Skip to main content

AI Systems

Cloud Remote AI System Creation​

Create OpenAI AI System​

create_openai_model(name, api_key, api_instance, key?)​

Creates a new remote openai model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

api_key | required string

OpenAI API Key to use for the model.

api_instance | required string

Model identifier name from OpenAI.
Example: "gpt3.5-turbo-0125"

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_openai_model(
    name="GPT 3.5 Model",
    api_instance="gpt-3.5-turbo-0125",
    api_key="sk-***"
)

Create Azure OpenAI AI System​

create_azure_openai_model(name, api_key, api_instance, api_version, model_endpoint, key?)​

Creates a new remote Azure OpenAI model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

api_key | required string

Azure API Key to use for the model.

api_instance | required string

Model identifier name from Azure OpenAI. Example: "gpt35-turbo"

api_version | required string

Azure OpenAI version to use. Example: "2023-07-01-preview"

model_endpoint | required string

URL string representing model endpoint. Example: "https://abc-azure-openai.openai.azure.com/"

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_azure_openai_model(
    name="GPT 3.5 Model",
    api_instance="gpt35-turbo",
    api_key="***",
    api_version="2023-07-01-preview",
    model_endpoint="https://abc-azure-openai.openai.azure.com/"
)

Create Databricks AI System​

create_databricks_model(name, api_key, model_endpoint, key?)​

Creates a new remote Azure OpenAI model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

api_key | required string

Databricks API Key to use for the model.

model_endpoint | required string

Databricks model endpoint. Example: "<host>/serving-endpoints/<some-model-name>/invocations"

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_databricks_model(
    name="Databricks Mixtral",
    api_key="***",
    model_endpoint="<host>/serving-endpoints/<mixtral-model-name>/invocations"
)

Create Anthropic AI System​

create_anthropic_model(name, api_instance, api_key, key?)​

Creates a new remote Anthropic model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

api_instance | required string

Model identifier name from Anthropic. Example: "claude-3-sonnet-20240229"

api_key | required string

Anthropic API Key to use for the model.

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_anthropic_model(
    name="Claude 3 Sonnet",
    api_instance="claude-3-sonnet-20240229",
    api_key="***",
)

Create Mistral AI System​

create_mistral_model(name, api_instance, api_key, key?)​

Creates a new remote Mistral model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

api_instance | required string

Model identifier name from Mistral. Example: "mistral-large-latest"

api_key | required string

Mistral API Key to use for the model.

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_mistral_model(
    name="Mistral Large",
    api_instance="mistral-large-latest",
    api_key="***",
)

Custom Remote AI System Creation​

Create Custom AI System​

create_custom_model(name, remote_model_endpoint, remote_api_auth_config, request_transformation_expression?, response_transformation_expression?, response_type?, batch_size?, multi_turn_support?, enable_retry?, key?)​

Creates a new custom remote model object. The model object can then be used for running evaluations and tests.

Method Parameters​

name | required string

Model name.

remote_model_endpoint | required string

Endpoint URL for the remote model.

remote_api_auth_config | required dict

Authentication configuration for the remote API.

request_transformation_expression | optional string

Expression to transform the outbound request payload to the remote model.

response_transformation_expression | optional string

Expression to transform the inbound response payload from the remote model.

response_type | optional string

Response type returned after transformation. Defaults to "string".

batch_size | optional int

Batch size for requests. Defaults to 1.

multi_turn_support | optional boolean

Indicates if multi‑turn interactions are supported. Defaults to True.

enable_retry | optional boolean

Enable client‑side retry for failed requests. Defaults to False.

key | optional string

Unique model identifier key. Will be autogenerated if not provided.

Returns​

RemoteModel object.

Example​

model = dfl.create_custom_model(
    name="My Custom Model",
    remote_model_endpoint="https://my-remote-llm/api/infer",
    remote_api_auth_config={"type": "bearer", "token": "***"},
    request_transformation_expression="payload = {'inputs': input_text}",
    response_transformation_expression="return response_json['output']",
    response_type="string",
    batch_size=1,
    multi_turn_support=True,
    enable_retry=False,
)

AI Systems - Helpers​

Get Model​

get_model(key)​

Returns model object based on identifier key.

Method Parameters​

key | required string

Unique model identifier key.

Returns​

LocalModel or RemoteModel object.

Example​

model = dfl.get_model('unique_identifier_key')