Source code for langchain_core.output_parsers.transform

from __future__ import annotations

from typing import (
    TYPE_CHECKING,
    Any,
    AsyncIterator,
    Iterator,
    Optional,
    Union,
)

from langchain_core.messages import BaseMessage, BaseMessageChunk
from langchain_core.output_parsers.base import BaseOutputParser, T
from langchain_core.outputs import (
    ChatGeneration,
    ChatGenerationChunk,
    Generation,
    GenerationChunk,
)

if TYPE_CHECKING:
    from langchain_core.runnables import RunnableConfig


class BaseTransformOutputParser(BaseOutputParser[T]):
    """用于处理流式输入的输出解析器的基类。"""

    def _transform(self, input: Iterator[Union[str, BaseMessage]]) -> Iterator[T]:
        for chunk in input:
            if isinstance(chunk, BaseMessage):
                yield self.parse_result([ChatGeneration(message=chunk)])
            else:
                yield self.parse_result([Generation(text=chunk)])

    async def _atransform(
        self, input: AsyncIterator[Union[str, BaseMessage]]
    ) -> AsyncIterator[T]:
        async for chunk in input:
            if isinstance(chunk, BaseMessage):
                yield self.parse_result([ChatGeneration(message=chunk)])
            else:
                yield self.parse_result([Generation(text=chunk)])

    def transform(
        self,
        input: Iterator[Union[str, BaseMessage]],
        config: Optional[RunnableConfig] = None,
        **kwargs: Any,
    ) -> Iterator[T]:
        yield from self._transform_stream_with_config(
            input, self._transform, config, run_type="parser"
        )

    async def atransform(
        self,
        input: AsyncIterator[Union[str, BaseMessage]],
        config: Optional[RunnableConfig] = None,
        **kwargs: Any,
    ) -> AsyncIterator[T]:
        async for chunk in self._atransform_stream_with_config(
            input, self._atransform, config, run_type="parser"
        ):
            yield chunk


class BaseCumulativeTransformOutputParser(BaseTransformOutputParser[T]):
    """用于处理流式输入的输出解析器的基类。"""

    diff: bool = False
    """在流模式下，是要产生先前和当前解析输出之间的差异，还是只产生当前解析输出。"""

    def _diff(self, prev: Optional[T], next: T) -> T:
        """将解析后的输出转换为diff格式。其语义取决于输出解析器。
"""
        raise NotImplementedError()

    def _transform(self, input: Iterator[Union[str, BaseMessage]]) -> Iterator[Any]:
        prev_parsed = None
        acc_gen = None
        for chunk in input:
            if isinstance(chunk, BaseMessageChunk):
                chunk_gen: Generation = ChatGenerationChunk(message=chunk)
            elif isinstance(chunk, BaseMessage):
                chunk_gen = ChatGenerationChunk(
                    message=BaseMessageChunk(**chunk.dict())
                )
            else:
                chunk_gen = GenerationChunk(text=chunk)

            if acc_gen is None:
                acc_gen = chunk_gen
            else:
                acc_gen = acc_gen + chunk_gen

            parsed = self.parse_result([acc_gen], partial=True)
            if parsed is not None and parsed != prev_parsed:
                if self.diff:
                    yield self._diff(prev_parsed, parsed)
                else:
                    yield parsed
                prev_parsed = parsed

    async def _atransform(
        self, input: AsyncIterator[Union[str, BaseMessage]]
    ) -> AsyncIterator[T]:
        prev_parsed = None
        acc_gen = None
        async for chunk in input:
            if isinstance(chunk, BaseMessageChunk):
                chunk_gen: Generation = ChatGenerationChunk(message=chunk)
            elif isinstance(chunk, BaseMessage):
                chunk_gen = ChatGenerationChunk(
                    message=BaseMessageChunk(**chunk.dict())
                )
            else:
                chunk_gen = GenerationChunk(text=chunk)

            if acc_gen is None:
                acc_gen = chunk_gen
            else:
                acc_gen = acc_gen + chunk_gen

            parsed = await self.aparse_result([acc_gen], partial=True)
            if parsed is not None and parsed != prev_parsed:
                if self.diff:
                    yield self._diff(prev_parsed, parsed)
                else:
                    yield parsed
                prev_parsed = parsed