mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +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
46 lines
1.2 KiB
Python
46 lines
1.2 KiB
Python
import datetime
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Iterator, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
def concatenate_rows(row: dict) -> str:
|
|
"""Combine message information in a readable format ready to be used.
|
|
|
|
Args:
|
|
row: dictionary containing message information.
|
|
"""
|
|
sender = row["sender_name"]
|
|
text = row["content"]
|
|
date = datetime.datetime.fromtimestamp(row["timestamp_ms"] / 1000).strftime(
|
|
"%Y-%m-%d %H:%M:%S"
|
|
)
|
|
return f"{sender} on {date}: {text}\n\n"
|
|
|
|
|
|
class FacebookChatLoader(BaseLoader):
|
|
"""Load `Facebook Chat` messages directory dump."""
|
|
|
|
def __init__(self, path: Union[str, Path]):
|
|
"""Initialize with a path."""
|
|
self.file_path = path
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
p = Path(self.file_path)
|
|
|
|
with open(p, encoding="utf8") as f:
|
|
d = json.load(f)
|
|
|
|
text = "".join(
|
|
concatenate_rows(message)
|
|
for message in d["messages"]
|
|
if message.get("content") and isinstance(message["content"], str)
|
|
)
|
|
metadata = {"source": str(p)}
|
|
|
|
yield Document(page_content=text, metadata=metadata)
|