nemo_microservices.types.shared_params.config_data_param#

Module Contents#

Classes#

API#

class nemo_microservices.types.shared_params.config_data_param.ConfigDataParam#

Bases: typing_extensions.TypedDict

actions_server_url: str#

None

The URL of the actions server that should be used for the rails.

colang_version: str#

None

The Colang version to use.

custom_data: Dict[str, object]#

None

Any custom configuration data that might be needed.

enable_multi_step_generation: bool#

None

Whether to enable multi-step generation for the LLM.

enable_rails_exceptions: bool#

None

If set, the pre-defined guardrails raise exceptions instead of returning pre-defined messages.

instructions: Iterable[nemo_microservices.types.shared_params.instruction.Instruction]#

None

List of instructions in natural language that the LLM should use.

lowest_temperature: float#

None

The lowest temperature that should be used for the LLM.

models: typing_extensions.Required[Iterable[nemo_microservices.types.shared_params.guardrail_model.GuardrailModel]]#

None

The list of models used by the rails configuration.

passthrough: bool#

None

Weather the original prompt should pass through the guardrails configuration as is. This means it will not be altered in any way.

prompting_mode: str#

None

Allows choosing between different prompting strategies.

prompts: Iterable[nemo_microservices.types.shared_params.task_prompt.TaskPrompt]#

None

The prompts that should be used for the various LLM tasks.

rails: nemo_microservices.types.shared_params.rails_param.RailsParam#

None

Configuration of specific rails.

sample_conversation: str#

None

The sample conversation that should be used inside the prompts.

tracing: nemo_microservices.types.shared_params.tracing_config.TracingConfig#

None

Configuration for tracing.