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

scratch/get_drive.py

@@ -0,0 +1,26 @@
+import logging
+import json
+from ingestion.graph_client import GraphClient
+
+logging.basicConfig(level=logging.INFO)
+
+def get_real_drive_id():
+    client = GraphClient()
+    try:
+        site = client.get_site_by_path("285pdg.sharepoint.com", "/sites/poc_system")
+        site_id = site["id"]
+        print(f"Site ID: {site_id}")
+        
+        drive = client.get_drive(site_id)
+        drive_id = drive["id"]
+        print(f"Drive ID: {drive_id}")
+        
+        # Write the correct drive ID to a file so we know what it is
+        with open("correct_drive_id.txt", "w") as f:
+            f.write(drive_id)
+            
+    except Exception as e:
+        print(f"Error: {e}")
+
+if __name__ == "__main__":
+    get_real_drive_id()

scratch/test_item.py

@@ -0,0 +1,12 @@
+import os
+import sys
+import json
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from ingestion.graph_client import GraphClient
+
+client = GraphClient()
+drive_id = "b!15GOzaN4pU2LRNmRYc8vat7d48GJXyJBj-eKaLgrGv9svCswiraBQalAnVnRMl79"
+item_id = "01BP532D2O74Z6FYQPOVBKE5DBMYDWCWCK"
+url = f"https://graph.microsoft.com/v1.0/drives/{drive_id}/items/{item_id}"
+resp = client._make_request("GET", url)
+print(json.dumps(resp, indent=2))

scratch/test_paddle.py

@@ -0,0 +1,14 @@
+import cv2
+import numpy as np
+from paddleocr import PaddleOCR
+
+# Create a dummy image with some text
+img = np.zeros((100, 300, 3), dtype=np.uint8)
+cv2.putText(img, "Hello World", (10, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
+
+ocr = PaddleOCR(use_angle_cls=False, lang="vi", enable_mkldnn=False)
+result = ocr.ocr(img)
+
+print("===== RAW RESULT =====")
+print(result)
+print("======================")