RunBase#

class langsmith.schemas.RunBase[source]#

Bases: BaseModel

Base Run schema.

A Run is a span representing a single unit of work or operation within your LLM app. This could be a single call to an LLM or chain, to a prompt formatting call, to a runnable lambda invocation. If you are familiar with OpenTelemetry, you can think of a run as a span.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param attachments: Dict[str, Tuple[str, bytes] | Attachment] [Optional]#: Attachments associated with the run. Each entry is a tuple of (mime_type, bytes).

param end_time: datetime | None = None#: End time of the run, if applicable.

param error: str | None = None#: Error message, if the run encountered any issues.

param events: List[Dict] | None = None#: List of events associated with the run, like start and end events.

param extra: dict | None [Optional]#: Additional metadata or settings related to the run.

param id: UUID [Required]#: Unique identifier for the run.

param inputs: dict [Optional]#: Inputs used for the run.

param name: str [Required]#: Human-readable name for the run.

param outputs: dict | None = None#: Outputs generated by the run, if any.

param parent_run_id: UUID | None = None#: Identifier for a parent run, if this run is a sub-run.

param reference_example_id: UUID | None = None#: Reference to an example that this run may be based on.

param run_type: str [Required]#: The type of run, such as tool, chain, llm, retriever, embedding, prompt, parser.

param serialized: dict | None = None#: Serialized object that executed the run for potential reuse.

param start_time: datetime [Required]#: Start time of the run.

param tags: List[str] | None = None#: Tags for categorizing or annotating the run.

property metadata: dict[str, Any]#: Retrieve the metadata (if any).

property revision_id: UUID | None#: Retrieve the revision ID (if any).