feat(storage): integrate Alibaba Cloud OSS for file persistence - Add OSSAdapter and LocalAdapter with StorageFactory pattern - Integrate PKB module with OSS upload - Rename difyDocumentId to storageKey - Create 4 OSS buckets and development specification

extraction_service/.dockerignore

@@ -82,6 +82,9 @@ models/
 
 
 
+
+
+
 
 
 

extraction_service/operations/__init__.py

@@ -70,6 +70,9 @@ __version__ = '1.0.0'
 
 
 
+
+
+
 
 
 

extraction_service/operations/dropna.py

@@ -203,6 +203,9 @@ def get_missing_summary(df: pd.DataFrame) -> dict:
 
 
 
+
+
+
 
 
 

extraction_service/operations/filter.py

@@ -163,6 +163,9 @@ def apply_filter(
 
 
 
+
+
+
 
 
 

extraction_service/operations/unpivot.py

@@ -327,6 +327,9 @@ def get_unpivot_preview(
 
 
 
+
+
+
 
 
 

extraction_service/services/pdf_markdown_processor.py

@@ -144,3 +144,6 @@ def extract_pdf_to_markdown(pdf_path: str) -> Dict[str, Any]:
     return processor.to_markdown(pdf_path)
 
 
+
+
+

extraction_service/test_dc_api.py

@@ -337,6 +337,9 @@ if __name__ == "__main__":
 
 
 
+
+
+
 
 
 

extraction_service/test_execute_simple.py

@@ -103,6 +103,9 @@ except Exception as e:
 
 
 
+
+
+
 
 
 

extraction_service/test_module.py

@@ -83,6 +83,9 @@ except Exception as e:
 
 
 
+
+
+