LLMs and RAG

Once model access is in place, these tutorials take you from a deployed model to a working application. First you deploy a model on DKubeX with Model Studio and bring it to a running state; then you build a retrieval-augmented (RAG) assistant that grounds its answers in your own documents instead of relying on the model’s training data alone.

Start here if you want to stand up a model and put a question-answering application in front of it.

• Deploying Models on DKubeX Using Model Studio
• Building a Legal Contract Q&A Assistant on DKubeX