mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-29 04:26:20 +00:00
* security(deps): bump fastapi floor to >=0.109.1 (PYSEC-2024-38) The [explorer] extra declared fastapi>=0.100.0, which allows the vulnerable 0.109.0 (PYSEC-2024-38, HTTP response splitting). Raise the floor to 0.109.1, the patched release. One-line change, no functional impact -- the 0.109.x API is stable and backward-compatible. Fixes #869 * fix(deps): bump fastapi to >=0.109.2 and python-multipart to >=0.0.7 for PYSEC-2024-38 PYSEC-2024-38 (CVE-2024-24762 / GHSA-2jv5-9r88-3w3p) is a ReDoS in python-multipart < 0.0.7: an attacker sends a crafted Content-Type header that causes catastrophic backtracking in the multipart regex, stalling the event loop and causing a DoS on any endpoint that parses form data. The original PR bumped fastapi to >=0.109.1, but that version pins starlette<0.36.0,>=0.35.0 and cannot install starlette 0.36.2+ (which contains the fix via python-multipart>=0.0.7). FastAPI 0.109.2 is the first version that pins starlette>=0.36.3 (verified against PyPI metadata). Two changes are necessary: 1. fastapi>=0.109.1 -> fastapi>=0.109.2: ensures starlette>=0.36.3 is installed as a transitive dependency, which in turn pulls the fixed python-multipart>=0.0.7. 2. python-multipart>=0.0.6 -> python-multipart>=0.0.7: closes the direct dependency path. python-multipart is listed explicitly in the explorer extra, so without this floor a resolver could still install 0.0.6 and leave the vulnerability present even with the fastapi bump. The fix targets only the 'explorer' optional dependency group, which is the only code surface where FastAPI and form-data parsing are used. No functional API changes between 0.109.1 and 0.109.2; 239 Explorer tests pass without modification. * ci(security): gate pip-audit on explorer-extra dependency PRs, add changelog entry for PYSEC-2024-38 The Security workflow's pip-audit job ran weekly against a bare Python env with none of Semantica's optional extras installed, and always continue-on-error'd -- it would never have flagged the vulnerable fastapi/python-multipart floors this PR fixes, or the first attempt at the fix that left python-multipart>=0.0.6 in place. security-scan.yml's Safety check has the same blind spot (only installs [llm-litellm]). pip-audit now also runs on pull_request when pyproject.toml changes, installs semantica[all] so it can actually see extras like [explorer], and fails the build on findings for that trigger. Scheduled/dispatch runs stay non-blocking pending a full pass over the [all] tree. Also documents the fix (#871, closes #869) in CHANGELOG.md, including the correction made during review after the original fastapi-only bump turned out not to close the vulnerability. * fix(deps): raise setuptools floor to >=83.0.0 (CVE-2026-59890), harden audit env The new pull_request pip-audit gate (previous commit) caught this on its first run: pip install -e ".[all]" resolved setuptools==79.0.1, vulnerable to CVE-2026-59890 / GHSA-h35f-9h28-mq5c / PYSEC-2026-3447 (Unicode normalization lets a MANIFEST.in exclude/prune pattern be bypassed on macOS APFS/HFS+, leaking excluded files into a built sdist). Fixed in setuptools 83.0.0. [build-system] requires had the same too-permissive floor this whole PR is about (setuptools>=61.0). Raised to >=83.0.0. Also upgrade pip/ setuptools explicitly in the Security workflow before running pip-audit, since [build-system] requires only governs isolated build environments, not the ambient one actions/setup-python provisions and pip-audit scans. --------- Co-authored-by: Sameer Kadam <sskadam6305@gmail.com> Co-authored-by: KaifAhmad1 <kaifahmad087@gmail.com>
279 lines
7.9 KiB
TOML
279 lines
7.9 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=83.0.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "semantica"
|
|
version = "0.6.5"
|
|
description = "Accountability and context layer for AI agents. Context graphs, decision intelligence, full provenance tracking, and explainable reasoning engines — every AI decision traceable, every output auditable."
|
|
readme = "README.md"
|
|
license = { text = "MIT" }
|
|
|
|
authors = [{ name = "Semantica", email = "kaif@getsemantica.ai" }]
|
|
maintainers = [{ name = "Semantica", email = "kaif@getsemantica.ai" }]
|
|
|
|
requires-python = ">=3.8"
|
|
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Intended Audience :: Information Technology",
|
|
"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 :: Scientific/Engineering :: Information Analysis",
|
|
"Topic :: Text Processing :: Linguistic",
|
|
"Topic :: Database :: Database Engines/Servers",
|
|
"Topic :: Software Development :: Libraries :: Python Modules"
|
|
]
|
|
|
|
keywords = [
|
|
"knowledge-graph", "context-graph", "ai-agents", "llm", "decision-intelligence",
|
|
"provenance", "explainability", "reasoning-engine", "entity-extraction",
|
|
"relation-extraction", "graph-rag", "knowledge-intelligence", "semantic-layer",
|
|
"nlp", "embeddings", "ontology", "rdf", "triplet-extraction", "agentic-ai",
|
|
"knowledge-base", "entity-resolution", "w3c-prov", "audit-trail"
|
|
]
|
|
|
|
# ---------------- CORE DEPENDENCIES (SAFE DEFAULT) ----------------
|
|
dependencies = [
|
|
"numpy>=2.0.2",
|
|
"pandas>=1.3.0",
|
|
"scipy>=1.13.1",
|
|
"scikit-learn>=1.7.2",
|
|
"umap-learn>=0.5.12",
|
|
"spacy>=3.4.0",
|
|
"transformers>=4.20.0",
|
|
"torch>=1.13.1",
|
|
"sentence-transformers>=2.2.0",
|
|
"rdflib>=6.2.0",
|
|
"networkx>=2.8.0",
|
|
"matplotlib>=3.9.4",
|
|
"seaborn>=0.13.2",
|
|
"plotly>=6.8.0",
|
|
"ipywidgets>=8.0.0",
|
|
"requests>=2.34.2",
|
|
"GitPython>=3.1.50",
|
|
"chardet>=7.4.3",
|
|
"protobuf>=5.29.1,<8.0",
|
|
"grpcio>=1.81.1",
|
|
"beautifulsoup4>=4.15.0",
|
|
"lxml>=6.1.1",
|
|
"python-docx>=1.2.0",
|
|
"openpyxl>=3.1.5",
|
|
"pillow>=12.2.0",
|
|
"librosa>=0.9.0",
|
|
"opencv-python>=4.13.0.92",
|
|
"faiss-cpu>=1.7.0",
|
|
"fastembed>=0.2.0",
|
|
"onnxruntime>=1.20.1",
|
|
"tokenizers>=0.15.0",
|
|
"pydantic>=2.13.4",
|
|
"click>=8.4.2",
|
|
"rich>=12.5.0",
|
|
"tqdm>=4.68.3",
|
|
"pyyaml>=6.0",
|
|
"toml>=0.10.0",
|
|
"python-dotenv>=1.2.1",
|
|
"loguru>=0.7.3",
|
|
"structlog>=22.1.0",
|
|
"gensim>=4.4.0",
|
|
"httpx<0.29.0"
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://getsemantica.ai"
|
|
Documentation = "https://docs.getsemantica.ai"
|
|
Repository = "https://github.com/semantica-agi/semantica"
|
|
Changelog = "https://github.com/semantica-agi/semantica/blob/main/CHANGELOG.md"
|
|
"Bug Tracker" = "https://github.com/semantica-agi/semantica/issues"
|
|
Discord = "https://discord.gg/sV34vps5hH"
|
|
|
|
# ---------------- 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>=1.83.9"]
|
|
llm-instructor = ["instructor>=1.15.3"]
|
|
|
|
llm-all = [
|
|
"semantica[llm-openai,llm-groq,llm-gemini,llm-anthropic,llm-ollama,llm-deepseek,llm-litellm,llm-instructor]"
|
|
]
|
|
|
|
# ---- Document Parsing ----
|
|
parse-docling = ["docling>=2.107.0"]
|
|
|
|
# ---- SHACL Validation ----
|
|
shacl = ["pyshacl>=0.25.0"]
|
|
|
|
# ---- Database Connectors ----
|
|
db-snowflake = ["snowflake-connector-python>=4.6.0", "cryptography>=49.0.0"]
|
|
db-databricks = ["databricks-sdk>=0.60.0", "databricks-sql-connector>=4.0.0"]
|
|
db-arrow = ["pyarrow>=24.0.0"]
|
|
ingest-parquet = ["pyarrow>=24.0.0"]
|
|
ingest-arrow = ["pyarrow>=24.0.0"]
|
|
|
|
db-all = [
|
|
"semantica[db-snowflake,db-databricks,db-arrow]"
|
|
]
|
|
|
|
# ---- Embedding / Models ----
|
|
models-huggingface = [
|
|
"transformers>=4.20.0",
|
|
"torch>=1.13.1"
|
|
]
|
|
|
|
# ---- 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-apache-age = ["psycopg2-binary>=2.9.0"]
|
|
|
|
graph-all = [
|
|
"semantica[graph-neo4j,graph-falkordb,graph-amazon-neptune,graph-apache-age]"
|
|
]
|
|
|
|
# ---- Triplet Store Backends ----
|
|
tripletstore-oxigraph = ["pyoxigraph>=0.5.0"]
|
|
|
|
# ---- 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-sqlite = ["sqlite-vec>=0.1.1"]
|
|
|
|
vectorstore-all = [
|
|
"semantica[vectorstore-qdrant,vectorstore-weaviate,vectorstore-pinecone,vectorstore-milvus,vectorstore-pgvector,vectorstore-sqlite]"
|
|
]
|
|
|
|
# ---- Infra / Queues / Workers ----
|
|
infra = [
|
|
"redis>=4.3.0",
|
|
"celery>=5.2.0",
|
|
"kafka-python>=3.0.2",
|
|
"pulsar-client>=3.0.0",
|
|
"pika>=1.3.0"
|
|
]
|
|
|
|
# ---- Cloud Providers ----
|
|
cloud = [
|
|
"boto3>=1.24.0",
|
|
"azure-storage-blob>=12.30.0",
|
|
"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,<0.65",
|
|
"opentelemetry-instrumentation>=0.62b1,<0.65"
|
|
]
|
|
|
|
# ---- Visualization ----
|
|
viz = [
|
|
"pyvis>=0.3.0",
|
|
"graphviz>=0.21",
|
|
"d3blocks>=1.0.0"
|
|
]
|
|
|
|
# ---- GPU ----
|
|
gpu = [
|
|
"faiss-gpu>=1.7.0",
|
|
"cupy>=10.0.0"
|
|
]
|
|
|
|
# ---- Agentic Framework Integrations ----
|
|
agno = ["agno>=1.0.0"]
|
|
|
|
# ---- File Watching ----
|
|
watch = ["watchdog>=6.0.0"]
|
|
|
|
# ---- Splitting / Chunking ----
|
|
split-tiktoken = ["tiktoken>=0.5.0"]
|
|
split-community = ["python-louvain>=0.16"]
|
|
split-topic = ["bertopic>=0.15.0", "gensim>=4.4.0"]
|
|
|
|
split-all = [
|
|
"semantica[split-tiktoken,split-community,split-topic]"
|
|
]
|
|
|
|
# ---- Dev ----
|
|
dev = [
|
|
"pytest>=7.1.0",
|
|
"pytest-cov>=7.1.0",
|
|
"pytest-asyncio>=0.19.0",
|
|
"black>=22.6.0",
|
|
"isort>=6.1.0",
|
|
"flake8>=4.0.0",
|
|
"mypy>=0.971",
|
|
"pre-commit>=4.6.0",
|
|
"jupyter>=1.0.0",
|
|
"ipykernel>=6.15.0"
|
|
]
|
|
|
|
# Explorer Dashboard
|
|
explorer = [
|
|
"fastapi>=0.109.2",
|
|
"uvicorn[standard]>=0.22.0",
|
|
"websockets>=15.0.1",
|
|
"python-multipart>=0.0.7",
|
|
"defusedxml>=0.7.1"
|
|
]
|
|
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,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,explorer]",
|
|
"semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,agno]"
|
|
]
|
|
|
|
# ---------------- ENTRYPOINTS ----------------
|
|
[project.scripts]
|
|
semantica = "semantica.cli:main"
|
|
semantica-server = "semantica.server:main"
|
|
semantica-worker = "semantica.worker:main"
|
|
semantica-explorer = "semantica.explorer:main"
|
|
semantica-mcp = "semantica.mcp_server:main"
|
|
|
|
# ---------------- TOOLING ----------------
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
include = ["semantica*", "integrations*"]
|
|
|
|
[tool.setuptools.package-data]
|
|
# Explicit patterns are more reliable than **/* across setuptools versions.
|
|
# static/* covers index.html / favicon; static/assets/* covers all JS/CSS chunks.
|
|
"semantica" = ["static/*", "static/assets/*"]
|
|
|
|
[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')",
|
|
]
|