chore: optimize dependencies (#11)

Author: bsbds

README.md

@@ -2,29 +2,24 @@
 
 ### Installations
 
-- pip
+CPU-only (default):
 
-    ``` bassh
-    pip install deepdoc-lib --extra-index-url https://huangpustar.github.io/deepdoc-lib/simple
-    ```
-
-- pyproject
+```bash
+pip install git+https://github.com/xorbitsai/deepdoc-lib
+```
 
-    Add the following to pyproject.toml
+GPU (Linux x86_64 only):
 
-    For uv:
+```bash
+pip install "deepdoc-lib[gpu] @ git+https://github.com/xorbitsai/deepdoc-lib"
+```
 
-    ```toml
-    [[tool.uv.index]]
-    name = "deepdoc"
-    url = "https://huangpustar.github.io/deepdoc-lib/simple"
+Note: `onnxruntime` (CPU) and `onnxruntime-gpu` should not be installed together. If you're switching an existing environment to GPU, uninstall CPU ORT first:
 
-    [project]
-    dependencies = [
-        "deepdoc-lib",
-    ]
-    ```
-    ```
+```bash
+pip uninstall -y onnxruntime
+pip install onnxruntime-gpu==1.19.2
+```
 
 ### Parser Usage
 

deepdoc/common/misc_utils.py

@@ -18,15 +18,16 @@
 
 logger = logging.getLogger(__name__)
 
+
 def pip_install_torch():
     """
     Install torch based on system configuration.
     This is a simplified version for the independent library.
     """
     try:
         import torch
+
         logger.info("PyTorch is already installed")
         return True
     except ImportError:
-        logger.warning("PyTorch not found. Please install manually: pip install torch")
         return False

pyproject.toml

@@ -12,148 +12,61 @@ readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
     "datrie==0.8.2",
-    "akshare>=1.15.78,<2.0.0",
-    "azure-storage-blob==12.22.0",
-    "azure-identity==1.17.1",
-    "azure-storage-file-datalake==12.16.0",
     "anthropic==0.69.0",
-    "arxiv==2.1.3",
-    "aspose-slides>=24.9.0,<25.0.0; platform_machine == 'x86_64' or (sys_platform == 'darwin' and platform_machine == 'arm64')",
     "beartype>=0.18.5,<0.19.0",
-    "bio==1.7.1",
-    "blinker==1.7.0",
-    "boto3==1.34.140",
-    "botocore==1.34.140",
-    "cachetools==5.3.3",
+    "beautifulsoup4>=4.12.0",
     "chardet==5.2.0",
-    "cn2an==0.5.22",
-    "cohere==5.6.2",
-    "dashscope==1.20.11",
-    "deepl==1.18.0",
     "demjson3==3.0.6",
-    "discord-py==2.3.2",
-    "duckduckgo-search>=7.2.0,<8.0.0",
-    "editdistance==0.8.1",
-    "elastic-transport==8.12.0",
-    "elasticsearch==8.12.1",
-    "elasticsearch-dsl==8.12.0",
-    "filelock==3.15.4",
-    "flask==3.0.3",
-    "flask-cors==5.0.0",
-    "flask-login==0.6.3",
-    "flask-session==0.8.0",
-    "google-search-results==2.4.2",
-    "groq==0.9.0",
     "hanziconv==0.3.2",
-    "html-text==0.6.2",
-    "httpx[socks]==0.27.2",
-    "huggingface-hub>=0.25.0,<0.26.0",
-    "infinity-emb>=0.0.66,<0.0.67",
-    "itsdangerous==2.1.2",
-    "json-repair==0.35.0",
+    "html5lib>=1.1",
+    "jinja2>=3.1.0",
     "markdown==3.6",
-    "markdown-to-json==2.1.1",
-    "minio==7.2.4",
-    "mistralai==0.4.2",
     "nltk==3.9.1",
     "numpy>=1.26.0,<2.0.0",
     "ollama==0.2.1",
-    "onnxruntime==1.19.2; sys_platform == 'darwin' or platform_machine != 'x86_64'",
-    "onnxruntime-gpu==1.19.2; sys_platform != 'darwin' and platform_machine == 'x86_64'",
+    "onnxruntime==1.19.2",
     "openai>=1.45.0",
     "opencv-python==4.10.0.84",
     "opencv-python-headless==4.10.0.84",
     "openpyxl>=3.1.0,<4.0.0",
-    "opendal>=0.45.0,<0.46.0",
     "pandas>=2.2.0,<3.0.0",
     "pdfplumber==0.10.4",
-    "peewee==3.17.1",
     "pillow>=11.0.0",
-    "protobuf>=5.27.2",
-    "psycopg2-binary==2.9.9",
     "pyclipper==1.3.0.post5",
-    "pycryptodomex==3.20.0",
-    "pymysql>=1.1.1,<2.0.0",
     "pypdf==6.0.0",
-    "python-dotenv==1.0.1",
-    "python-dateutil==2.8.2",
     "python-pptx>=1.0.2,<2.0.0",
-    "pywencai==0.12.2",
-    "qianfan==0.4.6",
-    "ranx==0.3.20",
-    "readability-lxml==0.8.1",
-    "valkey==6.0.2",
+    "python-docx>=1.1.2,<2.0.0",
+    "pyyaml>=6.0.0",
     "requests==2.32.2",
-    "replicate==0.31.0",
-    "roman-numbers==1.0.2",
-    "ruamel-base==1.0.0",
-    "ruamel-yaml>=0.18.6,<0.19.0",
-    "scholarly==1.7.11",
     "scikit-learn==1.5.0",
-    "selenium==4.22.0",
-    "selenium-wire==5.1.0",
-    "setuptools>=75.2.0,<76.0.0",
     "shapely==2.0.5",
     "six==1.16.0",
     "strenum==0.4.15",
-    "tabulate==0.9.0",
-    "tavily-python==0.5.1",
     "tencentcloud-sdk-python==3.0.1215",
-    "tika==2.6.0",
     "tiktoken>=0.7.0",
-    "umap_learn==0.5.6",
-    "vertexai==1.64.0",
-    "volcengine==1.0.194",
-    "voyageai==0.2.3",
-    "webdriver-manager==4.0.1",
-    "werkzeug==3.0.6",
-    "wikipedia==1.4.0",
-    "word2number==1.1",
     "xgboost==1.6.0",
     "xpinyin==0.7.6",
-    "yfinance==0.2.65",
     "zhipuai==2.0.1",
     "google-generativeai>=0.8.1,<0.9.0",
-    "python-docx>=1.1.2,<2.0.0",
-    "pypdf2>=3.0.1,<4.0.0",
-    "graspologic>=3.4.1,<4.0.0",
-    "mini-racer>=0.12.4,<0.13.0",
-    "pyodbc>=5.2.0,<6.0.0",
-    "flasgger>=0.9.7.1,<0.10.0",
-    "xxhash>=3.5.0,<4.0.0",
     "trio>=0.29.0",
-    "langfuse>=2.60.0",
-    "debugpy>=1.8.13",
-    "mcp>=1.9.4",
-    "opensearch-py==2.7.1",
-    "pluginlib==0.9.4",
-    "click>=8.1.8",
-    "python-calamine>=0.4.0",
-    "litellm>=1.74.15.post1",
-    "flask-mail>=0.10.0",
-    "lark>=1.2.2",
-    "torch",
+    "setuptools>=75.2.0,<76.0.0",
+    "huggingface-hub>=0.25.0,<0.26.0",
 ]
 
 [project.optional-dependencies]
-full = [
-    "bcembedding==0.1.5",
-    "flagembedding==1.2.10",
-    "torch>=2.5.0,<3.0.0",
-    "transformers>=4.35.0,<5.0.0",
+gpu = [
+    "onnxruntime-gpu==1.19.2; sys_platform != 'darwin' and platform_machine == 'x86_64'",
+    "torch",
 ]
 
 [dependency-groups]
 test = [
-    "hypothesis>=6.132.0",
     "openpyxl>=3.1.5",
     "pillow>=10.4.0",
     "pytest>=8.3.5",
     "python-docx>=1.1.2",
     "python-pptx>=1.0.2",
-    "reportlab>=4.4.1",
     "requests>=2.32.2",
-    "requests-toolbelt>=1.0.0",
 ]
 
 [tool.setuptools]