mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
f7a1fd91b8
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
26 lines
865 B
Python
26 lines
865 B
Python
import json
|
|
from pathlib import Path
|
|
from typing import List, Union
|
|
|
|
from langchain_core.documents import Document
|
|
from langchain_core.utils import stringify_dict
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class AirbyteJSONLoader(BaseLoader):
|
|
"""Load local `Airbyte` json files."""
|
|
|
|
def __init__(self, file_path: Union[str, Path]):
|
|
"""Initialize with a file path. This should start with '/tmp/airbyte_local/'."""
|
|
self.file_path = file_path
|
|
"""Path to the directory containing the json files."""
|
|
|
|
def load(self) -> List[Document]:
|
|
text = ""
|
|
for line in open(self.file_path, "r"):
|
|
data = json.loads(line)["_airbyte_data"]
|
|
text += stringify_dict(data)
|
|
metadata = {"source": str(self.file_path)}
|
|
return [Document(page_content=text, metadata=metadata)]
|