LakeFSLoader#

class langchain_community.document_loaders.lakefs.LakeFSLoader(lakefs_access_key: str, lakefs_secret_key: str, lakefs_endpoint: str, repo: str | None = None, ref: str | None = 'main', path: str | None = '')[source]#

Load from lakeFS.

Parameters:
  • lakefs_access_key (str) – [required] lakeFS server’s access key

  • lakefs_secret_key (str) – [required] lakeFS server’s secret key

  • lakefs_endpoint (str) – [required] lakeFS server’s endpoint address, ex: https://example.my-lakefs.com

  • repo (str) – [optional, default = ‘’] target repository

  • ref (str) – [optional, default = ‘main’] target ref (branch name, tag, or commit ID)

  • path (str) – [optional, default = ‘’] target path

Attributes

Methods

__init__(lakefs_access_key, ...[, repo, ...])

param lakefs_access_key:

[required] lakeFS server's access key

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.

set_path(path)

set_ref(ref)

set_repo(repo)

__init__(lakefs_access_key: str, lakefs_secret_key: str, lakefs_endpoint: str, repo: str | None = None, ref: str | None = 'main', path: str | None = '')[source]#
Parameters:
  • lakefs_access_key (str) – [required] lakeFS server’s access key

  • lakefs_secret_key (str) – [required] lakeFS server’s secret key

  • lakefs_endpoint (str) – [required] lakeFS server’s endpoint address, ex: https://example.my-lakefs.com

  • repo (str | None) – [optional, default = ‘’] target repository

  • ref (str | None) – [optional, default = ‘main’] target ref (branch name, tag, or commit ID)

  • path (str | None) – [optional, default = ‘’] target path

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]#

A lazy loader for Documents.

Return type:

Iterator[Document]

load() List[Document][source]#

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]

set_path(path: str) None[source]#
Parameters:

path (str) –

Return type:

None

set_ref(ref: str) None[source]#
Parameters:

ref (str) –

Return type:

None

set_repo(repo: str) None[source]#
Parameters:

repo (str) –

Return type:

None

Examples using LakeFSLoader