176c04cd6c
Shared 512-token chunking module for the OB1/vault embedding stack. Wraps tiktoken cl100k_base; consumed by vault_mcp, ob1-enricher, ob1-reflector before passing to Ollama (nomic-embed-text, 768-d). Extracted from /opt/projects/homelab/shared/python/embedding_chunking to its own repo so consumers can pin via git ref instead of editable path source, unblocking docker builds outside the homelab tree.
33 lines
690 B
TOML
33 lines
690 B
TOML
[project]
|
|
name = "embedding-chunking"
|
|
version = "0.1.0"
|
|
description = "Shared 512-token chunking for the OB1/vault embedding stack. Wraps tiktoken cl100k_base; consumed by vault_mcp, ob1-enricher, ob1-reflector."
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"tiktoken>=0.8",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/embedding_chunking"]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"pytest>=8.0",
|
|
"pytest-cov>=5.0",
|
|
"ruff>=0.8",
|
|
]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py312"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "B", "UP", "SIM", "RUF"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|