Prompts

Call Prompt

Call a Prompt.

Calling a Prompt calls the model provider before logging the request, responses and metadata to Humanloop.

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.

post/prompts/call

Request

  • Base URL: https://api.humanloop.com/v5
  • URL: https://api.humanloop.com/v5/prompts/call
  • Auth: API key in header X-API-KEY

Query parameters

version_idstring

A specific Version ID of the Prompt to log to.

environmentstring

Name of the Environment identifying a deployed version to log to.

Request body

pathstring

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.

idstring

ID for an existing Prompt.

inputsobject

The inputs passed to the prompt template.

sourcestring

Identifies where the model was called from.

metadataobject

Any additional metadata to record.

start_timestring date-time

When the logged event started.

end_timestring date-time

When the logged event ended.

source_datapoint_idstring

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_idstring

The ID of the parent Log to nest this Log under in a Trace.

userstring

End-user ID related to the Log.

environmentstring

The name of the Environment the Log is associated to.

saveboolean

Whether the request/response payloads will be stored on Humanloop.

log_idstring

This will identify a Log. If you don't provide a Log ID, Humanloop will generate one for you.

num_samplesinteger

The number of generations.

streamtrue required

If true, tokens will be sent as data-only server-sent events. If num_samples > 1, samples are streamed back independently.

return_inputsboolean

Whether to return the inputs in the response. If false, the response will contain an empty dictionary under inputs. This is useful for reducing the size of the response. Defaults to true.

logprobsinteger

Include the log probabilities of the top n tokens in the provider_response

suffixstring

The suffix that comes after a completion of inserted text. Useful for completions that act like inserts.

Changes

No recorded changes to this operation across all 1 revision of this API.