The current process of identifying the root cause of a package build failure in Copr or Koji is time-consuming and requires considerable expertise. Log Detective proposes an automated log analysis system to help diagnose such failures and assist maintainers.

Log Detective uses Template Mining and Large Language Models to process your log files. It’s very simple to use, just go to https://logdetective.com/explain, paste a link to your log file, wait one minute and the service will explain that log to you.

Existing models like granite, llama, or mistral can give good feedback on your logs, but they don't understand our specific ecosystem. We are collecting log annotations to train our own models under the CDLA-Permissive-2.0 license. Our aim is to create a service that provides near-perfect explanations and solutions, as if an experienced maintainer was guiding you.

In this talk, we’ll give you an overview of Log Detective, explain the technical decisions and finish with a demo. You shouldn’t miss this talk if you are building software as your job.

Meet the representatives of various AI projects and initiatives from the region! Learn about Red Hat AI projects, customers leveraging AI for their solutions and university activities shaping the AI future. Listen to the experts involved in global initiatives but also the representatives of local efforts and communities.

• Patrik Plachy - Senior Solution Architect with focus on Red Hat AI portfolio
• Marek Grac - Senior Software Engineer and researcher with focus on AI and Machine learning
• Vladimír Kadlec - Principal Data Scientist at Red Hat
• Karel Piwko - Senior Principal Software Engineer with focus on DevOps tools and practices enhanced by AI
• Tomas Tomecek - Senior Principal Software Engineer with focus on AI tools and AI enabled CI/CD tools