cherry-pick c46c1b26

lightrag/api/routers/document_routes.py

@@ -1061,6 +1061,8 @@ async def pipeline_enqueue_file(
                         else:
                             if not pm.is_installed("pypdf2"):  # type: ignore
                                 pm.install("pypdf2")
+                            if not pm.is_installed("pycryptodome"):  # type: ignore
+                                pm.install("pycryptodome")
                             from PyPDF2 import PdfReader  # type: ignore
                             from io import BytesIO
 

pyproject.toml

@@ -24,12 +24,10 @@ dependencies = [
     "aiohttp",
     "configparser",
     "future",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
     "json_repair",
     "nano-vectordb",
     "networkx",
-    "numpy>=1.24.0,<2.0.0",
+    "numpy",
     "pandas>=2.0.0,<2.4.0",
     "pipmaster",
     "pydantic",
@@ -42,13 +40,6 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-# Test framework dependencies (for CI/CD and testing)
-pytest = [
-    "pytest>=8.4.2",
-    "pytest-asyncio>=1.2.0",
-    "pre-commit",
-]
-
 api = [
     # Core dependencies
     "aiohttp",
@@ -57,8 +48,8 @@ api = [
     "json_repair",
     "nano-vectordb",
     "networkx",
-    "numpy>=1.24.0,<2.0.0",
+    "numpy",
-    "openai>=2.0.0,<3.0.0",
+    "openai>=1.0.0,<3.0.0",
     "pandas>=2.0.0,<2.4.0",
     "pipmaster",
     "pydantic",
@@ -68,8 +59,6 @@ api = [
     "tenacity",
     "tiktoken",
     "xlsxwriter>=3.1.0",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
     # API-specific dependencies
     "aiofiles",
     "ascii_colors",
@@ -86,23 +75,18 @@ api = [
     "python-multipart",
     "pytz",
     "uvicorn",
-    "gunicorn",
-    # Document processing dependencies (required for API document upload functionality)
-    "openpyxl>=3.0.0,<4.0.0",      # XLSX processing
-    "pycryptodome>=3.0.0,<4.0.0",  # PDF encryption support
-    "pypdf>=6.1.0",                 # PDF processing
-    "python-docx>=0.8.11,<2.0.0",  # DOCX processing
-    "python-pptx>=0.6.21,<2.0.0",  # PPTX processing
-]
-
-# Advanced document processing engine (optional)
-docling = [
-    # On macOS, pytorch and frameworks use Objective-C are not fork-safe,
-    # and not compatible to gunicorn multi-worker mode
-    "docling>=2.0.0,<3.0.0; sys_platform != 'darwin'",
 ]
 
 # Offline deployment dependencies (layered design for flexibility)
+offline-docs = [
+    # Document processing dependencies
+    "openpyxl>=3.0.0,<4.0.0",
+    "pycryptodome>=3.0.0,<4.0.0",
+    "pypdf2>=3.0.0",
+    "python-docx>=0.8.11,<2.0.0",
+    "python-pptx>=0.6.21,<2.0.0",
+]
+
 offline-storage = [
     # Storage backend dependencies
     "redis>=5.0.0,<8.0.0",
@@ -110,48 +94,29 @@ offline-storage = [
     "pymilvus>=2.6.2,<3.0.0",
     "pymongo>=4.0.0,<5.0.0",
     "asyncpg>=0.29.0,<1.0.0",
-    "qdrant-client>=1.11.0,<2.0.0",
+    "qdrant-client>=1.7.0,<2.0.0",
 ]
 
 offline-llm = [
     # LLM provider dependencies
-    "openai>=2.0.0,<3.0.0",
+    "openai>=1.0.0,<3.0.0",
     "anthropic>=0.18.0,<1.0.0",
     "ollama>=0.1.0,<1.0.0",
     "zhipuai>=2.0.0,<3.0.0",
     "aioboto3>=12.0.0,<16.0.0",
     "voyageai>=0.2.0,<1.0.0",
     "llama-index>=0.9.0,<1.0.0",
-    "google-api-core>=2.0.0,<3.0.0",
-    "google-genai>=1.0.0,<2.0.0",
 ]
 
 offline = [
-    # Complete offline package (includes api for document processing, plus storage and LLM)
+    # Complete offline package (includes all offline dependencies)
-    "lightrag-hku[api,offline-storage,offline-llm]",
+    "lightrag-hku[offline-docs,offline-storage,offline-llm]",
-]
-
-evaluation = [
-    # Test framework dependencies (for evaluation)
-    "pytest>=8.4.2",
-    "pytest-asyncio>=1.2.0",
-    "pre-commit",
-    # RAG evaluation dependencies (RAGAS framework)
-    "ragas>=0.3.7",
-    "datasets>=4.3.0",
-    "httpx>=0.28.1",
-]
-
-observability = [
-    # LLM observability and tracing dependencies
-    "langfuse>=3.8.1",
 ]
 
 [project.scripts]
 lightrag-server = "lightrag.api.lightrag_server:main"
 lightrag-gunicorn = "lightrag.api.run_with_gunicorn:main"
 lightrag-download-cache = "lightrag.tools.download_cache:main"
-lightrag-clean-llmqc = "lightrag.tools.clean_llm_query_cache:main"
 
 [project.urls]
 Homepage = "https://github.com/HKUDS/LightRAG"
@@ -172,13 +137,5 @@ version = {attr = "lightrag.__version__"}
 [tool.setuptools.package-data]
 lightrag = ["api/webui/**/*", "api/static/**/*"]
 
-[tool.pytest.ini_options]
-asyncio_mode = "auto"
-asyncio_default_fixture_loop_scope = "function"
-testpaths = ["tests"]
-python_files = ["test_*.py"]
-python_classes = ["Test*"]
-python_functions = ["test_*"]
-
 [tool.ruff]
 target-version = "py310"

requirements-offline-docs.txt

@@ -9,6 +9,7 @@
 
 # Document processing dependencies (with version constraints matching pyproject.toml)
 openpyxl>=3.0.0,<4.0.0
+pycryptodome>=3.0.0,<4.0.0
 pypdf2>=3.0.0
 python-docx>=0.8.11,<2.0.0
 python-pptx>=0.6.21,<2.0.0

requirements-offline.txt

@@ -20,6 +20,7 @@ neo4j>=5.0.0,<7.0.0
 ollama>=0.1.0,<1.0.0
 openai>=2.0.0,<3.0.0
 openpyxl>=3.0.0,<4.0.0
+pycryptodome>=3.0.0,<4.0.0
 pymilvus>=2.6.2,<3.0.0
 pymongo>=4.0.0,<5.0.0
 pypdf2>=3.0.0