llama_index.retrieval.duration

LlamaIndex query response times degrade at P95/P99 percentiles due to slow LLM calls, inefficient retrieval, or tool execution bottlenecks without granular latency breakdown.

LlamaIndex retrieval returns insufficient or irrelevant documents, degrading answer quality due to poor index coverage, misconfigured similarity thresholds, or index staleness.

Query engine failures prevent users from receiving answers due to LLM API errors, retrieval failures, or agent execution errors without proper error handling and fallback mechanisms.