DeepchecksLLMClient

class DeepchecksLLMClient

DeepchecksLLMClient is the class through which you can interact with the Deepchecks LLM API.

__init__(host: str = None, api_token: str = None, log_level: int = 30, silent_mode: bool = False)

Init Deepchecks LLM Client. Connect to the server and perform a simple handshake with the API.

Parameters:

hoststr

The URL of the Deepchecks server to communicate with. By default, it’s set to the Deepchecks LLM host (https://app.llm.deepchecks.com), but you can override it by providing a custom URL. If not provided, the value is read from the environment variable DEEPCHECKS_LLM_HOST.

api_tokenstr

Deepchecks API Token (can be generated from the UI). If not provided, the value is read from the environment variable DEEPCHECKS_LLM_API_TOKEN.

silent_mode: bool, default=False

If True, the SDK will print logs upon encountering errors rather than raising them

log_level: int, default=logging.WARNING

Set SDK loggers logging level

Returns:

None

__new__(*args, **kwargs)

Attributes

DeepchecksLLMClient.api

Get the API object for the client.

Methods

DeepchecksLLMClient.annotate(app_name, ...)	Annotate a specific interaction by its user_interaction_id.
DeepchecksLLMClient.create_app_version(...)	Create a new application.
DeepchecksLLMClient.create_application(...)	Create a new application.
DeepchecksLLMClient.create_custom_property(...)	Define a custom property for the current application.
DeepchecksLLMClient.data_iterator(app_name, ...)	Fetch all interactions from the specified environment type (PROD/EVAL) as an iterable.
DeepchecksLLMClient.delete_custom_property(...)	Delete a custom property for the current application.
DeepchecksLLMClient.delete_interactions(...)	Delete specific interactions by their user_interaction_ids.
DeepchecksLLMClient.get_application_config(...)	Write the auto-annotation YAML configuration file to the specified path.
DeepchecksLLMClient.get_applications()	Get all applications as Application objects.
DeepchecksLLMClient.get_custom_properties(...)	Get the custom properties defined for the current application.
DeepchecksLLMClient.get_data(app_name, ...)	Fetch all the interactions from the specified environment (PROD/EVAL) as a pandas DataFrame.
DeepchecksLLMClient.get_data_if_calculations_completed(...)	Check if calculations for specified events are completed by calling get_interactions_complete_status.
DeepchecksLLMClient.get_interaction_by_user_interaction_id(...)	Get a specific interaction by its user_interaction_id.
DeepchecksLLMClient.get_interactions_complete_status(...)	Get the completion status of interactions for specified events and user interaction IDs.
DeepchecksLLMClient.get_pentest_prompts(app_name)	Get pentest prompts for the application.
DeepchecksLLMClient.get_versions([app_name])	Get all versions of an application as Version objects.
DeepchecksLLMClient.log_batch_interactions(...)	Log multiple interactions at once.
DeepchecksLLMClient.log_interaction(...[, ...])	Log a single interaction.
DeepchecksLLMClient.update_application_config(...)	Update the auto-annotation YAML configuration file for the current application.
DeepchecksLLMClient.update_custom_property(...)	Update a custom property for the current application.
DeepchecksLLMClient.update_interaction(...)	Update a specific interaction by its user_interaction_id.