Skip to content

feat: skip existing files when uploading directory #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xddxdd wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: skip existing files when uploading directory #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 18 additions & 1 deletion kbmanager/app_logic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ async def upload_file_to_kb(self, file_path_str: str, kb_id: str):
click.echo(f"Error: {e}", err=True)
sys.exit(1)

async def upload_directory_to_kb(self, directory_path_str: str, kb_id: str, ignore_file_path: Optional[str] = None):
async def upload_directory_to_kb(self, directory_path_str: str, kb_id: str, ignore_file_path: Optional[str] = None, skip_existing: Optional[bool] = None):
directory_path = Path(directory_path_str)
if not directory_path.is_dir():
raise FileOperationError(f"Directory not found: {directory_path_str}")
Expand All @@ -118,12 +118,29 @@ async def upload_directory_to_kb(self, directory_path_str: str, kb_id: str, igno

files_to_upload: List[Tuple[Path, str]] = []

if skip_existing:
existing_files = [
f.meta.additional_properties["name"]
for f in await self._api.list_files_for_knowledge_base(kb_id)
if (
hasattr(f, "meta")
and isinstance(f.meta, self._api.FileMetadataResponseMeta)
and "name" in f.meta.additional_properties
)
]
else:
existing_files = []

for root, _, files_in_dir in os.walk(directory_path):
current_dir_path = Path(root)
for file_name in files_in_dir: # Renamed 'files' to 'files_in_dir' to avoid conflict with outer 'files_to_upload'
full_file_path = current_dir_path / file_name
relative_file_path = str(full_file_path.relative_to(directory_path))

if file_name in existing_files:
logging.debug(f"Skipping existing file: {relative_file_path}")
continue

if not kbignore_parser.is_ignored(str(relative_file_path)):
files_to_upload.append((full_file_path, relative_file_path))
else:
Expand Down
10 changes: 8 additions & 2 deletions kbmanager/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,16 +184,22 @@ async def upload_file(ctx: CLIContext, file_path, kb_id):
type=click.Path(exists=True, dir_okay=False, resolve_path=True),
help="Path to a .kbignore file. Defaults to .kbignore in the directory_path if not specified.",
)
@click.option(
"--skip-existing",
'skip_existing',
flag_value=True,
help="Skip existing files in knowledge base. Files are matched on file name.",
)
@click.pass_obj
@coro
async def upload_dir(ctx: CLIContext, directory_path, kb_id, ignore_file):
async def upload_dir(ctx: CLIContext, directory_path, kb_id, ignore_file, skip_existing):
"""
Uploads files from a directory to a specified knowledge base, respecting .kbignore.
"""
ctx.init_api_client_and_app_logic()
click.echo(f"Uploading directory: {directory_path}")
try:
await ctx.app_logic.upload_directory_to_kb(directory_path, kb_id, ignore_file)
await ctx.app_logic.upload_directory_to_kb(directory_path, kb_id, ignore_file, skip_existing)
except (APIError, FileOperationError) as e:
logger.error(f"Could not complete directory upload: {e}")
click.echo(f"Error: {e}", err=True)
Expand Down