Log to a Flow.
You can use query parameters version_id
, or environment
, to target
an existing version of the Flow. Otherwise, the default deployed version will be chosen.
If you create the Flow Log with a log_status
of incomplete
, you should later update it to complete
in order to trigger Evaluators.
A specific Version ID of the Flow to log to.
Name of the Environment identifying a deployed version to log to.
List of chat messages that were used as an input to the Flow.
The output message returned by this Flow.
Unique identifier for the Run to associate the Log to.
Path of the Flow, including the name. This locates the Flow in the Humanloop filesystem and is used as as a unique identifier. For example: folder/name
or just name
.
ID for an existing Flow.
The start time of the Trace. Will be updated if a child Log with an earlier start time is added.
The end time of the Trace. Will be updated if a child Log with a later end time is added.
Generated output from your model for the provided inputs. Can be None
if logging an error, or if creating a parent Log with the intention to populate it later.
User defined timestamp for when the log was created.
Error message if the log is an error.
Duration of the logged event in seconds.
Captured log and debug statements.
Raw request sent to provider.
Raw response received the provider.
The inputs passed to the prompt template.
Identifies where the model was called from.
Any additional metadata to record.
Status of the Flow Log. When a Log is updated from incomplete
to complete
, it becomes available to Monitoring Evaluators. Flow Logs cannot have an unspecified status: they must start as incomplete
to allow children to be added. Provide complete
if you don’t intend to add children to the trace.
Unique identifier for the Datapoint that this Log is derived from. This can be used by Humanloop to associate Logs to Evaluations. If provided, Humanloop will automatically associate this Log to Evaluations that require a Log for this Datapoint-Version pair.
The ID of the parent Log to nest this Log under in a Trace.
End-user ID related to the Log.
The name of the Environment the Log is associated to.
Whether the request/response payloads will be stored on Humanloop.
This will identify a Log. If you don’t provide a Log ID, Humanloop will generate one for you.
Flow used to generate the Trace.
Successful Response
Unique identifier for the Log.
Unique identifier for the Flow.
Unique identifier for the Flow Version.
Status of the Flow Log. When a Flow Log is marked as complete
, no more Logs can be added to it. Monitoring Evaluators will only run on complete
Flow Logs.