Question

Your team runs a RAG-based support assistant on Azure AI Foundry. Users complain that answers frequently include irrelevant passages that dilute accuracy, even though the correct passages are almost always retrieved. Offline evaluation confirms high retrieval recall but low precision, and many low-scoring chunks are being passed into the prompt context. You must reduce the inclusion of weakly related chunks while preserving the strong retrieval recall you already have. What is the most appropriate first tuning action?

Accepted Answer

Raise the minimum similarity score threshold so that only chunks above a higher relevance score are passed into the prompt context.

Answer

Increase the top-k value so that more candidate chunks are retrieved for each query.

Answer

Reduce the chunk size and overlap so each chunk contains less text.

Answer

Switch the vector index distance metric from cosine similarity to Euclidean distance.