mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-08 02:45:22 +03:00
Huge thanks to @leo-gan for improving the document loaders notebooks --------- Co-authored-by: Leonid Ganeline <leo.gan.57@gmail.com>
4.1 KiB
4.1 KiB
In [ ]:
!pip install GitPythonIn [2]:
from git import Repo
repo = Repo.clone_from(
"https://github.com/hwchase17/langchain", to_path="./example_data/test_repo1"
)
branch = repo.head.referenceIn [ ]:
from langchain.document_loaders import GitLoaderIn [6]:
loader = GitLoader(repo_path="./example_data/test_repo1/", branch=branch)In [8]:
data = loader.load()In [ ]:
len(data)In [9]:
print(data[0])page_content='.venv\n.github\n.git\n.mypy_cache\n.pytest_cache\nDockerfile' metadata={'file_path': '.dockerignore', 'file_name': '.dockerignore', 'file_type': ''}
In [5]:
from langchain.document_loaders import GitLoaderIn [2]:
loader = GitLoader(
clone_url="https://github.com/hwchase17/langchain",
repo_path="./example_data/test_repo2/",
branch="master",
)In [10]:
data = loader.load()In [11]:
len(data)Out [11]:
1074
In [12]:
from langchain.document_loaders import GitLoader
# eg. loading only python files
loader = GitLoader(repo_path="./example_data/test_repo1/", file_filter=lambda file_path: file_path.endswith(".py"))In [ ]: