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

test_dce_pipeline.py

@@ -0,0 +1,38 @@
+import os
+import sys
+import json
+import logging
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+from core.models import IngestedDocument
+from extraction.dce import DocumentClassificationEngine
+
+logging.basicConfig(level=logging.INFO, format="%(levelname)s:%(name)s:%(message)s")
+
+def main():
+    print("=== STARTING DCE PIPELINE TEST ===")
+    
+    if not os.path.exists("ingestion_output.json"):
+        print("File ingestion_output.json not found! Please run ingestion sync first.")
+        return
+        
+    with open("ingestion_output.json", "r", encoding="utf-8") as f:
+        items = json.load(f)
+        
+    dce = DocumentClassificationEngine()
+    
+    print(f"Loaded {len(items)} items from ingestion_output.json\n")
+    
+    for item in items:
+        if item.get("is_folder"):
+            continue # DCE only processes files
+            
+        doc = IngestedDocument(**item)
+        
+        print(f"\n--- Processing: {doc.name} ---")
+        result = dce.classify(doc)
+        print(f">> Policy: {result.processing_policy.value} | Reason: {result.reason}")
+
+if __name__ == "__main__":
+    main()