fix(nvidia): avoid AttributeError when langfuse trace is None
All checks were successful
E2E Health Check / e2e-health (push) Successful in 19s
All checks were successful
E2E Health Check / e2e-health (push) Successful in 19s
This commit is contained in:
@@ -750,7 +750,7 @@ class NvidiaProvider:
|
||||
NVIDIA_LATENCY_HISTOGRAM.observe(latency_ms / 1000)
|
||||
|
||||
# Langfuse
|
||||
langfuse_ctx.trace.generation(
|
||||
langfuse_ctx.generation(
|
||||
name="nvidia_chat",
|
||||
model=model_name,
|
||||
input=prompt[:500],
|
||||
|
||||
Reference in New Issue
Block a user