Metadata-Version: 2.4
Name: semantic-service
Version: 0.0.1
Summary: Unified semantic layer for better business decision.
Requires-Python: <3.14,>=3.10
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.28.0
Requires-Dist: mysql-connector-python>=8.0.0
Requires-Dist: apscheduler>=3.10.0
Requires-Dist: openai>=1.0.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: openai>=1.40.0
Requires-Dist: python-dotenv>=1.0.1
Requires-Dist: PyYAML>=6.0.2
Requires-Dist: PyMuPDF>=1.24.0
Requires-Dist: PyPDF2>=3.0.1
Requires-Dist: pycryptodome>=3.20.0
Requires-Dist: psycopg[binary]>=3.2.0
Requires-Dist: litellm>=1.51.0
Requires-Dist: fastapi>=0.115.0
Requires-Dist: uvicorn>=0.30.0
Requires-Dist: python-multipart>=0.0.9
Requires-Dist: loguru>=0.7.3
Requires-Dist: pydantic>=2.0
Requires-Dist: pydantic-settings>=2.0
Requires-Dist: networkx>=3.0
Requires-Dist: langchain-openai>=0.1.0
Requires-Dist: ray[data]>=2.9.0
Provides-Extra: unstructured
Requires-Dist: fastapi>=0.116.1; extra == "unstructured"
Requires-Dist: uvicorn>=0.35.0; extra == "unstructured"
Requires-Dist: python-multipart>=0.0.20; extra == "unstructured"
Requires-Dist: pdfplumber>=0.11.7; extra == "unstructured"
Provides-Extra: omniextractor
Requires-Dist: pypdfium2>=4.0.0; extra == "omniextractor"
Requires-Dist: Pillow>=10.0.0; extra == "omniextractor"
Requires-Dist: httpx>=0.27.0; extra == "omniextractor"
Requires-Dist: mineru[pipeline]; extra == "omniextractor"
Requires-Dist: docling>=2.0.0; extra == "omniextractor"
Requires-Dist: pypptx-with-oxml>=1.0.0; extra == "omniextractor"
Provides-Extra: tests
Requires-Dist: pytest-cov>=4.0.0; extra == "tests"
Requires-Dist: pytest>=9.0.2; extra == "tests"
Requires-Dist: pytestarch>=4.0.1; extra == "tests"
Requires-Dist: diff_cover; extra == "tests"
Requires-Dist: httpx>=0.27.0; extra == "tests"
Provides-Extra: dev
Requires-Dist: black>=24.0.0; extra == "dev"
Requires-Dist: coverage>=7.0.0; extra == "dev"
Requires-Dist: isort>=5.13.0; extra == "dev"
Requires-Dist: mypy>=1.14.0; extra == "dev"
Requires-Dist: pre-commit>=4.0.0; extra == "dev"
Requires-Dist: ruff>=0.8.0; extra == "dev"
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: shellcheck-py>=0.10.0.1; extra == "dev"
Provides-Extra: examples
Requires-Dist: openai-agents==0.10.5; extra == "examples"
Provides-Extra: all
Requires-Dist: semantic-construct[omniextractor,unstructured]; extra == "all"

# SemanticConstruct

语义建模。

## DocArbor

DocArbor is the long-document tree indexing and retrieval package in this repository.
Its source code is physically located under:

```text
src/semantic_construct/core/knowledge/augmentation/docarbor/
```

It is still exposed as the public Python package and CLI name `docarbor`.

Start here:

- [DocArbor README](docs/docarbor/README.md): capabilities, configuration, CLI usage, and API examples.
- [DocArbor contributing guide](docs/docarbor/CONTRIBUTING.md): first-time developer setup, local checks, formatting, and commit conventions.
- [DocArbor REST API](docs/docarbor/REST_API.md): service endpoints, runtime capability discovery, documents, and jobs.
- [DocArbor design notes](docs/docarbor/docarbor_project_design.md): architecture and pipeline details.
- [FinanceBench guide](bench/FinanceBench/README.md): local benchmark data preparation and evaluation commands.
