to parse it, but IIRC we have support for Ubuntu already). No patches detected. Do we support patches for Debian at all?[W]Applying any basic salt state (including a formula)[W]Salt remote commands[ ]Bonus point: Java part for product identification, and monitoring enablement
Team Hedgehogs' Data Observability Dashboard by gsamardzhiev
Description
This project aims to develop a comprehensive Data Observability Dashboard that provides r insights into key aspects of data quality and reliability. The dashboard will track:
Data Freshness: Monitor when data was last updated and flag potential delays.
Data Volume: Track table row counts to detect unexpected surges or drops in data.
Data Distribution: Analyze data for null values, outliers, and anomalies to ensure accuracy.
Data Schema: Track schema changes over time to prevent breaking changes.
The dashboard's aim is to support historical tracking to support proactive data management and enhance data trust across the data function.
Goals
Although the final goal is to create a power bi dashboard that we are able to monitor, our goals is to 1. Create the necessary tables that track the relevant metadata about our current data 2. Automate the process so it runs in a timely manner
Resources
AWS Redshift; AWS Glue, Airflow, Python, SQL
Why Hedgehogs?
Because we like them.
Make more sense of openQA test results using AI by livdywan
Description
AI has the potential to help with something many of us spend a lot of time doing which is making sense of openQA logs when a job fails.
User Story
Allison Average has a puzzled look on their face while staring at log files that seem to make little sense. Is this a known issue, something completely new or maybe related to infrastructure changes?
Goals
- Leverage a chat interface to help Allison
- Create a model from scratch based on data from openQA
- Proof of concept for automated analysis of openQA test results
Bonus
- Use AI to suggest solutions to merge conflicts
- This would need a merge conflict editor that can suggest solving the conflict
- Use image recognition for needles
Resources
Timeline
Day 1
- Conversing with open-webui to teach me how to create a model based on openQA test results
- Asking for example code using TensorFlow in Python
- Discussing log files to explore what to analyze
- Drafting a new project called Testimony (based on Implementing a containerized Python action) - the project name was also suggested by the assistant
Day 2
- Using NotebookLLM (Gemini) to produce conversational versions of blog posts
- Researching the possibility of creating a project logo with AI
- Asking open-webui, persons with prior experience and conducting a web search for advice
Highlights
- I briefly tested compared models to see if they would make me more productive. Between llama, gemma and mistral there was no amazing difference in the results for my case.
- Convincing the chat interface to produce code specific to my use case required very explicit instructions.
- Asking for advice on how to use open-webui itself better was frustratingly unfruitful both in trivial and more advanced regards.
- Documentation on source materials used by LLM's and tools for this purpose seems virtually non-existent - specifically if a logo can be generated based on particular licenses
Outcomes
- Chat interface-supported development is providing good starting points and open-webui being open source is more flexible than Gemini. Although currently some fancy features such as grounding and generated podcasts are missing.
- Allison still has to be very experienced with openQA to use a chat interface for test review. Publicly available system prompts would make that easier, though.
Saline (state deployment control and monitoring tool for SUSE Manager/Uyuni) by vizhestkov
Project Description
Saline is an addition for salt used in SUSE Manager/Uyuni aimed to provide better control and visibility for states deploymend in the large scale environments.
In current state the published version can be used only as a Prometheus exporter and missing some of the key features implemented in PoC (not published). Now it can provide metrics related to salt events and state apply process on the minions. But there is no control on this process implemented yet.
Continue with implementation of the missing features and improve the existing implementation:
authentication (need to decide how it should be/or not related to salt auth)
web service providing the control of states deployment
Goal for this Hackweek
Implement missing key features
Implement the tool for state deployment control with CLI
Resources
https://github.com/openSUSE/saline
Learn how to integrate Elixir and Phoenix Liveview with LLMs by ninopaparo
Description
Learn how to integrate Elixir and Phoenix Liveview with LLMs by building an application that can provide answers to user queries based on a corpus of custom-trained data.
Goals
Develop an Elixir application via the Phoenix framework that:
- Employs Retrieval Augmented Generation (RAG) techniques
- Supports the integration and utilization of various Large Language Models (LLMs).
- Is designed with extensibility and adaptability in mind to accommodate future enhancements and modifications.
Resources
- https://elixir-lang.org/
- https://www.phoenixframework.org/
- https://github.com/elixir-nx/bumblebee
- https://ollama.com/
Save pytorch models in OCI registries by jguilhermevanz
Description
A prerequisite for running applications in a cloud environment is the presence of a container registry. Another common scenario is users performing machine learning workloads in such environments. However, these types of workloads require dedicated infrastructure to run properly. We can leverage these two facts to help users save resources by storing their machine learning models in OCI registries, similar to how we handle some WebAssembly modules. This approach will save users the resources typically required for a machine learning model repository for the applications they need to run.
Goals
Allow PyTorch users to save and load machine learning models in OCI registries.
Resources
SUSE AI Meets the Game Board by moio
Use tabletopgames.ai’s open source TAG and PyTAG frameworks to apply Statistical Forward Planning and Deep Reinforcement Learning to two board games of our own design. On an all-green, all-open source, all-AWS stack!
Results: Infrastructure Achievements
We successfully built and automated a containerized stack to support our AI experiments. This included:
- a Fully-Automated, One-Command, GPU-accelerated Kubernetes setup: we created an OpenTofu based script, tofu-tag, to deploy SUSE's RKE2 Kubernetes running on CUDA-enabled nodes in AWS, powered by openSUSE with GPU drivers and gpu-operator
- Containerization of the TAG and PyTAG frameworks: TAG (Tabletop AI Games) and PyTAG were patched for seamless deployment in containerized environments. We automated the container image creation process with GitHub Actions. Our forks (PRs upstream upcoming):
./deploy.sh and voilà - Kubernetes running PyTAG (k9s, above) with GPU acceleration (nvtop, below)
Results: Game Design Insights
Our project focused on modeling and analyzing two card games of our own design within the TAG framework:
- Game Modeling: We implemented models for Dario's "Bamboo" and Silvio's "Totoro" and "R3" games, enabling AI agents to play thousands of games ...in minutes!
- AI-driven optimization: By analyzing statistical data on moves, strategies, and outcomes, we iteratively tweaked the game mechanics and rules to achieve better balance and player engagement.
- Advanced analytics: Leveraging AI agents with Monte Carlo Tree Search (MCTS) and random action selection, we compared performance metrics to identify optimal strategies and uncover opportunities for game refinement .
- more about Bamboo on Dario's site
- more about R3 on Silvio's site (italian, translation coming)
- more about Totoro on Silvio's site
A family picture of our card games in progress. From the top: Bamboo, Totoro, R3
Results: Learning, Collaboration, and Innovation
Beyond technical accomplishments, the project showcased innovative approaches to coding, learning, and teamwork:
- "Trio programming" with AI assistance: Our "trio programming" approach—two developers and GitHub Copilot—was a standout success, especially in handling slightly-repetitive but not-quite-exactly-copypaste tasks. Java as a language tends to be verbose and we found it to be fitting particularly well.
- AI tools for reporting and documentation: We extensively used AI chatbots to streamline writing and reporting. (Including writing this report! ...but this note was added manually during edit!)
- GPU compute expertise: Overcoming challenges with CUDA drivers and cloud infrastructure deepened our understanding of GPU-accelerated workloads in the open-source ecosystem.
- Game design as a learning platform: By blending AI techniques with creative game design, we learned not only about AI strategies but also about making games fun, engaging, and balanced.
Last but not least we had a lot of fun! ...and this was definitely not a chatbot generated line!
The Context: AI + Board Games
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.
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.