If you are a software engineer like me who has heard about RAGs, LLM, and LLMOps, and wondering how to deploy these models on production and what the lifecycle of LLM models looks like, then you should attend this talk.
What you will gain:
- Understand the cloud-agnostic frameworks and tools in the landscape of MLOps/LLMOps.
- Learn about the purpose of inference servers for ML models and LLMs.
- Discover how to use VectorDBs.
- Find out how to run ML models and LLMs on Kubernetes.
I will talk about my experience of exploring the landscape and toolchain from my work.