Log to a Prompt.
You can use query parameters version_id
, or environment
, to target
an existing version of the Prompt. Otherwise, the default deployed version will be chosen.
Instead of targeting an existing version explicitly, you can instead pass in Prompt details in the request body. In this case, we will check if the details correspond to an existing version of the Prompt. If they do not, we will create a new version. This is helpful in the case where you are storing or deriving your Prompt details in code.
A specific Version ID of the Prompt to log to.
Name of the Environment identifying a deployed version to log to.
Unique identifier for the Evaluation Report to associate the Log to.
Path of the Prompt, including the name. This locates the Prompt in the Humanloop filesystem and is used as as a unique identifier. For example: folder/name
or just name
.
ID for an existing Prompt.
The message returned by the provider.
Number of tokens in the prompt used to generate the output.
Number of tokens in the output generated by the model.
Cost in dollars associated to the tokens in the prompt.
Cost in dollars associated to the tokens in the output.
Reason the generation finished.
The messages passed to the to provider chat endpoint.
Controls how the model uses tools. The following options are supported:
'none'
means the model will not call any tool and instead generates a message; this is the default when no tools are provided as part of the Prompt.'auto'
means the model can decide to call one or more of the provided tools; this is the default when tools are provided as part of the Prompt.'required'
means the model can decide to call one or more of the provided tools.{'type': 'function', 'function': {name': <TOOL_NAME>}}
forces the model to use the named function.Details of your Prompt. A new Prompt version will be created if the provided details are new.
When the logged event started.
When the logged event ended.
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.
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.
Unique identifier for the Batch to add this Batch to. Batches are used to group Logs together for Evaluations. A Batch will be created if one with the given ID does not exist.
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.
String ID of log.
ID of the Prompt the log belongs to.
ID of the specific version of the Prompt.
String ID of session the log belongs to.