gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: fix linting issues in retry and metadata extraction code

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-13 21:07:23 +00:00
parent 42d35c7c6f
commit bcf5f652fc
2 changed files with 12 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/api/files.py
+11 -12
View File
@@ -525,7 +525,7 @@ def _retry_pipeline_step(file_record: FileRecord, step_name: str, db: Session) -
# Retrying embed requires re-running metadata extraction first, because # Retrying embed requires re-running metadata extraction first, because
# embed_metadata_into_pdf needs the actual metadata dict (not empty). # embed_metadata_into_pdf needs the actual metadata dict (not empty).
# Re-trigger extract_metadata_with_gpt which will chain into embed_metadata_into_pdf. # Re-trigger extract_metadata_with_gpt which will chain into embed_metadata_into_pdf.
# Check for file in multiple locations: # Check for file in multiple locations:
# 1. Original location in tmp (file_record.local_filename) # 1. Original location in tmp (file_record.local_filename)
# 2. Processed location (file_record.processed_file_path) # 2. Processed location (file_record.processed_file_path)
@@ -536,21 +536,20 @@ def _retry_pipeline_step(file_record: FileRecord, step_name: str, db: Session) -
elif file_record.processed_file_path and os.path.exists(file_record.processed_file_path): elif file_record.processed_file_path and os.path.exists(file_record.processed_file_path):
# File has been processed and moved to processed directory # File has been processed and moved to processed directory
file_path = file_record.processed_file_path file_path = file_record.processed_file_path
else: # Try fallback path in workdir/tmp
# Try fallback path in workdir/tmp elif file_record.local_filename:
if file_record.local_filename: workdir = settings.workdir
workdir = settings.workdir tmp_dir = os.path.join(workdir, "tmp")
tmp_dir = os.path.join(workdir, "tmp") fallback_path = os.path.join(tmp_dir, os.path.basename(file_record.local_filename))
fallback_path = os.path.join(tmp_dir, os.path.basename(file_record.local_filename)) if os.path.exists(fallback_path):
if os.path.exists(fallback_path): file_path = fallback_path
file_path = fallback_path
if not file_path: if not file_path:
raise HTTPException( raise HTTPException(
status_code=400, status_code=400,
detail="File not found in tmp or processed directory. Cannot retry metadata embedding." detail="File not found in tmp or processed directory. Cannot retry metadata embedding."
) )
extracted_text = _extract_text_from_pdf(file_path) extracted_text = _extract_text_from_pdf(file_path)
# Pass the full path to the task so it can locate the file # Pass the full path to the task so it can locate the file
task = extract_metadata_task.delay(file_path, extracted_text, file_id) task = extract_metadata_task.delay(file_path, extracted_text, file_id)
app/tasks/extract_metadata_with_gpt.py
+1 -1
View File
@@ -49,7 +49,7 @@ def extract_json_from_text(text):
def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: int = None): def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: int = None):
""" """
Uses OpenAI to classify document metadata. Uses OpenAI to classify document metadata.
Args: Args:
filename: Can be either a basename (e.g., "file.pdf") or a full path (e.g., "/workdir/processed/file.pdf") filename: Can be either a basename (e.g., "file.pdf") or a full path (e.g., "/workdir/processed/file.pdf")
cleaned_text: The extracted text from the document cleaned_text: The extracted text from the document