Configure Xet tracking for documents

.gitattributes

@@ -0,0 +1,2 @@
+documents/*.pdf filter=lfs diff=lfs merge=lfs -text
+

.gitignore

@@ -48,6 +48,4 @@ yarn-error.log*
 .DS_Store
 Thumbs.db
 
-# Documents (optional - you may want to track these)
-documents/
-documents/*.pdf
+# Documents (tracked via Hugging Face Xet)

Dockerfile

@@ -31,7 +31,7 @@ RUN mkdir -p vectorstore documents
 COPY vectorstore/ ./vectorstore/
 
 # Copy documents and processed data
-# COPY documents/ ./documents/
+COPY documents/ ./documents/
 COPY processed_documents.json ./processed_documents.json
 
 # Copy built frontend bundle
@@ -39,7 +39,7 @@ COPY frontend/build/ ./frontend/build/
 
 # Copy main app entry point
 COPY app.py .
-COPY files_upload.py ./files_upload.py
+# COPY files_upload.py ./files_upload.py
 
 
 # Expose port (Hugging Face Spaces uses 7860)

app.py

@@ -15,31 +15,31 @@ from dotenv import load_dotenv
 from backend.main import app as backend_app, initialize_rag_system
 
 
-def run_files_upload_script(script_path: Path) -> None:
-    """Run the files_upload.py helper to ensure documents are available."""
-    if not script_path.exists():
-        print(f"[root_app] Upload script not found at {script_path}")
-        return
+# def run_files_upload_script(script_path: Path) -> None:
+#     """Run the files_upload.py helper to ensure documents are available."""
+#     if not script_path.exists():
+#         print(f"[root_app] Upload script not found at {script_path}")
+#         return
 
-    print(f"[root_app] Running upload script: {script_path}")
-    try:
-        completed = subprocess.run(
-            [sys.executable, str(script_path)],
-            capture_output=True,
-            text=True,
-            check=True,
-        )
-        if completed.stdout:
-            print(f"[root_app] upload script output:\n{completed.stdout}")
-        if completed.stderr:
-            print(f"[root_app] upload script warnings:\n{completed.stderr}")
-    except subprocess.CalledProcessError as exc:
-        print(f"[root_app] WARNING: upload script failed with code {exc.returncode}")
-        if exc.stdout:
-            print(f"[root_app] upload script stdout:\n{exc.stdout}")
-        if exc.stderr:
-            print(f"[root_app] upload script stderr:\n{exc.stderr}")
-        raise
+#     print(f"[root_app] Running upload script: {script_path}")
+#     try:
+#         completed = subprocess.run(
+#             [sys.executable, str(script_path)],
+#             capture_output=True,
+#             text=True,
+#             check=True,
+#         )
+#         if completed.stdout:
+#             print(f"[root_app] upload script output:\n{completed.stdout}")
+#         if completed.stderr:
+#             print(f"[root_app] upload script warnings:\n{completed.stderr}")
+#     except subprocess.CalledProcessError as exc:
+#         print(f"[root_app] WARNING: upload script failed with code {exc.returncode}")
+#         if exc.stdout:
+#             print(f"[root_app] upload script stdout:\n{exc.stdout}")
+#         if exc.stderr:
+#             print(f"[root_app] upload script stderr:\n{exc.stderr}")
+#         raise
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
@@ -95,7 +95,7 @@ async def lifespan(app: FastAPI):
         print(f"[root_app] PROCESSED_JSON: {processed_json} (exists: {processed_json.exists()})")
 
         # Run the upload script before initializing the RAG system
-        run_files_upload_script(upload_script)
+        # run_files_upload_script(upload_script)
 
         initialize_rag_system()
         print("[root_app] RAG system initialization completed")

documents/تنظيم صندوق النفقة.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2522a7e99b104117cd15bf53c4f072eeccb4667f493493ff73e2ba2839c3d7d
+size 88498

documents/شرح نظام الأحوال الشخصية.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2322f04afd2f881ad7118847022039c633d30e3552b84947f0ef81d3702fe444
+size 2779178

documents/فسخ عقد النكاح.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e439bddeb59dbb3d5a392fad2b434aab6389397c0584341a485b73bf56d5b3
+size 718605

documents/لا ئحة نظام الاحوال الشخصية.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a12d9757b13a214af4d5d4a3e85a31df82091ff482bfcf05547798c7ffa46a6
+size 103538

documents/لائحة التقارير الطبية.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672db5d1fe0b7878bb2020c253065e88bcc0a8846ccb654a8e825d2eb05ee1a2
+size 74599

documents/لائحة زواج السعودي بغير سعودية والسعودية بغير سعودي.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d2c90ff07e39e54bb6d08f2f81f420002208eb61adffd011384234b2053ab0
+size 75695

documents/نظام الاحوال الشخصية.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99105dfe2a78e38bcc630cb796f6035b83b731d389f90fa51156464c6a2cb09c
+size 341801

documents/نظام المرافعات الشرعية ولوائحه التنفيذية مع الفهارس.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad3294c37e0d3310f7237411a2da20ae6b00fd5730421054588dc5aa06eb192
+size 2259616

uv.lock

@@ -386,6 +386,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f3/4f/0ce34195b63240b6693086496c9bab4ef23999112184399a3e88854c7674/fastapi-0.104.1-py3-none-any.whl", hash = "sha256:752dc31160cdbd0436bb93bad51560b57e525cbb1d4bbf6f4904ceee75548241", size = 92862, upload-time = "2023-10-30T10:07:35.636Z" },
 ]
 
+[[package]]
+name = "filelock"
+version = "3.20.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/58/46/0028a82567109b5ef6e4d2a1f04a583fb513e6cf9527fcdd09afd817deeb/filelock-3.20.0.tar.gz", hash = "sha256:711e943b4ec6be42e1d4e6690b48dc175c822967466bb31c0c293f34334c13f4", size = 18922, upload-time = "2025-10-08T18:03:50.056Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/76/91/7216b27286936c16f5b4d0c530087e4a54eead683e6b0b73dd0c64844af6/filelock-3.20.0-py3-none-any.whl", hash = "sha256:339b4732ffda5cd79b13f4e2711a31b0365ce445d95d243bb996273d072546a2", size = 16054, upload-time = "2025-10-08T18:03:48.35Z" },
+]
+
 [[package]]
 name = "filetype"
 version = "1.2.0"
@@ -436,6 +445,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/9a/9a/e35b4a917281c0b8419d4207f4334c8e8c5dbf4f3f5f9ada73958d937dcc/frozenlist-1.8.0-py3-none-any.whl", hash = "sha256:0c18a16eab41e82c295618a77502e17b195883241c563b00f0aa5106fc4eaa0d", size = 13409, upload-time = "2025-10-06T05:38:16.721Z" },
 ]
 
+[[package]]
+name = "fsspec"
+version = "2025.10.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/24/7f/2747c0d332b9acfa75dc84447a066fdf812b5a6b8d30472b74d309bfe8cb/fsspec-2025.10.0.tar.gz", hash = "sha256:b6789427626f068f9a83ca4e8a3cc050850b6c0f71f99ddb4f542b8266a26a59", size = 309285, upload-time = "2025-10-30T14:58:44.036Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/02/a6b21098b1d5d6249b7c5ab69dde30108a71e4e819d4a9778f1de1d5b70d/fsspec-2025.10.0-py3-none-any.whl", hash = "sha256:7c7712353ae7d875407f97715f0e1ffcc21e33d5b24556cb1e090ae9409ec61d", size = 200966, upload-time = "2025-10-30T14:58:42.53Z" },
+]
+
 [[package]]
 name = "greenlet"
 version = "3.2.4"
@@ -475,6 +493,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" },
 ]
 
+[[package]]
+name = "hf-xet"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5e/6e/0f11bacf08a67f7fb5ee09740f2ca54163863b07b70d579356e9222ce5d8/hf_xet-1.2.0.tar.gz", hash = "sha256:a8c27070ca547293b6890c4bf389f713f80e8c478631432962bb7f4bc0bd7d7f", size = 506020, upload-time = "2025-10-24T19:04:32.129Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/96/2d/22338486473df5923a9ab7107d375dbef9173c338ebef5098ef593d2b560/hf_xet-1.2.0-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:46740d4ac024a7ca9b22bebf77460ff43332868b661186a8e46c227fdae01848", size = 2866099, upload-time = "2025-10-24T19:04:15.366Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/8c/c5becfa53234299bc2210ba314eaaae36c2875e0045809b82e40a9544f0c/hf_xet-1.2.0-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:27df617a076420d8845bea087f59303da8be17ed7ec0cd7ee3b9b9f579dff0e4", size = 2722178, upload-time = "2025-10-24T19:04:13.695Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/92/cf3ab0b652b082e66876d08da57fcc6fa2f0e6c70dfbbafbd470bb73eb47/hf_xet-1.2.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3651fd5bfe0281951b988c0facbe726aa5e347b103a675f49a3fa8144c7968fd", size = 3320214, upload-time = "2025-10-24T19:04:03.596Z" },
+    { url = "https://files.pythonhosted.org/packages/46/92/3f7ec4a1b6a65bf45b059b6d4a5d38988f63e193056de2f420137e3c3244/hf_xet-1.2.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d06fa97c8562fb3ee7a378dd9b51e343bc5bc8190254202c9771029152f5e08c", size = 3229054, upload-time = "2025-10-24T19:04:01.949Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/dd/7ac658d54b9fb7999a0ccb07ad863b413cbaf5cf172f48ebcd9497ec7263/hf_xet-1.2.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:4c1428c9ae73ec0939410ec73023c4f842927f39db09b063b9482dac5a3bb737", size = 3413812, upload-time = "2025-10-24T19:04:24.585Z" },
+    { url = "https://files.pythonhosted.org/packages/92/68/89ac4e5b12a9ff6286a12174c8538a5930e2ed662091dd2572bbe0a18c8a/hf_xet-1.2.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a55558084c16b09b5ed32ab9ed38421e2d87cf3f1f89815764d1177081b99865", size = 3508920, upload-time = "2025-10-24T19:04:26.927Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/44/870d44b30e1dcfb6a65932e3e1506c103a8a5aea9103c337e7a53180322c/hf_xet-1.2.0-cp37-abi3-win_amd64.whl", hash = "sha256:e6584a52253f72c9f52f9e549d5895ca7a471608495c4ecaa6cc73dba2b24d69", size = 2905735, upload-time = "2025-10-24T19:04:35.928Z" },
+]
+
 [[package]]
 name = "httpcore"
 version = "1.0.9"
@@ -526,6 +559,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/56/95/9377bcb415797e44274b51d46e3249eba641711cf3348050f76ee7b15ffc/httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0", size = 76395, upload-time = "2024-08-27T12:53:59.653Z" },
 ]
 
+[[package]]
+name = "huggingface-hub"
+version = "1.1.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "filelock" },
+    { name = "fsspec" },
+    { name = "hf-xet", marker = "platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'" },
+    { name = "httpx" },
+    { name = "packaging" },
+    { name = "pyyaml" },
+    { name = "shellingham" },
+    { name = "tqdm" },
+    { name = "typer-slim" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/fb/02/c3d534d7498ba2792da1d2ce56b5d38bbcbcbbba62071c90ee289b408e8d/huggingface_hub-1.1.5.tar.gz", hash = "sha256:40ba5c9a08792d888fde6088920a0a71ab3cd9d5e6617c81a797c657f1fd9968", size = 607199, upload-time = "2025-11-20T15:49:32.809Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/35/f4/124858007ddf3c61e9b144107304c9152fa80b5b6c168da07d86fe583cc1/huggingface_hub-1.1.5-py3-none-any.whl", hash = "sha256:e88ecc129011f37b868586bbcfae6c56868cae80cd56a79d61575426a3aa0d7d", size = 516000, upload-time = "2025-11-20T15:49:30.926Z" },
+]
+
 [[package]]
 name = "idna"
 version = "3.11"
@@ -719,6 +773,7 @@ dependencies = [
     { name = "faiss-cpu" },
     { name = "fastapi" },
     { name = "httpx" },
+    { name = "huggingface-hub" },
     { name = "langchain" },
     { name = "langchain-community" },
     { name = "openai" },
@@ -742,6 +797,7 @@ requires-dist = [
     { name = "faiss-cpu", specifier = "==1.7.4" },
     { name = "fastapi", specifier = "==0.104.1" },
     { name = "httpx", specifier = "==0.27.2" },
+    { name = "huggingface-hub", specifier = ">=0.25.0" },
     { name = "langchain", specifier = "==0.1.16" },
     { name = "langchain-community", specifier = "==0.0.36" },
     { name = "openai", specifier = ">=1.50.0" },
@@ -1403,6 +1459,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3f/51/d4db610ef29373b879047326cbf6fa98b6c1969d6f6dc423279de2b1be2c/requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06", size = 54481, upload-time = "2023-05-01T04:11:28.427Z" },
 ]
 
+[[package]]
+name = "shellingham"
+version = "1.5.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/58/15/8b3609fd3830ef7b27b655beb4b4e9c62313a4e8da8c676e142cc210d58e/shellingham-1.5.4.tar.gz", hash = "sha256:8dbca0739d487e5bd35ab3ca4b36e11c4078f3a234bfce294b0a0291363404de", size = 10310, upload-time = "2023-10-24T04:13:40.426Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755, upload-time = "2023-10-24T04:13:38.866Z" },
+]
+
 [[package]]
 name = "six"
 version = "1.17.0"
@@ -1527,6 +1592,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2", size = 78540, upload-time = "2024-11-24T20:12:19.698Z" },
 ]
 
+[[package]]
+name = "typer-slim"
+version = "0.20.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/8e/45/81b94a52caed434b94da65729c03ad0fb7665fab0f7db9ee54c94e541403/typer_slim-0.20.0.tar.gz", hash = "sha256:9fc6607b3c6c20f5c33ea9590cbeb17848667c51feee27d9e314a579ab07d1a3", size = 106561, upload-time = "2025-10-20T17:03:46.642Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5e/dd/5cbf31f402f1cc0ab087c94d4669cfa55bd1e818688b910631e131d74e75/typer_slim-0.20.0-py3-none-any.whl", hash = "sha256:f42a9b7571a12b97dddf364745d29f12221865acef7a2680065f9bb29c7dc89d", size = 47087, upload-time = "2025-10-20T17:03:44.546Z" },
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.15.0"