Data types for parameters

There are multiple data types that can be used for the parameters in the configuration. Each data type translates into an element in the playground.


This display a text area widget in the playground.

agenta.config.register_default(prompt_system = ag.TextParam("You are an expert in geography."),
                      prompt_user = ag.TextParam("What is the capital of {country}?"))


This displays a slider widget in the playground with a step 1 (integers).

agenta.config.register_default(intval1 = ag.IntParam(default=1, minval=0, maxval=2),
                      intval2 = ag.IntParam(1)


This displays a slider widget in the playground with a step 0.1 (float).

agenta.config.register_default(temperature = ag.IntParam(default=0.5, minval=0, maxval=2),
                      temperature2 = ag.IntParam(0.5)


This displays a binary switch in the playground.


The MultipleChoiceParam is a dropdown menu that provides a list of individual choices.


The GroupedMultipleChoiceParam is a dropdown menu that presents options in clustered groups, allowing users to select from a categorized list of choices. Image of Evaluation Interface

agenta.config.register_default(temperature = ag.IntParam(default=0.5, minval=0, maxval=2),
                      force_json = BinaryParam())
For now the binary parameter is always initialized with False and can only be changed from the playground

Data types for inputs

Inputs in contrast to parameters are given as argument to the function decorated with @agenta.entrypoint. They are not part of the configuration but instead are the input in the call to the LLM app.

def my_entrypoint(name:str):

Since the agenta sdk uses fastapi under the hood, the data types for the inputs are the same as the ones used in fastapi. In addition, there are some special data types.