mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
53 lines
1.8 KiB
Python
53 lines
1.8 KiB
Python
from typing import Any, Iterator
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class BaseDataFrameLoader(BaseLoader):
|
|
def __init__(self, data_frame: Any, *, page_content_column: str = "text"):
|
|
"""Initialize with dataframe object.
|
|
|
|
Args:
|
|
data_frame: DataFrame object.
|
|
page_content_column: Name of the column containing the page content.
|
|
Defaults to "text".
|
|
"""
|
|
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)
|
|
|
|
|
|
class DataFrameLoader(BaseDataFrameLoader):
|
|
"""Load `Pandas` DataFrame."""
|
|
|
|
def __init__(self, data_frame: Any, page_content_column: str = "text"):
|
|
"""Initialize with dataframe object.
|
|
|
|
Args:
|
|
data_frame: Pandas DataFrame object.
|
|
page_content_column: Name of the column containing the page content.
|
|
Defaults to "text".
|
|
"""
|
|
try:
|
|
import pandas as pd
|
|
except ImportError as e:
|
|
raise ImportError(
|
|
"Unable to import pandas, please install with `pip install pandas`."
|
|
) from e
|
|
|
|
if not isinstance(data_frame, pd.DataFrame):
|
|
raise ValueError(
|
|
f"Expected data_frame to be a pd.DataFrame, got {type(data_frame)}"
|
|
)
|
|
super().__init__(data_frame, page_content_column=page_content_column)
|