parse() — langchain Function Reference

Architecture documentation for the parse() function in boolean.py from the langchain codebase.

Function python OutputParsing StreamingParsers

Entity Profile

OutputParsing→ StreamingParsers→ parse() — langchain Function Reference

Dependency Diagram

graph TD
  461fb1ed_a3c7_c638_a529_699f63c96a8f["parse()"]
  da968a10_fe6d_3b39_b567_42129c1c66a4["BooleanOutputParser"]
  461fb1ed_a3c7_c638_a529_699f63c96a8f -->|defined in| da968a10_fe6d_3b39_b567_42129c1c66a4
  style 461fb1ed_a3c7_c638_a529_699f63c96a8f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/output_parsers/boolean.py lines 14–49

    def parse(self, text: str) -> bool:
        """Parse the output of an LLM call to a boolean.

        Args:
            text: output of a language model

        Returns:
            boolean
        """
        regexp = rf"\b({self.true_val}|{self.false_val})\b"

        truthy = {
            val.upper()
            for val in re.findall(regexp, text, flags=re.IGNORECASE | re.MULTILINE)
        }
        if self.true_val.upper() in truthy:
            if self.false_val.upper() in truthy:
                msg = (
                    f"Ambiguous response. Both {self.true_val} and {self.false_val} "
                    f"in received: {text}."
                )
                raise ValueError(msg)
            return True
        if self.false_val.upper() in truthy:
            if self.true_val.upper() in truthy:
                msg = (
                    f"Ambiguous response. Both {self.true_val} and {self.false_val} "
                    f"in received: {text}."
                )
                raise ValueError(msg)
            return False
        msg = (
            f"BooleanOutputParser expected output value to include either "
            f"{self.true_val} or {self.false_val}. Received {text}."
        )
        raise ValueError(msg)