langchain.output_parsers.rail_parser.GuardrailsOutputParser¶

class langchain.output_parsers.rail_parser.GuardrailsOutputParser(*, guard: Any = None, api: Optional[Callable] = None, args: Any = None, kwargs: Any = None)[source]¶

Bases: BaseOutputParser

Parse the output of an LLM call using Guardrails.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param api: Optional[Callable] = None¶

The API to use for the Guardrails object.

param args: Any = None¶

The arguments to pass to the API.

param guard: Any = None¶

The Guardrails object.

param kwargs: Any = None¶

The keyword arguments to pass to the API.

dict(**kwargs: Any) → Dict¶

Return dictionary representation of output parser.

classmethod from_pydantic(output_class: Any, num_reasks: int = 1, api: Optional[Callable] = None, *args: Any, **kwargs: Any) → GuardrailsOutputParser[source]¶
classmethod from_rail(rail_file: str, num_reasks: int = 1, api: Optional[Callable] = None, *args: Any, **kwargs: Any) → GuardrailsOutputParser[source]¶

Create a GuardrailsOutputParser from a rail file.

Parameters

  • rail_file – a rail file.

  • num_reasks – number of times to re-ask the question.

  • api – the API to use for the Guardrails object.

  • *args – The arguments to pass to the API

  • **kwargs – The keyword arguments to pass to the API.

Returns

GuardrailsOutputParser

classmethod from_rail_string(rail_str: str, num_reasks: int = 1, api: Optional[Callable] = None, *args: Any, **kwargs: Any) → GuardrailsOutputParser[source]¶
get_format_instructions() → str[source]¶

Instructions on how the LLM output should be formatted.

invoke(input: str | langchain.schema.messages.BaseMessage, config: langchain.schema.runnable.RunnableConfig | None = None) → T¶
parse(text: str) → Dict[source]¶

Parse a single string model output into some structure.

Parameters

text – String output of a language model.

Returns

Structured output.

parse_result(result: List[Generation]) → T¶

Parse a list of candidate model Generations into a specific format.

The return value is parsed from only the first Generation in the result, which

is assumed to be the highest-likelihood Generation.

Parameters

result – A list of Generations to be parsed. The Generations are assumed to be different candidate outputs for a single model input.

Returns

Structured output.

parse_with_prompt(completion: str, prompt: PromptValue) → Any¶

Parse the output of an LLM call with the input prompt for context.

The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.

Parameters

  • completion – String output of a language model.

  • prompt – Input PromptValue.

Returns

Structured output

to_json() → Union[SerializedConstructor, SerializedNotImplemented]¶
to_json_not_implemented() → SerializedNotImplemented¶
property lc_attributes: Dict¶

Return a list of attribute names that should be included in the serialized kwargs. These attributes must be accepted by the constructor.

property lc_namespace: List[str]¶

Return the namespace of the langchain object. eg. [“langchain”, “llms”, “openai”]

property lc_secrets: Dict[str, str]¶

Return a map of constructor argument names to secret ids. eg. {“openai_api_key”: “OPENAI_API_KEY”}

property lc_serializable: bool¶

Return whether or not the class is serializable.

model Config¶

Bases: object

extra = 'ignore'¶