What are the two main techniques used by ScaNN (Scalable Approximate Nearest Neighbor) to improve search performance in vector search?Cosine distance and Manhattan distanceSpace pruning and data quantizationBrute force search and approximate nearest neighbor searchDimensionality reduction and indexing

What are the two main technical challenges that need to be addressed in order to implement vector search effectively?Encoding and indexingUser adoption and costEfficiency and personalizationHallucination and grounding

What is the main purpose of using distance metrics like dot product distance in vector search?Measure the distance between vectors in terms of semantic similarity.Index vectors efficiently in the search space.Generate new vectors from existing ones.Search for the top three nearest neighbors of a query vector.

Which distance metric is commonly used in k-Nearest Neighbors (KNN) for numerical data?a.Cosine similarityb.Jaccard distancec.Euclidean distanced.Hamming distance

Which distance metric is commonly used in k-Nearest Neighbors (KNN) for numerical data?a.Euclidean distanceb.Hamming distancec.Cosine similarityd.Jaccard distance

Which of the following is not one of the general approaches to search algorithms:Question 1Select one:a.Buffer cache access methodsb.Sequential and list methodsc.Direct access by key value (hashing)d.Tree indexing methods