You are troubleshooting a RAG application in Azure AI Foundry where retrieved search results are irrelevant to user queries. Which THREE actions should you take to diagnose and improve retrieval quality? (Choose THREE)
Trap 1: Increase the Azure OpenAI model temperature parameter to 1.5
Temperature controls generative output randomness, not document retrieval quality.
Trap 2: Configure Azure Key Vault access policies for the search service
Key Vault access manages cryptographic keys, not search relevance.
- A
Evaluate whether document chunk sizes and overlaps align with query granularity
Poor chunking sizes can split vital context or bundle unrelated topics, ruining retrieval precision.
- B
Inspect embedding vector distances and similarity scores of retrieved documents
Checking similarity scores helps determine if embeddings accurately represent query-document semantic closeness.
- C
Increase the Azure OpenAI model temperature parameter to 1.5
Why wrong: Temperature controls generative output randomness, not document retrieval quality.
- D
Configure Azure Key Vault access policies for the search service
Why wrong: Key Vault access manages cryptographic keys, not search relevance.
- E
Enable semantic ranking in Azure AI Search to re-rank results based on deep language understanding
Semantic ranking significantly improves search precision by re-ranking initial results using advanced AI models.