You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
DocsGPT/application/parser/file/base.py

20 lines
645 B
Python

"""Base reader class."""
from abc import abstractmethod
from typing import Any, List
from langchain.docstore.document import Document as LCDocument
from parser.schema.base import Document
class BaseReader:
"""Utilities for loading data from a directory."""
@abstractmethod
def load_data(self, *args: Any, **load_kwargs: Any) -> List[Document]:
"""Load data from the input directory."""
def load_langchain_documents(self, **load_kwargs: Any) -> List[LCDocument]:
"""Load data in LangChain document format."""
docs = self.load_data(**load_kwargs)
return [d.to_langchain_format() for d in docs]