janus.parsers.partition_parser

Attributes

log
RNG
EXAMPLE_IDS

Classes

PartitionObject	Mixin to provide __str__, __repr__, and __pretty__ methods. See #884 for more details.
PartitionList	Mixin to provide __str__, __repr__, and __pretty__ methods. See #884 for more details.
PartitionParser	Base class to parse the output of an LLM call.

Module Contents

janus.parsers.partition_parser.log

janus.parsers.partition_parser.RNG

class janus.parsers.partition_parser.PartitionObject(**data)

Bases: langchain_core.pydantic_v1.BaseModel

Mixin to provide __str__, __repr__, and __pretty__ methods. See #884 for more details.

__pretty__ is used by [devtools](https://python-devtools.helpmanual.io/) to provide human readable representations of objects.

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.

Parameters:

data (Any) –

reasoning: str

location: str

class janus.parsers.partition_parser.PartitionList(**data)

Bases: langchain_core.pydantic_v1.BaseModel

Mixin to provide __str__, __repr__, and __pretty__ methods. See #884 for more details.

__pretty__ is used by [devtools](https://python-devtools.helpmanual.io/) to provide human readable representations of objects.

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.

Parameters:

data (Any) –

janus.parsers.partition_parser.EXAMPLE_IDS

class janus.parsers.partition_parser.PartitionParser(token_limit, model)

Bases: janus.parsers.parser.JanusParser, langchain.output_parsers.PydanticOutputParser

Base class to parse the output of an LLM call.

Output parsers help structure language model responses.

Example

class BooleanOutputParser(BaseOutputParser[bool]):
    true_val: str = "YES"
    false_val: str = "NO"

    def parse(self, text: str) -> bool:
        cleaned_text = text.strip().upper()
        if cleaned_text not in (self.true_val.upper(), self.false_val.upper()):
            raise OutputParserException(
                f"BooleanOutputParser expected output value to either be "
                f"{self.true_val} or {self.false_val} (case-insensitive). "
                f"Received {cleaned_text}."
            )
        return cleaned_text == self.true_val.upper()

    @property
    def _type(self) -> str:
        return "boolean_output_parser"

Parameters:

• token_limit (int) –

• model (langchain_core.language_models.BaseLanguageModel) –

token_limit: int

model: langchain_core.language_models.BaseLanguageModel

lines: list[str] = []

line_id_to_index: dict[str, int]

parse_input(block)

Parse the input block into raw string input ready to be passed to an LLM. Also perform any processing or saving of metadata.

Parameters:

block (janus.language.block.CodeBlock) – The CodeBlock to be processed

Returns:

A parsed version of the input text

Return type:

str

parse(text)

Parse a single string model output into some structure.

Parameters:

text (str | langchain_core.messages.BaseMessage) – String output of a language model.

Returns:

Structured output.

Return type:

str