Register

post

https://api.humanloop.com/v4/model-configs

If the project name provided does not exist, a new project will be created
automatically.

If an experiment name is provided, the specified experiment must already
exist. Otherwise, an error will be raised.

If the model config is the first to be associated to the project, it will
be set as the active model config.

Body Params

Model config request.

Contains fields that are common to all (i.e. both chat and complete) endpoints.

name

string

A friendly display name for the model config. If not provided, a name will be generated.

description

string

A description of the model config.

provider

string

enum

Defaults to openai

Supported model providers.

model

string

required

The model instance used. E.g. text-davinci-002.

max_tokens

integer

Defaults to -1

The maximum number of tokens to generate. Provide max_tokens=-1 to dynamically calculate the maximum number of tokens to generate given the length of the prompt

temperature

number

Defaults to 1

What sampling temperature to use when making a generation. Higher values means the model will be more creative.

top_p

number

Defaults to 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

stop

string | array

The string (or list of strings) after which the model will stop generating. The returned text will not contain the stop sequence.

presence_penalty

number

Defaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the generation so far.

frequency_penalty

number

Defaults to 0

Number between -2.0 and 2.0. Positive values penalize new tokens based on how frequently they appear in the generation so far.

other

object

Other parameter values to be passed to the provider call.

seed

integer

If specified, model will make a best effort to sample deterministically, but it is not guaranteed.

response_format

object

Response format of the model.

project

string

Unique project name. If it does not exist, a new project will be created.

project_id

string

Unique project ID

experiment

string

If specified, the model config will be added to this experiment. Experiments are used for A/B testing and optimizing hyperparameters.

prompt_template

string

Prompt template that will take your specified inputs to form your final request to the provider model. NB: Input variables within the prompt template should be specified with syntax: {{INPUT_NAME}}.

chat_template

array of objects

Messages prepended to the list of messages sent to the provider. These messages that will take your specified inputs to form your final request to the provider model. NB: Input variables within the prompt template should be specified with syntax: {{INPUT_NAME}}.

Chat template

endpoint

string

enum

Defaults to complete

Supported model provider endpoints.

Allowed:

tools

array

Make tools available to OpenAIs chat model as functions.

Tools - equivalent to OpenAI functions.

Responses

200Successful Response

422Validation Error