llama_index.llm.completion.duration
LLM completion durationDimensions:None
Available on:
OpenTelemetry (1)
Interface Metrics (1)
Dimensions:None
Related Insights (1)
LlamaIndex Query Latency P95 Degradationwarning
LlamaIndex query response times degrade at P95/P99 percentiles due to slow LLM calls, inefficient retrieval, or tool execution bottlenecks without granular latency breakdown.
▸