向量数据库与嵌入

题集来源:AMIT SHEKHAR(amitshekhariitbhu)收录项目:ai-engineering-interview-questions查看原题集

题目目录

26 道原题
  1. What are embeddings in the context of AI engineering?

    原题
  2. How do embedding models convert text to vectors?

    原题
  3. What is Contrastive Learning, and how is it used to train embedding models?

    原题
  4. What is the difference between sparse and dense embeddings?

    原题
  5. Explain cosine similarity, dot product, and Euclidean distance for vector search.

    原题
  6. What is a vector database, and how does it differ from a traditional database?

    原题
  7. How does Approximate Nearest Neighbor (ANN) search work?

    原题
  8. Compare HNSW, IVF, and flat indexes. How do you pick one, and what does recall@k cost in latency?

    原题
  9. How does an Embedding Cache work?

    原题
  10. How do you choose the right embedding model for your use case?

    原题