From 4b63a217c227d284a7bc75dcfd0cc55701760041 Mon Sep 17 00:00:00 2001
From: Nobuhiko Otoba <44864310+nobutoba@users.noreply.github.com>
Date: Fri, 23 Aug 2024 07:24:57 +0900
Subject: [PATCH] "community: Fix GithubFileLoader source code", "docs: Fix
 GithubFileLoader code sample" (#19943)

This PR adds tiny improvements to the `GithubFileLoader` document loader
and its code sample, addressing the following issues:

1. Currently, the `file_extension` argument of `GithubFileLoader` does
not change its behavior at all.
1. The `GithubFileLoader` sample code in
`docs/docs/integrations/document_loaders/github.ipynb` does not work as
it stands.

The respective solutions I propose are the following:

1. Remove `file_extension` argument from `GithubFileLoader`.
1. Specify the branch as `master` (not the default `main`) and rename
`documents` as `document`.

---------

Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
---
 docs/docs/integrations/document_loaders/github.ipynb         | 5 +++--
 .../community/langchain_community/document_loaders/github.py | 1 -
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/docs/docs/integrations/document_loaders/github.ipynb b/docs/docs/integrations/document_loaders/github.ipynb
index 6a1ac50382a..47e940b7c6a 100644
--- a/docs/docs/integrations/document_loaders/github.ipynb
+++ b/docs/docs/integrations/document_loaders/github.ipynb
@@ -175,6 +175,7 @@
    "source": [
     "loader = GithubFileLoader(\n",
     "    repo=\"langchain-ai/langchain\",  # the repo name\n",
+    "    branch=\"master\",  # the branch name\n",
     "    access_token=ACCESS_TOKEN,\n",
     "    github_api_url=\"https://api.github.com\",\n",
     "    file_filter=lambda file_path: file_path.endswith(\n",
@@ -191,13 +192,13 @@
     "example output of one of document: \n",
     "\n",
     "```json\n",
-    "documents.metadata: \n",
+    "document.metadata: \n",
     "    {\n",
     "      \"path\": \"README.md\",\n",
     "      \"sha\": \"82f1c4ea88ecf8d2dfsfx06a700e84be4\",\n",
     "      \"source\": \"https://github.com/langchain-ai/langchain/blob/master/README.md\"\n",
     "    }\n",
-    "documents.content:\n",
+    "document.content:\n",
     "    mock content\n",
     "```"
    ]
diff --git a/libs/community/langchain_community/document_loaders/github.py b/libs/community/langchain_community/document_loaders/github.py
index df53ed16c9d..ee647d42401 100644
--- a/libs/community/langchain_community/document_loaders/github.py
+++ b/libs/community/langchain_community/document_loaders/github.py
@@ -178,7 +178,6 @@ class GitHubIssuesLoader(BaseGitHubLoader):
 class GithubFileLoader(BaseGitHubLoader, ABC):
     """Load GitHub File"""
 
-    file_extension: str = ".md"
     branch: str = "main"
 
     file_filter: Optional[Callable[[str], bool]]