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

• Evaluate data gathering and cleanup. Create sensible embeddings to be used by LLMs.
• Explore performance of Open-source llama based models (LLama, Vicuna, Mistral) in generating coherent and reasonably fast responses.
• Look into creating evaluation data for later use
• [Optional][requires beefy GPUs] Train Low Rank Adaptations (LoRA) and compare results.

Resources