Phase 7: Hoàn thiện Modular RAG Backend với FastAPI và Đa LLM Provider

ingestion/providers/base_provider.py

@@ -0,0 +1,36 @@
+from abc import ABC, abstractmethod
+from typing import Dict, List, Tuple
+
+class BaseStorageProvider(ABC):
+    """
+    Abstract Base Class for all Document Storage Providers (SharePoint, Google Drive, Local, NAS, etc.)
+    Any new storage source must implement these methods to be seamlessly integrated into the ingestion pipeline.
+    """
+    
+    @abstractmethod
+    def fetch_changes(self, sync_state: Dict) -> Tuple[List[Dict], Dict]:
+        """
+        Fetch incremental changes (new, updated, or deleted files).
+        
+        Args:
+            sync_state (Dict): The last known synchronization state/token.
+            
+        Returns:
+            Tuple[List[Dict], Dict]: 
+                - A list of standardized item dictionaries.
+                - The new sync state to be saved for the next run.
+        """
+        pass
+
+    @abstractmethod
+    def download_file(self, target_item: Dict) -> bytes:
+        """
+        Download the raw file bytes for a given item.
+        
+        Args:
+            target_item (Dict): The standardized item dictionary returned by fetch_changes.
+            
+        Returns:
+            bytes: The raw file content.
+        """
+        pass