mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 13:26:32 -04:00
Matt Robinson
11fec7d4d1
### Summary Adds an `UnstructuredCSVLoader` for loading CSVs. One advantage of using `UnstructuredCSVLoader` relative to the standard `CSVLoader` is that if you use `UnstructuredCSVLoader` in `"elements"` mode, an HTML representation of the table will be available in the metadata. #### Who can review? @hwchase17 @eyurtsev
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
import csv
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
from langchain.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class CSVLoader(BaseLoader):
|
|
"""Loads a CSV file into a list of documents.
|
|
|
|
Each document represents one row of the CSV file. Every row is converted into a
|
|
key/value pair and outputted to a new line in the document's page_content.
|
|
|
|
The source for each document loaded from csv is set to the value of the
|
|
`file_path` argument for all doucments by default.
|
|
You can override this by setting the `source_column` argument to the
|
|
name of a column in the CSV file.
|
|
The source of each document will then be set to the value of the column
|
|
with the name specified in `source_column`.
|
|
|
|
Output Example:
|
|
.. code-block:: txt
|
|
|
|
column1: value1
|
|
column2: value2
|
|
column3: value3
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: str,
|
|
source_column: Optional[str] = None,
|
|
csv_args: Optional[Dict] = None,
|
|
encoding: Optional[str] = None,
|
|
):
|
|
self.file_path = file_path
|
|
self.source_column = source_column
|
|
self.encoding = encoding
|
|
self.csv_args = csv_args or {}
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load data into document objects."""
|
|
|
|
docs = []
|
|
with open(self.file_path, newline="", encoding=self.encoding) as csvfile:
|
|
csv_reader = csv.DictReader(csvfile, **self.csv_args) # type: ignore
|
|
for i, row in enumerate(csv_reader):
|
|
content = "\n".join(f"{k.strip()}: {v.strip()}" for k, v in row.items())
|
|
try:
|
|
source = (
|
|
row[self.source_column]
|
|
if self.source_column is not None
|
|
else self.file_path
|
|
)
|
|
except KeyError:
|
|
raise ValueError(
|
|
f"Source column '{self.source_column}' not found in CSV file."
|
|
)
|
|
metadata = {"source": source, "row": i}
|
|
doc = Document(page_content=content, metadata=metadata)
|
|
docs.append(doc)
|
|
|
|
return docs
|
|
|
|
|
|
class UnstructuredCSVLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load CSV files."""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
validate_unstructured_version(min_unstructured_version="0.6.8")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.csv import partition_csv
|
|
|
|
return partition_csv(filename=self.file_path, **self.unstructured_kwargs)
|