mirror of
https://github.com/arc53/DocsGPT
synced 2024-11-16 00:12:46 +00:00
20 lines
645 B
Python
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]
|