Tracing Data Model

Tracing in Langfuse is a way to log and analyze the execution of your LLM applications. The following reference provides a detailed overview of the data model used. It is inspired by OpenTelemetry.

Traces and Observations

A trace typically represents a single request or operation. It contains the overall input and output of the function, as well as metadata about the request, such as the user, the session, and tags. Usually, a trace corresponds to a single api call of an application.

Each trace can contain multiple observations to log the individual steps of the execution.

• Observations are of different types:
  • Events are the basic building blocks. They are used to track discrete events in a trace.
  • Spans represent durations of units of work in a trace.
  • Generations are spans used to log generations of AI models. They contain additional attributes about the model, the prompt, and the completion. For generations, token usage and costs are automatically calculated.
• Observations can be nested.

Sessions

Optionally, traces can be grouped into sessions. Sessions are used to group traces that are part of the same user interaction. A common example is a thread in a chat interface.

Please refer to the Sessions documentation to add sessions to your traces.

Scores

Traces and observations can be evaluated using scores. Scores are flexible objects that store evaluation metrics and can be:

• Numeric, categorical, or boolean values
• Associated with a trace (required)
• Linked to a specific observation (optional)
• Annotated with comments for additional context
• Validated against a score configuration schema (optional)

Please refer to the scores documentation to get started. For more details on score types and attributes, refer to the score data model documentation.