Question

You maintain a RAG system for a legal research assistant. Users submit natural-language questions that frequently include specific statute citations (e.g., "Section 302(b)(2)"). Pure semantic vector search retrieves conceptually related passages but often misses documents containing the exact citation, while a keyword-only index returns the citation matches but misses paraphrased legal concepts. You have already enabled both a vector index and a keyword (BM25) index in Azure AI Search. What should you configure to maximize retrieval accuracy across both query types with a single ranked result set?

Accepted Answer

Enable hybrid search that runs vector and keyword queries in parallel and merges results using Reciprocal Rank Fusion (RRF), then apply semantic reranking to the fused list

Answer

Increase the vector search top-k to 100 so more documents are retrieved, then rely on the LLM to filter out irrelevant passages

Answer

Lower the similarity threshold on the vector index so that citation-containing documents fall within the retrieved candidate set

Answer

Replace the embedding model with a higher-dimension model to improve exact-match recall on citation strings