KeyArgo
/
private-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Adding support to ingest files with extensions in uppercase 

Files in the source_directory where ignored if their extensions where in uppercase like (*.PDF).
This change supports ingestion of files that match either lowercase or uppercase extensions like *.pdf or *.PDF. 
This can be enhanced further to support camelcase like *.Pdf at a later stage. The assumption is that this scenario is probably less than 5%.
This commit is contained in:
parampavar 2023-08-16 16:03:56 -07:00 committed by GitHub
parent 8b9f7589c3
commit 8f369dd2b9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ingest.py
View File

@ -82,7 +82,7 @@ LOADER_MAPPING = {
def load_single_document(file_path: str) -> List[Document]:
ext = "." + file_path.rsplit(".", 1)[-1]
ext = "." + file_path.rsplit(".", 1)[-1].lower()
if ext in LOADER_MAPPING:
loader_class, loader_args = LOADER_MAPPING[ext]
loader = loader_class(file_path, **loader_args)
@ -97,7 +97,10 @@ def load_documents(source_dir: str, ignored_files: List[str] = []) -> List[Docum
all_files = []
for ext in LOADER_MAPPING:
all_files.extend(
glob.glob(os.path.join(source_dir, f"**/*{ext}"), recursive=True)
glob.glob(os.path.join(source_dir, f"**/*{ext.lower()}"), recursive=True)
)
all_files.extend(
glob.glob(os.path.join(source_dir, f"**/*{ext.upper()}"), recursive=True)
)
filtered_files = [file_path for file_path in all_files if file_path not in ignored_files]