Add offline deployment support with cache management and layered deps

• Add tiktoken cache downloader CLI
• Add layered offline dependencies
• Add offline requirements files
• Add offline deployment guide

(cherry picked from commit a5c05f1b92)
This commit is contained in:
yangdx 2025-10-11 10:28:14 +08:00 committed by Raphaël MANSUY
parent e19a4be0af
commit 6bd5b2d95b
4 changed files with 68 additions and 110 deletions

View file

@ -23,13 +23,13 @@ classifiers = [
dependencies = [
"aiohttp",
"configparser",
"google-api-core>=2.0.0,<3.0.0",
"google-genai>=1.0.0,<2.0.0",
"dotenv",
"future",
"json_repair",
"nano-vectordb",
"networkx",
"numpy>=1.24.0,<2.0.0",
"pandas>=2.0.0,<2.4.0",
"numpy",
"pandas>=2.0.0",
"pipmaster",
"pydantic",
"pypinyin",
@ -41,24 +41,18 @@ dependencies = [
]
[project.optional-dependencies]
# Test framework dependencies (for CI/CD and testing)
pytest = [
"pytest>=8.4.2",
"pytest-asyncio>=1.2.0",
"pre-commit",
"ruff",
]
api = [
# Core dependencies
"aiohttp",
"configparser",
"dotenv",
"future",
"json_repair",
"nano-vectordb",
"networkx",
"numpy>=1.24.0,<2.0.0",
"openai>=2.0.0,<3.0.0",
"pandas>=2.0.0,<2.4.0",
"numpy",
"openai",
"pandas>=2.0.0",
"pipmaster",
"pydantic",
"pypinyin",
@ -67,8 +61,6 @@ 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",
@ -78,80 +70,57 @@ api = [
"httpcore",
"httpx",
"jiter",
"bcrypt>=4.0.0",
"passlib[bcrypt]",
"psutil",
"PyJWT>=2.8.0,<3.0.0",
"PyJWT",
"python-jose[cryptography]",
"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
"docling>=1.0.0",
"pypdf2>=3.0.0",
"python-docx>=0.8.11",
"python-pptx>=0.6.21",
"openpyxl>=3.0.0",
]
offline-storage = [
# Storage backend dependencies
"redis>=5.0.0,<8.0.0",
"neo4j>=5.0.0,<7.0.0",
"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",
"redis>=5.0.0",
"neo4j>=5.0.0",
"pymilvus==2.5.2",
"pymongo>=4.0.0",
"asyncpg>=0.29.0",
"qdrant-client>=1.7.0",
]
offline-llm = [
# LLM provider dependencies
"openai>=2.0.0,<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",
"openai>=1.0.0",
"anthropic>=0.18.0",
"ollama>=0.1.0",
"zhipuai>=2.0.0",
"aioboto3>=12.0.0",
"voyageai>=0.2.0",
"llama-index>=0.9.0",
"transformers>=4.30.0",
"torch>=2.0.0",
]
offline = [
# Complete offline package (includes api for document processing, plus storage and LLM)
"lightrag-hku[api,offline-storage,offline-llm]",
]
evaluation = [
# Test framework dependencies
"pytest>=8.4.2",
"pytest-asyncio>=1.2.0",
"pre-commit",
"ruff",
# 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",
# Complete offline package (includes all offline dependencies)
"lightrag-hku[offline-docs,offline-storage,offline-llm]",
]
[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"
@ -161,7 +130,6 @@ Repository = "https://github.com/HKUDS/LightRAG"
[tool.setuptools.packages.find]
include = ["lightrag*"]
exclude = ["data*", "tests*", "scripts*", "examples*", "dickens*", "reproduce*", "output_complete*", "rag_storage*", "inputs*"]
[tool.setuptools]
include-package-data = true
@ -170,15 +138,7 @@ include-package-data = true
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_*"]
lightrag = ["api/webui/**/*"]
[tool.ruff]
target-version = "py310"

View file

@ -3,12 +3,10 @@
# For offline installation:
# pip download -r requirements-offline-docs.txt -d ./packages
# pip install --no-index --find-links=./packages -r requirements-offline-docs.txt
#
# Recommended: Use pip install lightrag-hku[offline-docs] for the same effect
# Or use constraints: pip install --constraint constraints-offline.txt -r requirements-offline-docs.txt
# Document processing dependencies (with version constraints matching pyproject.toml)
openpyxl>=3.0.0,<4.0.0
# Document processing dependencies
docling>=1.0.0
openpyxl>=3.0.0
pypdf2>=3.0.0
python-docx>=0.8.11,<2.0.0
python-pptx>=0.6.21,<2.0.0
python-docx>=0.8.11
python-pptx>=0.6.21

View file

@ -6,7 +6,7 @@
asyncpg>=0.29.0
neo4j>=5.0.0
pymilvus>=2.6.2
pymilvus==2.5.2
pymongo>=4.0.0
qdrant-client>=1.7.0
# Storage backend dependencies

View file

@ -4,30 +4,30 @@
# pip download -r requirements-offline.txt -d ./packages
# pip install --no-index --find-links=./packages -r requirements-offline.txt
#
# Recommended: Use pip install lightrag-hku[offline] for the same effect
# Or use constraints: pip install --constraint constraints-offline.txt -r requirements-offline.txt
# Or use pip install lightrag-hku[offline] for the same effect
# LLM provider dependencies (with version constraints matching pyproject.toml)
aioboto3>=12.0.0,<16.0.0
anthropic>=0.18.0,<1.0.0
aioboto3>=12.0.0
anthropic>=0.18.0
asyncpg>=0.29.0
# Document processing dependencies
docling>=1.0.0
llama-index>=0.9.0
neo4j>=5.0.0
ollama>=0.1.0
# LLM provider dependencies
openai>=1.0.0
openpyxl>=3.0.0
pymilvus==2.5.2
pymongo>=4.0.0
pypdf2>=3.0.0
python-docx>=0.8.11
python-pptx>=0.6.21
qdrant-client>=1.7.0
# Storage backend dependencies
asyncpg>=0.29.0,<1.0.0
# Document processing dependencies
llama-index>=0.9.0,<1.0.0
neo4j>=5.0.0,<7.0.0
ollama>=0.1.0,<1.0.0
openai>=1.0.0,<2.0.0
openpyxl>=3.0.0,<4.0.0
pymilvus>=2.6.2,<3.0.0
pymongo>=4.0.0,<5.0.0
pypdf2>=3.0.0
python-docx>=0.8.11,<2.0.0
python-pptx>=0.6.21,<2.0.0
qdrant-client>=1.7.0,<2.0.0
redis>=5.0.0,<7.0.0
torch>=2.0.0,<2.3.0
transformers>=4.30.0,<5.0.0
voyageai>=0.2.0,<1.0.0
zhipuai>=2.0.0,<3.0.0
redis>=5.0.0
torch>=2.0.0
transformers>=4.30.0
voyageai>=0.2.0
zhipuai>=2.0.0