mirror of
https://github.com/james-m-jordan/morphik-core.git
synced 2025-05-09 19:32:38 +00:00
18 lines
478 B
Python
18 lines
478 B
Python
from abc import ABC, abstractmethod
|
|
from typing import List, Union
|
|
from fastapi import UploadFile
|
|
|
|
|
|
class BaseParser(ABC):
|
|
"""Base class for document parsing"""
|
|
|
|
@abstractmethod
|
|
async def split_text(self, text: str) -> List[str]:
|
|
"""Split plain text into chunks"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def parse_file(self, file: Union[UploadFile, bytes], content_type: str) -> List[str]:
|
|
"""Parse file content into text chunks"""
|
|
pass
|