Ignore files from .gitignore in Git loader (#2909)

fixes #2905 extends #2851
2023-04-14 18:02:21 -04:00 · 2023-04-14 18:02:21 -04:00 · 66bef1d7ed
commit 66bef1d7ed
parent 7ee87eb0c8
1 changed files with 4 additions and 0 deletions
--- a/langchain/document_loaders/git.py
+++ b/langchain/document_loaders/git.py
@ -54,6 +54,10 @@ class GitLoader(BaseLoader):

            file_path = os.path.join(self.repo_path, item.path)

+            ignored_files = repo.ignored([file_path])
+            if len(ignored_files):
+                continue
+
            # uses filter to skip files
            if self.file_filter and not self.file_filter(file_path):
                continue