Traces

What are Traces

Traces let you dive into the workflow of each model generation and understand the inner workings of an LLM call on orq.ai.

Traces correspond to events within the generations. Events within a Deployment can be various:

• Evaluators & Guardrails
• Retrieval using Knowledge Bases
  • Embedding
  • Reranking
• Caching
• Retries & Fallbacks

Traces let you dive into the events, understanding the inputs, outputs and execution of each step.

How to Lookup Traces

To find traces, head to the Orq.ai panel and to the Traces section.

By looking up events, you can explore traces for each action taken during a generation:

• The left column shows the list of Traces available.
• By selecting a trace, the middle column opens, showing the hierarchy of events shown in order of execution.
• By selecting a single trace, the right column opens, showing details for the specific step.

Trace Detail

Opening a single trace you have access to multiple tabs:

• Details will show the JSON Inputs and optional Documents sent to the step. The Output generated by the step will also be visible.
• The Request tab displays detail of the call, Prompt configuration and Billing details (Token and Costs).
• The Attributes tab displays a JSON payload containing all configuration details available for the Request tab.

💡

Cost and latency of all sub-events add up to those displayed on the parent event.

Filtering Traces

The Trace panel offers Filters to search for traces.

Configuring Column

Columns can be enabled and toggled to display more available data in the traces list.