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.
RunBase()Unique identifier for the run.
Human-readable name for the run.
Start time of the run.
The type of run, such as tool, chain, llm, retriever, embedding, prompt, parser.
End time of the run, if applicable.
Additional metadata or settings related to the run.
Error message, if the run encountered any issues.
Serialized object that executed the run for potential reuse.
List of events associated with the run, like start and end events.
Inputs used for the run.
Outputs generated by the run, if any.
Reference to an example that this run may be based on.
Identifier for a parent run, if this run is a sub-run.
Tags for categorizing or annotating the run.
Attachments associated with the run.
Each entry is a tuple of (mime_type, bytes).
Retrieve the metadata (if any).
Retrieve the revision ID (if any).
Latency in seconds.