MLOps Table of Contents AI as a Service: simple AI-based service with serverless (AWS Lambda) AWS Lambda invoke sagemaker with aws lambda SageMaker SageMaker HuggingFace toolkits SageMaker serverless inference Data Management DVC Kubernetes Basic examples Troubleshootings minikube troubleshooting LLM large language models document oriented agent with openai api function callings - make LLM to use tools RAG peft fsdp_qlora llama_index TensorLLM prompt engineering leaked-system-prompts: leaked system prompts of actual LLM-based services source codes and notebooks for learning prompt engineering with openai ML serving bento-ml build ML pipelines with Nvidia Triton Server serving ML models with fastapi serving ML models with flask ray Serve GPT-2 pipeline with Ray-serve and FastAPI Serve GPT-J-6B model with Ray-AIR GPU Recommendations