Submit Evaluator Judgment
Submit Evaluator judgment for an existing Log.
Creates a new Log. The evaluated Log will be set as the parent of the created Log.
Headers
X-API-KEY
Query parameters
version_id
ID of the Evaluator version to log against.
environment
Name of the Environment identifying a deployed version to log to.
Request
This endpoint expects an object.
parent_id
Identifier of the evaluated Log. The newly created Log will have this one set as parent.
path
Path of the Evaluator, including the name. This locates the Evaluator in the Humanloop filesystem and is used as as a unique identifier. For example: folder/name
or just name
.
id
ID for an existing Evaluator.
start_time
When the logged event started.
end_time
When the logged event ended.
output
Generated output from the LLM. Only populated for LLM Evaluator Logs.
created_at
User defined timestamp for when the log was created.
error
Error message if the log is an error.
provider_latency
Duration of the logged event in seconds.
stdout
Captured log and debug statements.
provider_request
Raw request sent to provider. Only populated for LLM Evaluator Logs.
provider_response
Raw response received the provider. Only populated for LLM Evaluator Logs.
inputs
The inputs passed to the prompt template.
source
Identifies where the model was called from.
metadata
Any additional metadata to record.
source_datapoint_id
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.
trace_parent_id
The ID of the parent Log to nest this Log under in a Trace.
user
End-user ID related to the Log.
environment
The name of the Environment the Log is associated to.
save
Whether the request/response payloads will be stored on Humanloop.
log_id
This will identify a Log. If you don't provide a Log ID, Humanloop will generate one for you.
output_message
The message returned by the LLM. Only populated for LLM Evaluator Logs.
judgment
Evaluator assessment of the Log.
marked_completed
Whether the Log has been manually marked as completed by a user.
spec
Response
Successful Response
id
String identifier of the new Log.
parent_id
Identifier of the evaluated parent Log.
version_id
Identifier of Evaluator Version for which the Log was registered.
session_id
Identifier of the Session containing both the parent and the new child Log. If the parent Log does not belong to a Session, a new Session is created with this ID.