Ask a question to get started
Enter to send•Shift+Enter new line
TracerSessionResult( self, _host_url: Optional[str] = None, **kwargs: Any =
TracerSession
Recursively generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
Generates a JSON string representing this model as it would be received from or sent to the API (but with indentation).
Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump
Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump_json
The number of runs in the project.
The median (50th percentile) latency for the project.
The 99th percentile latency for the project.
The total number of tokens consumed in the project.
The total number of prompt tokens consumed in the project.
The total number of completion tokens consumed in the project.
The start time of the last run in the project.
Feedback stats for the project.
Summary feedback stats for the project.
Facets for the runs in the project.
The total estimated LLM cost associated with the completion tokens.
The estimated cost associated with the prompt (input) tokens.
The estimated cost associated with the completion tokens.
The median (50th percentile) time to process the first token.
The 99th percentile time to process the first token.
The error rate for the project.
A project, hydrated with additional information.
Sessions are also referred to as "Projects" in the UI.
