nerdexam
DatabricksDatabricks

GENERATIVE-AI-ENGINEER-ASSOCIATE · Question #4

GENERATIVE-AI-ENGINEER-ASSOCIATE Question #4: Real Exam Question with Answer & Explanation

The correct answer is A: Compare the cosine similarities of the embeddings of returned results against those of a. Cosine similarity is a common metric used for evaluating the semantic accuracy of vector-based retrieval models, such as those used in LSH and HNSW indexing. By comparing the cosine similarities between the embeddings of returned results and the embeddings of a representative sam

Vector Search Performance Evaluation

Question

A Generative AI Engineer is deciding between using LSH (Locality Sensitive Hashing) and HNSW (Hierarchical Navigable Small World) for indexing their vector database. Their top priority is semantic accuracy. Which approach should the Generative AI Engineer use to evaluate these two techniques?

Options

  • ACompare the cosine similarities of the embeddings of returned results against those of a
  • BCompare the Bilingual Evaluation Understudy (BLEU) scores of returned results for a
  • CCompare the Recall-Oriented-Understudy for Gisting Evaluation (ROUGE) scores of returned
  • DCompare the Levenshtein distances of returned results against a representative sample of test

Explanation

Cosine similarity is a common metric used for evaluating the semantic accuracy of vector-based retrieval models, such as those used in LSH and HNSW indexing. By comparing the cosine similarities between the embeddings of returned results and the embeddings of a representative sample of test inputs, the Generative AI Engineer can assess how semantically accurate the results are in terms of their proximity to the correct or most relevant items.

Topics

#Vector Databases#Approximate Nearest Neighbor (ANN)#Evaluation Metrics#Semantic Search

Community Discussion

No community discussion yet for this question.

Full GENERATIVE-AI-ENGINEER-ASSOCIATE PracticeBrowse All GENERATIVE-AI-ENGINEER-ASSOCIATE Questions