mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-08-26 16:55:38 -04:00
Yifei Song
7d29bb2c02
- [Xorbits](https://doc.xorbits.io/en/latest/) is an open-source computing framework that makes it easy to scale data science and machine learning workloads in parallel. Xorbits can leverage multi cores or GPUs to accelerate computation on a single machine, or scale out up to thousands of machines to support processing terabytes of data. - This PR added support for the Xorbits document loader, which allows langchain to leverage Xorbits to parallelize and distribute the loading of data. - Dependencies: This change requires the Xorbits library to be installed in order to be used. `pip install xorbits` - Request for review: @rlancemartin, @eyurtsev - Twitter handle: https://twitter.com/Xorbitsio Co-authored-by: Bagatur <baskaryan@gmail.com>
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
from typing import Any, Iterator, List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
class XorbitsLoader(BaseLoader):
|
|
"""Load Xorbits DataFrame."""
|
|
|
|
def __init__(self, data_frame: Any, page_content_column: str = "text"):
|
|
"""Initialize with dataframe object.
|
|
|
|
Requirements:
|
|
Must have xorbits installed. You can install with `pip install xorbits`.
|
|
|
|
Args:
|
|
data_frame: Xorbits DataFrame object.
|
|
page_content_column: Name of the column containing the page content.
|
|
Defaults to "text".
|
|
"""
|
|
try:
|
|
import xorbits.pandas as pd
|
|
except ImportError as e:
|
|
raise ImportError(
|
|
"Cannot import xorbits, please install with 'pip install xorbits'."
|
|
) from e
|
|
|
|
if not isinstance(data_frame, pd.DataFrame):
|
|
raise ValueError(
|
|
f"Expected data_frame to be a xorbits.pandas.DataFrame, \
|
|
got {type(data_frame)}"
|
|
)
|
|
self.data_frame = data_frame
|
|
self.page_content_column = page_content_column
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Lazy load records from dataframe."""
|
|
for _, row in self.data_frame.iterrows():
|
|
text = row[self.page_content_column]
|
|
metadata = row.to_dict()
|
|
metadata.pop(self.page_content_column)
|
|
yield Document(page_content=text, metadata=metadata)
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load full dataframe."""
|
|
return list(self.lazy_load())
|