The Exceptions page shows all traces that contain errors or exceptions from your AI applications. You can filter by time range and exception type to quickly find and debug issues.

Error traces

All error traces are automatically captured and displayed here, including:
  • LLM API errors: Authentication, rate limits, model issues
  • Framework errors: LangChain, LlamaIndex execution failures
  • Vector database errors: Connection and query issues
  • Application errors: Custom exceptions and validation errors

Filtering

Use the time range selector to filter errors by period (24H, 7D, 1M, 3M, or custom range). Each error shows the trace ID, timestamp, span name, deployment type, and specific exception type.

Exception details

Click any error to view the complete trace context with detailed exception information, stack traces, and execution flow.

Kubernetes

Running in Kubernetes? Try the OpenLIT Operator

Automatically inject instrumentation into existing workloads without modifying pod specs, container images, or application code.