Question

You operate a RAG-based support assistant on Azure AI Foundry. Evaluation shows the assistant frequently misses relevant policy details that exist in the knowledge base (low answer completeness), yet groundedness scores remain acceptable. The retrieval pipeline currently returns the top 3 chunks per query using pure vector search. You need to improve completeness without significantly degrading groundedness or latency. Which change should you make FIRST?

Accepted Answer

Increase the number of retrieved chunks (top_k) and re-evaluate relevance and groundedness metrics on your test set.

Answer

Lower the model temperature so responses adhere more strictly to retrieved context.

Answer

Raise the similarity threshold so only the highest-scoring chunks are returned.

Answer

Switch the deployment from serverless to provisioned throughput units to reduce retrieval latency.