raggy.loaders.github

Loaders for GitHub.

GitHubIssueLoader

Loader for GitHub issues in a given repository.

Beware the GitHub API rate limit.

Attributes:

Name	Type	Description
repo	str	The GitHub repository in the format 'owner/repo'.
n_issues	int	The number of issues to load.
include_comments	bool	Whether to include comments in the issues.
ignore_body_after	str	The text to ignore in the issue body.
ignore_users	List[str]	A list of users to ignore.
use_GH_token	bool	Whether to use the GITHUB_TOKEN environment variable for authentication (recommended).

load async

Load all issues for the given repository.

Returns:

Type	Description
list[Document]	A list of Document objects, each representing an issue.

GitHubRepoLoader

Loader for files on GitHub that match a glob pattern.

Attributes:

Name	Type	Description
repo	str	The GitHub repository in the format 'owner/repo'.
include_globs	list[str]	A list of glob patterns to include.
exclude_globs	list[str]	A list of glob patterns to exclude.

Raises:

Type	Description
ValueError	If the repository is not in the format 'owner/repo'.

Example

Load all files from the prefecthq/prefect

from raggy.loaders.github import GitHubRepoLoader

loader = GitHubRepoLoader(repo="prefecthq/prefect")

documents = await loader.load()
print(documents)

load async

Load files from GitHub that match the glob pattern.