Observability 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

Traces

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 ( i.e. user, session, tags, etc.).

Observations

Each trace can contain multiple observations to log the individual steps of the execution. Usually, a trace corresponds to a single api call of an application.

Types

• event is the basic building block. An event is used to track discrete events in a trace.
• span represents durations of units of work in a trace.
• generation logs generations of AI models incl. prompts, token usage and costs.
• agent decides on the application flow and can for example use tools with the guidance of a LLM.
• tool represents a tool call, for example to a weather API.
• chain is a link between different application steps, like passing context from a retriever to a LLM call.
• retriever represents data retrieval steps, such as a call to a vector store or a database.
• evaluator represents functions that assess relevance/correctness/helpfulness of a LLM’s outputs.
• embedding is a call to a LLM to generate embeddings and can include model, token usage and costs
• guardrail is a component that protects against malicious content or jailbreaks.

Nesting

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

Scores are flexible objects used to evaluate traces, observations, sessions and dataset runs.

They can be:

• Numeric, categorical, or boolean values
• Associated with a trace, a session, or a dataset run (one and only one is required)
• For trace level scores only: Linked to a specific observation within a trace (optional)
• Annotated with comments for additional context
• Validated against a score configuration schema (optional)

Typically, session-level scores are used for comprehensive evaluation of conversational experiences across multiple interactions, while trace-level scores are used for evaluation of a single interaction. Dataset run level scores are used for overall evaluation of a dataset run, e.g. precision, recall, F1-score.

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

Billable Units

Langfuse Cloud pricing is based on the number of ingested units per billing period.

Units = Traces + Observations + Scores

Use our pricing calculator to estimate your monthly costs based on your expected usage.

FAQ

How can I track my Langfuse Cloud usage? Use the Usage Monitoring Report in the Dashboards tab in Langfuse to analyze your Langfuse Cloud usage.

How can I optimize my Langfuse Cloud usage to reduce cost? If your application scales and you want to optimize Langfuse Cloud cost, please check out this guide.