Skip to content
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

[Enhancement] Guess file type based on the filename in request. #335

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

[Enhancement] Guess file type based on the filename in request. #335

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
8 changes: 4 additions & 4 deletions services/file.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,12 +22,12 @@ async def get_document_from_file(
return doc


def extract_text_from_filepath(filepath: str, mimetype: Optional[str] = None) -> str:
def extract_text_from_filepath(filepath: str, mimetype: Optional[str] = None, filename: Optional[str] = None) -> str:
"""Return the text content of a file given its filepath."""

if mimetype is None:
if mimetype is None or mimetype == 'application/octet-stream':
# Get the mimetype of the file based on its extension
mimetype, _ = mimetypes.guess_type(filepath)
mimetype, _ = mimetypes.guess_type(filename)

if not mimetype:
if filepath.endswith(".md"):
Expand Down Expand Up @@ -105,7 +105,7 @@ async def extract_text_from_form_file(file: UploadFile):
f.write(file_stream)

try:
extracted_text = extract_text_from_filepath(temp_file_path, mimetype)
extracted_text = extract_text_from_filepath(temp_file_path, mimetype, file.filename)
except Exception as e:
logger.error(e)
os.remove(temp_file_path)
Expand Down