m2 (AI Agent)
6da874b2e6
Phase 1: router skeleton + Qdrant read path - FastAPI app with /health, /search/generic, /ingest endpoints - Qdrant reader (hybrid dense+sparse w/ RRF, plus payload scroll) - BGE-M3 TEI client for query-side embedding - memory-api client proxying writes to /memory/store (m2-memory untouched) - Pydantic Fact + Exemplar payloads, discriminated by `kind` - Dockerfile + docker-compose joining the coolify Docker network Phase 2: authoritative-source ingest pipeline - PDF text extraction + paragraph-aware (§ N) and size chunkers - Loaders for bnatschg, mhbasp, biotopwertliste, state-<slug> - CLI: artenschutz-ingest --source <name> [--states ...] [--dry-run] - Helper script to fetch BNatSchG from gesetze-im-internet.de - End-to-end smoke script (scripts/smoke.sh) for Coolify validation 22/22 unit tests pass. Real-world dry-runs verified against mhbasp Anhang 4, biotopwertlisteNEU and Berlin Kartierstandards PDFs from GST-DATA. See COOLIFY-DEPLOY.md for staging deploy + smoke procedure.
42 lines
855 B
TOML
42 lines
855 B
TOML
[project]
|
|
name = "artenschutz-router"
|
|
version = "0.1.0"
|
|
description = "Sidecar router for Artenschutz domain queries against agent.memory.system"
|
|
requires-python = ">=3.11"
|
|
readme = "README.md"
|
|
|
|
dependencies = [
|
|
"fastapi>=0.110",
|
|
"uvicorn[standard]>=0.27",
|
|
"pydantic>=2.6",
|
|
"pydantic-settings>=2.2",
|
|
"httpx>=0.27",
|
|
"qdrant-client>=1.9",
|
|
"pypdf>=4.0",
|
|
"python-dateutil>=2.9",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.0",
|
|
"pytest-asyncio>=0.23",
|
|
"ruff>=0.4",
|
|
]
|
|
|
|
[project.scripts]
|
|
artenschutz-ingest = "artenschutz_router.ingest.cli:main"
|
|
|
|
[build-system]
|
|
requires = ["setuptools>=68"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py311"
|