Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://python.langchain.com/docs/integrations/document_loaders/github/ below:

GitHub | 🦜️🔗 LangChain

This notebooks shows how you can load issues and pull requests (PRs) for a given repository on GitHub. Also shows how you can load github files for a given repository on GitHub. We will use the LangChain Python repository as an example.

To access the GitHub API, you need a personal access token - you can set up yours here: https://github.com/settings/tokens?type=beta. You can either set this token as the environment variable GITHUB_PERSONAL_ACCESS_TOKEN and it will be automatically pulled in, or you can pass it in directly at initialization as the access_token named parameter.

from getpass import getpass

ACCESS_TOKEN = getpass()

from langchain_community.document_loaders import GitHubIssuesLoader

loader = GitHubIssuesLoader(
    repo="langchain-ai/langchain",
    access_token=ACCESS_TOKEN,  
    creator="UmerHA",
)

Let's load all issues and PRs created by "UmerHA".

Here's a list of all filters you can use:

• include_prs
• milestone
• state
• assignee
• creator
• mentioned
• labels
• sort
• direction
• since

For more info, see https://docs.github.com/en/rest/issues/issues?apiVersion=2022-11-28#list-repository-issues.

print(docs[0].page_content)
print(docs[0].metadata)

By default, the GitHub API returns considers pull requests to also be issues. To only get 'pure' issues (i.e., no pull requests), use include_prs=False

loader = GitHubIssuesLoader(
    repo="langchain-ai/langchain",
    access_token=ACCESS_TOKEN,  
    creator="UmerHA",
    include_prs=False,
)
docs = loader.load()

print(docs[0].page_content)
print(docs[0].metadata)

For below code, loads all markdown file in rpeo langchain-ai/langchain

from langchain_community.document_loaders import GithubFileLoader

loader = GithubFileLoader(
    repo="langchain-ai/langchain",  
    branch="master",  
    access_token=ACCESS_TOKEN,
    github_api_url="https://api.github.com",
    file_filter=lambda file_path: file_path.endswith(
        ".md"
    ),  
)
documents = loader.load()

example output of one of document:

document.metadata: 
    {
      "path": "README.md",
      "sha": "82f1c4ea88ecf8d2dfsfx06a700e84be4",
      "source": "https://github.com/langchain-ai/langchain/blob/master/README.md"
    }
document.content:
    mock content

• Document loader conceptual guide
• Document loader how-to guides

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4