mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
4eda647fdd
Previously, if this did not find a mypy cache then it wouldnt run this makes it always run adding mypy ignore comments with existing uncaught issues to unblock other prs --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
112 lines
3.6 KiB
Python
112 lines
3.6 KiB
Python
"""Abstract interface for document loader implementations."""
|
|
from __future__ import annotations
|
|
|
|
from abc import ABC, abstractmethod
|
|
from typing import TYPE_CHECKING, AsyncIterator, Iterator, List, Optional
|
|
|
|
from langchain_core.documents import Document
|
|
from langchain_core.runnables import run_in_executor
|
|
|
|
from langchain_community.document_loaders.blob_loaders import Blob
|
|
|
|
if TYPE_CHECKING:
|
|
from langchain.text_splitter import TextSplitter
|
|
|
|
|
|
class BaseLoader(ABC):
|
|
"""Interface for Document Loader.
|
|
|
|
Implementations should implement the lazy-loading method using generators
|
|
to avoid loading all Documents into memory at once.
|
|
|
|
The `load` method will remain as is for backwards compatibility, but its
|
|
implementation should be just `list(self.lazy_load())`.
|
|
"""
|
|
|
|
# Sub-classes should implement this method
|
|
# as return list(self.lazy_load()).
|
|
# This method returns a List which is materialized in memory.
|
|
@abstractmethod
|
|
def load(self) -> List[Document]:
|
|
"""Load data into Document objects."""
|
|
|
|
def load_and_split(
|
|
self, text_splitter: Optional[TextSplitter] = None
|
|
) -> List[Document]:
|
|
"""Load Documents and split into chunks. Chunks are returned as Documents.
|
|
|
|
Args:
|
|
text_splitter: TextSplitter instance to use for splitting documents.
|
|
Defaults to RecursiveCharacterTextSplitter.
|
|
|
|
Returns:
|
|
List of Documents.
|
|
"""
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
|
|
if text_splitter is None:
|
|
_text_splitter: TextSplitter = RecursiveCharacterTextSplitter()
|
|
else:
|
|
_text_splitter = text_splitter
|
|
docs = self.load()
|
|
return _text_splitter.split_documents(docs)
|
|
|
|
# Attention: This method will be upgraded into an abstractmethod once it's
|
|
# implemented in all the existing subclasses.
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""A lazy loader for Documents."""
|
|
raise NotImplementedError(
|
|
f"{self.__class__.__name__} does not implement lazy_load()"
|
|
)
|
|
|
|
async def alazy_load(self) -> AsyncIterator[Document]:
|
|
"""A lazy loader for Documents."""
|
|
iterator = await run_in_executor(None, self.lazy_load)
|
|
done = object()
|
|
while True:
|
|
doc = await run_in_executor(None, next, iterator, done) # type: ignore[call-arg, arg-type]
|
|
if doc is done:
|
|
break
|
|
yield doc # type: ignore[misc]
|
|
|
|
|
|
class BaseBlobParser(ABC):
|
|
"""Abstract interface for blob parsers.
|
|
|
|
A blob parser provides a way to parse raw data stored in a blob into one
|
|
or more documents.
|
|
|
|
The parser can be composed with blob loaders, making it easy to reuse
|
|
a parser independent of how the blob was originally loaded.
|
|
"""
|
|
|
|
@abstractmethod
|
|
def lazy_parse(self, blob: Blob) -> Iterator[Document]:
|
|
"""Lazy parsing interface.
|
|
|
|
Subclasses are required to implement this method.
|
|
|
|
Args:
|
|
blob: Blob instance
|
|
|
|
Returns:
|
|
Generator of documents
|
|
"""
|
|
|
|
def parse(self, blob: Blob) -> List[Document]:
|
|
"""Eagerly parse the blob into a document or documents.
|
|
|
|
This is a convenience method for interactive development environment.
|
|
|
|
Production applications should favor the lazy_parse method instead.
|
|
|
|
Subclasses should generally not over-ride this parse method.
|
|
|
|
Args:
|
|
blob: Blob instance
|
|
|
|
Returns:
|
|
List of documents
|
|
"""
|
|
return list(self.lazy_parse(blob))
|