Generative AI: bliss or miss? by Diana Todea
GenAI is not a brand new technology yet it has become a hot topic in the last couple of years. As many organisations are adopting it within different business cases, SREs and DevOps engineers have a great deal to say about its best use cases.
This talk puts GenAI on the DevOps map, and deep dives into the GenAI applications within the DevOps/SRE realm.
In this talk, I will revisit concepts and technologies linked to GenAI such as transformers, LLMs and RAG and see them applied into observability, in particular in the shape of the AI Assistant and focus on some use cases for DevOps engineers. Whether GenAI is really a must try technology, we will understand by the end of this talk.
Talk Questions
Questions moderation
All questions have to comply with our Code of conduct. So if you don't see your question right after sending it it's because either it has not been moderated yet or it's a question that does not comply with our CoC.
Question 719
Could you please name your top 3 vector database choices?Question 720
What do you think about tools like HolmesGPT, gptscript.ai or botkube in combination with a private genAI + RAG. Which would you recommend?Question 722
Do you think that in the future, observability combined with General AI (GenAI) could allow us to create comprehensible insights to predict potential system errors without fully understanding the internal mechanics?Question 718
Do you know any good MLOps AIOps AgentSRE frameworks you can recommend?Question 721
Could you please give some examples from your experience on how much it costs to fine-tune a model?Question 724
Do you think MLOps will eventually become an integral part of DevOps rather than a specialized field?Question 723
How to pass from Langchain/Langsmith observation workflow to OpenTelemetry ?