semantica/pyproject.toml

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "semantica"
version = "0.4.0"
description = "🧠 Semantica - An Open Source Framework for building Semantic Layers and Knowledge Engineering"
readme = "README.md"
license = { text = "MIT" }

authors = [{ name = "Hawksight AI", email = "semantica-dev@users.noreply.github.com" }]
maintainers = [{ name = "Hawksight AI", email = "semantica-dev@users.noreply.github.com" }]

requires-python = ">=3.8"

classifiers = [
  "Development Status :: 5 - Production/Stable",
  "Intended Audience :: Developers",
  "Intended Audience :: Science/Research",
  "License :: OSI Approved :: MIT License",
  "Operating System :: OS Independent",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.8",
  "Programming Language :: Python :: 3.9",
  "Programming Language :: Python :: 3.10",
  "Programming Language :: Python :: 3.11",
  "Programming Language :: Python :: 3.12",
  "Topic :: Scientific/Engineering :: Artificial Intelligence",
  "Topic :: Software Development :: Libraries :: Python Modules"
]

keywords = [
  "semantic-layer", "knowledge-graph", "nlp", "embeddings",
  "entity-extraction", "relationship-extraction", "rdf", "ontology"
]

# ---------------- CORE DEPENDENCIES (SAFE DEFAULT) ----------------
dependencies = [
  "numpy>=1.21.0",
  "pandas>=1.3.0",
  "scipy>=1.9.0",
  "scikit-learn>=1.0.0",
  "umap-learn>=0.5.0",
  "spacy>=3.4.0",
  "transformers>=4.20.0",
  "torch>=1.12.0",
  "sentence-transformers>=2.2.0",
  "rdflib>=6.2.0",
  "networkx>=2.8.0",
  "matplotlib>=3.5.0",
  "seaborn>=0.11.0",
  "plotly>=5.10.0",
  "ipywidgets>=8.0.0",
  "requests>=2.28.0",
  "GitPython>=3.1.30",
  "chardet>=5.1.0",
  "protobuf>=5.29.1,<7.0",
  "grpcio>=1.71.2",
  "beautifulsoup4>=4.11.0",
  "lxml>=4.9.0",
  "pypdf2>=2.10.0",
  "python-docx>=0.8.11",
  "openpyxl>=3.0.10",
  "pillow>=9.2.0",
  "librosa>=0.9.0",
  "opencv-python>=4.6.0",
  "faiss-cpu>=1.7.0",
  "fastembed>=0.2.0",
  "onnxruntime>=1.17.0",
  "tokenizers>=0.15.0",
  "pydantic>=2.0.0",
  "click>=8.1.0",
  "rich>=12.5.0",
  "tqdm>=4.64.0",
  "pyyaml>=6.0",
  "toml>=0.10.0",
  "python-dotenv>=0.20.0",
  "loguru>=0.6.0",
  "structlog>=22.1.0",
  "gensim>=4.3.0"
]

# ---------------- OPTIONAL DEPENDENCIES ----------------
[project.optional-dependencies]

# ---- LLM Providers ----
llm-openai = ["openai>=1.0.0"]
llm-groq = ["groq>=0.4.0"]
llm-gemini = ["google-genai>=0.1.0"]
llm-anthropic = ["anthropic>=0.18.0"]
llm-ollama = ["ollama>=0.1.0"]
llm-deepseek = ["openai>=1.0.0"]
llm-litellm = ["litellm>=1.0.0"]
llm-instructor = ["instructor>=1.0.0"]

llm-all = [
  "semantica[llm-openai,llm-groq,llm-gemini,llm-anthropic,llm-ollama,llm-deepseek,llm-litellm,llm-instructor]"
]

# ---- Document Parsing ----
parse-docling = ["docling>=1.0.0"]

# ---- Database Connectors ----
db-snowflake = ["snowflake-connector-python>=3.0.0", "cryptography>=3.4.0"]
db-arrow = ["pyarrow>=10.0.0"]

db-all = [
  "semantica[db-snowflake,db-arrow]"
]

# ---- Embedding / Models ----
models-huggingface = [
  "transformers>=4.20.0",
  "torch>=1.12.0"
]

# ---- Graph Backends ----
graph-neo4j = ["neo4j>=5.0.0"]
graph-falkordb = ["falkordb>=1.0.0", "redis>=4.3.0"]
graph-amazon-neptune = ["boto3>=1.24.0", "neo4j>=5.0.0"]

graph-all = [
  "semantica[graph-neo4j,graph-falkordb,graph-amazon-neptune]"
]

# ---- Vector Store Backends ----
vectorstore-qdrant = ["qdrant-client>=1.0.0"]
vectorstore-weaviate = ["weaviate-client>=4.0.0"]
vectorstore-pinecone = ["pinecone-client>=3.0.0"]
vectorstore-milvus = ["pymilvus>=2.0.0"]
vectorstore-pgvector = ["psycopg[binary,pool]>=3.0.0", "pgvector>=0.2.0"]

vectorstore-all = [
  "semantica[vectorstore-qdrant,vectorstore-weaviate,vectorstore-pinecone,vectorstore-milvus,vectorstore-pgvector]"
]

# ---- Infra / Queues / Workers ----
infra = [
  "redis>=4.3.0",
  "celery>=5.2.0",
  "kafka-python>=2.0.0",
  "pulsar-client>=3.0.0",
  "pika>=1.3.0"
]

# ---- Cloud Providers ----
cloud = [
  "boto3>=1.24.0",
  "azure-storage-blob>=12.12.0",
  "google-cloud-storage>=2.5.0"
]

# ---- Monitoring (FIXED) ----
monitoring = [
  "prometheus-client>=0.14.0",
  "opentelemetry-api>=1.30.0,<2.0.0",
  "opentelemetry-sdk>=1.30.0,<2.0.0",
  "opentelemetry-semantic-conventions>=0.58b0,<0.62",
  "opentelemetry-instrumentation>=0.58b0,<0.62"
]

# ---- Visualization ----
viz = [
  "pyvis>=0.3.0",
  "graphviz>=0.20.0",
  "d3blocks>=1.0.0"
]

# ---- GPU ----
gpu = [
  "faiss-gpu>=1.7.0",
  "cupy>=10.0.0"
]

# ---- Agentic Framework Integrations ----
agno = ["agno>=1.0.0"]

# ---- Splitting / Chunking ----
split-tiktoken = ["tiktoken>=0.5.0"]
split-community = ["python-louvain>=0.16"]
split-topic = ["bertopic>=0.15.0", "gensim>=4.3.0"]

split-all = [
  "semantica[split-tiktoken,split-community,split-topic]"
]

# ---- Dev ----
dev = [
  "pytest>=7.1.0",
  "pytest-cov>=3.0.0",
  "pytest-asyncio>=0.19.0",
  "black>=22.6.0",
  "isort>=5.10.0",
  "flake8>=4.0.0",
  "mypy>=0.971",
  "pre-commit>=2.19.0",
  "jupyter>=1.0.0",
  "ipykernel>=6.15.0"
]

# Explorer Dashboard
explorer = [
  "fastapi>=0.100.0",
  "uvicorn[standard]>=0.22.0",
  "websockets>=11.0",
  "python-multipart>=0.0.6"
]
explorer-lite = [
  "streamlit>=1.25.0",
  "streamlit-agraph>=0.0.45"
]

# Everything (cross-platform — gpu excluded; install semantica[gpu] separately on Linux)
all = [
  "semantica[dev,viz,infra,cloud,monitoring,llm-all,models-huggingface,split-all,graph-all,vectorstore-all,parse-docling,explorer]",
  "semantica[dev,viz,infra,cloud,monitoring,llm-all,models-huggingface,split-all,graph-all,vectorstore-all,parse-docling,agno]"
]

# ---------------- ENTRYPOINTS ----------------
[project.scripts]
semantica = "semantica.cli:main"
semantica-server = "semantica.server:main"
semantica-worker = "semantica.worker:main"
semantica-explorer = "semantica.explorer:main"

# ---------------- TOOLING ----------------
[tool.setuptools.packages.find]
where = ["."]
include = ["semantica*", "integrations*"]

[tool.black]
line-length = 88

[tool.isort]
profile = "black"

[tool.pytest.ini_options]
testpaths = ["tests"]
markers = [
    "integration: marks tests that require external services or API keys (deselect with '-m not integration')",
]