1df9be6563
- codex/parsing/mathpix.py: pix2tex (local, CPU) primary + MathPix API optional; bbox heuristic h>15px, math-char-count>5; singleton model cache - codex/parsing/figures.py: pymupdf embedded-image extraction → PNG; caption detection via proximity + "Figure/Fig./Abbildung" prefix - codex/models.py: FormulaChunk + FigureChunk dataclasses (R-10/R-11) - codex/ingest.py: --rich flag wires formula+figure extraction post-ingest - codex/cli.py: search_app sub-typer (paper + formula subcommands), --rich flag on ingest; wiki_app from F-12 preserved intact - codex/config.py: mathpix_app_id/key, pix2tex_fallback, figures_dir - infra/schema.sql: formulas + figures tables with HNSW pgvector indexes - pyproject.toml: pymupdf>=1.24, pix2tex>=0.1.4 - tests/parsing/test_mathpix.py + test_figures.py: 31 tests (mock pix2tex + MathPix HTTP, real pymupdf on synthetic PDF) Gate: 158 passed, ruff clean, mypy clean (20 files) Requirements: R-10 R-11 R-12 R-13 R-14 → done Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
50 lines
938 B
TOML
50 lines
938 B
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "codex"
|
|
version = "0.1.0"
|
|
description = "Personal knowledge base for scientific papers — provenance, citation graph, semantic search."
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"psycopg[binary]>=3.1",
|
|
"pgvector>=0.3",
|
|
"pydantic-settings>=2",
|
|
"sentence-transformers>=3",
|
|
"flagembedding>=1.2",
|
|
"typer>=0.12",
|
|
"httpx>=0.27",
|
|
"tenacity>=8",
|
|
"pymupdf>=1.24",
|
|
"pix2tex>=0.1.4",
|
|
]
|
|
|
|
[project.scripts]
|
|
codex = "codex.cli:app"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"ruff>=0.4",
|
|
"mypy>=1.10",
|
|
"pytest>=8",
|
|
"pytest-mock>=3",
|
|
]
|
|
|
|
[tool.ruff]
|
|
target-version = "py312"
|
|
line-length = 100
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "UP", "B", "SIM"]
|
|
ignore = []
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
strict = true
|
|
ignore_missing_imports = true
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|