diff --git a/apps/api/src/services/nvidia_provider.py b/apps/api/src/services/nvidia_provider.py index ce7a5d02..21bbdfe6 100644 --- a/apps/api/src/services/nvidia_provider.py +++ b/apps/api/src/services/nvidia_provider.py @@ -747,7 +747,7 @@ class NvidiaProvider: # Prometheus NVIDIA_REQUESTS_TOTAL.labels(status="success", tool_name="chat").inc() - NVIDIA_LATENCY_SECONDS.labels(tool_name="chat").observe(latency_ms / 1000) + NVIDIA_LATENCY_HISTOGRAM.labels(tool_name="chat").observe(latency_ms / 1000) # Langfuse langfuse_ctx.trace.generation(