You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
89 lines
3.0 KiB
89 lines
3.0 KiB
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from abc import ABC, abstractmethod
|
|
from functools import partial
|
|
from typing import Any, Literal, Sequence
|
|
|
|
from langchain.load.serializable import Serializable
|
|
from pydantic import Field
|
|
|
|
|
|
class Document(Serializable):
|
|
"""Class for storing a piece of text and associated metadata."""
|
|
|
|
page_content: str
|
|
"""String text."""
|
|
metadata: dict = Field(default_factory=dict)
|
|
"""Arbitrary metadata about the page content (e.g., source, relationships to other
|
|
documents, etc.).
|
|
"""
|
|
type: Literal["Document"] = "Document"
|
|
|
|
@classmethod
|
|
def is_lc_serializable(cls) -> bool:
|
|
"""Return whether this class is serializable."""
|
|
return True
|
|
|
|
|
|
class BaseDocumentTransformer(ABC):
|
|
"""Abstract base class for document transformation systems.
|
|
|
|
A document transformation system takes a sequence of Documents and returns a
|
|
sequence of transformed Documents.
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
class EmbeddingsRedundantFilter(BaseDocumentTransformer, BaseModel):
|
|
embeddings: Embeddings
|
|
similarity_fn: Callable = cosine_similarity
|
|
similarity_threshold: float = 0.95
|
|
|
|
class Config:
|
|
arbitrary_types_allowed = True
|
|
|
|
def transform_documents(
|
|
self, documents: Sequence[Document], **kwargs: Any
|
|
) -> Sequence[Document]:
|
|
stateful_documents = get_stateful_documents(documents)
|
|
embedded_documents = _get_embeddings_from_stateful_docs(
|
|
self.embeddings, stateful_documents
|
|
)
|
|
included_idxs = _filter_similar_embeddings(
|
|
embedded_documents, self.similarity_fn, self.similarity_threshold
|
|
)
|
|
return [stateful_documents[i] for i in sorted(included_idxs)]
|
|
|
|
async def atransform_documents(
|
|
self, documents: Sequence[Document], **kwargs: Any
|
|
) -> Sequence[Document]:
|
|
raise NotImplementedError
|
|
|
|
""" # noqa: E501
|
|
|
|
@abstractmethod
|
|
def transform_documents(self, documents: Sequence[Document],
|
|
**kwargs: Any) -> Sequence[Document]:
|
|
"""Transform a list of documents.
|
|
|
|
Args:
|
|
documents: A sequence of Documents to be transformed.
|
|
|
|
Returns:
|
|
A list of transformed Documents.
|
|
"""
|
|
|
|
async def atransform_documents(self, documents: Sequence[Document],
|
|
**kwargs: Any) -> Sequence[Document]:
|
|
"""Asynchronously transform a list of documents.
|
|
|
|
Args:
|
|
documents: A sequence of Documents to be transformed.
|
|
|
|
Returns:
|
|
A list of transformed Documents.
|
|
"""
|
|
return await asyncio.get_running_loop().run_in_executor(
|
|
None, partial(self.transform_documents, **kwargs), documents)
|