Embeddings and Vector Search Quiz

What you'll be asked

1. What is the primary purpose of an embedding in the context of Large Language Models?
2. When implementing a Retrieval-Augmented Generation (RAG) pattern, why is a vector database used?
3. Which metric is commonly used to measure the similarity between two embedding vectors in Azure AI Search?
4. In the context of Azure OpenAI, what happens if you try to compare embeddings generated by two different embedding models (e.g., text-embedding-ada-002 vs text-embedding-3-small)?
5. When designing a vector search architecture for a large document repository, what is the impact of choosing a higher number of dimensions in your embedding model?

Answers and explanations come after you submit.