CSVLoader#

class langchain_community.document_loaders.csv_loader.CSVLoader(file_path: str | Path, source_column: str | None = None, metadata_columns: Sequence[str] = (), csv_args: Dict | None = None, encoding: str | None = None, autodetect_encoding: bool = False, *, content_columns: Sequence[str] = ())[source]#

Load 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 documents 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:

column1: value1
column2: value2
column3: value3

Instantiate:

from langchain_community.document_loaders import CSVLoader

loader = CSVLoader(file_path='./hw_200.csv',
    csv_args={
    'delimiter': ',',
    'quotechar': '"',
    'fieldnames': ['Index', 'Height', 'Weight']
})

Load:

docs = loader.load()
print(docs[0].page_content[:100])
print(docs[0].metadata)

Index: Index
Height: Height(Inches)"
Weight: "Weight(Pounds)"
{'source': './hw_200.csv', 'row': 0}

Async load:

docs = await loader.aload()
print(docs[0].page_content[:100])
print(docs[0].metadata)

Index: Index
Height: Height(Inches)"
Weight: "Weight(Pounds)"
{'source': './hw_200.csv', 'row': 0}

Lazy load:

docs = []
docs_lazy = loader.lazy_load()

# async variant:
# docs_lazy = await loader.alazy_load()

for doc in docs_lazy:
    docs.append(doc)
print(docs[0].page_content[:100])
print(docs[0].metadata)

Index: Index
Height: Height(Inches)"
Weight: "Weight(Pounds)"
{'source': './hw_200.csv', 'row': 0}

Parameters:

file_path (str | Path) – The path to the CSV file.
source_column (str | None) – The name of the column in the CSV file to use as the source. Optional. Defaults to None.
metadata_columns (Sequence[str]) – A sequence of column names to use as metadata. Optional.
csv_args (Dict | None) – A dictionary of arguments to pass to the csv.DictReader. Optional. Defaults to None.
encoding (str | None) – The encoding of the CSV file. Optional. Defaults to None.
autodetect_encoding (bool) – Whether to try to autodetect the file encoding.
content_columns (Sequence[str]) – A sequence of column names to use for the document content. If not present, use all columns that are not part of the metadata.

Methods

`__init__`(file_path[, source_column, ...])
`alazy_load`()	A lazy loader for Documents.
`aload`()	Load data into Document objects.
`lazy_load`()	A lazy loader for Documents.
`load`()	Load data into Document objects.
`load_and_split`([text_splitter])	Load Documents and split into chunks.

__init__(file_path: str | Path, source_column: str | None = None, metadata_columns: Sequence[str] = (), csv_args: Dict | None = None, encoding: str | None = None, autodetect_encoding: bool = False, *, content_columns: Sequence[str] = ())[source]#

Parameters:

file_path (str | Path) – The path to the CSV file.
source_column (str | None) – The name of the column in the CSV file to use as the source. Optional. Defaults to None.
metadata_columns (Sequence[str]) – A sequence of column names to use as metadata. Optional.
csv_args (Dict | None) – A dictionary of arguments to pass to the csv.DictReader. Optional. Defaults to None.
encoding (str | None) – The encoding of the CSV file. Optional. Defaults to None.
autodetect_encoding (bool) – Whether to try to autodetect the file encoding.
content_columns (Sequence[str]) – A sequence of column names to use for the document content. If not present, use all columns that are not part of the metadata.

async alazy_load() → AsyncIterator[Document]#

A lazy loader for Documents.

Return type:: AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

lazy_load() → Iterator[Document][source]#

A lazy loader for Documents.

Return type:: Iterator[Document]

load() → list[Document]#

Load data into Document objects.

Return type:: list[Document]

load_and_split(text_splitter: TextSplitter | None = None) → list[Document]#

Load Documents and split into chunks. Chunks are returned as Documents.

Do not override this method. It should be considered to be deprecated!

Parameters:: text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.
Returns:: List of Documents.
Return type:: list[Document]

Examples using CSVLoader