Run schema when loading from the DB.
The project ID this run belongs to.
Deprecated: The child run IDs of this run.
The child runs of this run, if instructed to load using the client These are not populated by default, as it is a heavier query to make.
Feedback stats for this run.
Relative URL path of this run within the app.
Unique ID of the serialized object for this run.
Status of the run (e.g., 'success').
Number of tokens used for the prompt.
Number of tokens generated as output.
Total tokens for prompt and completion.
Breakdown of prompt (input) token counts.
Does not need to sum to full prompt token count.
Breakdown of completion (output) token counts.
Does not need to sum to full completion token count.
Time the first token was processed.
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.
Breakdown of prompt (input) token costs.
Does not need to sum to full prompt token cost.
Breakdown of completion (output) token costs.
Does not need to sum to full completion token cost.
List of parent run IDs.
Unique ID assigned to every run within this nested trace.
Dotted order for the run.
This is a string composed of {time}{run-uuid}.* so that a trace can be sorted in the order it was executed.
Whether this run is in a dataset.
URL of this run within the app.
Alias for prompt_tokens.
Alias for completion_tokens.
Alias for prompt_cost.
Alias for completion_cost.
Alias for prompt_token_details.
Alias for output_token_details.
Alias for prompt_cost_details.
Alias for completion_cost_details.
Unique identifier for the run.
Human-readable name for the run.
The type of run, such as tool, chain, llm, retriever,
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
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.
Retrieve the metadata (if any).
Retrieve the revision ID (if any).
Latency in seconds.
