f964631d02
Module 5 phase 4 step 0 (docs/kb/modules/05-faza4-plan.md, §3, decision 1): kb-query is a long-lived Docker service, documents-ingest is a venv job with an `anthropic` dependency and CLI scripts it doesn't need. Move embed_chunk/_vector_literal/cascade_query/flat_query into a shared package with minimal deps (asyncpg, aiohttp only) so both can depend on the same tested retrieval code without the service image pulling in the job's extras. documents_ingest.chunk_embed/retrieval keep thin re-exports so nothing importing the old paths breaks. Pure refactor: retrieval_eval.py run live against kb-postgres@PIHA + Ollama@SOLARIA before/after gives byte-identical `dist`/hit@3/gate results (still PASS) — zero behavior change in the cascade. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
32 lines
778 B
TOML
32 lines
778 B
TOML
[build-system]
|
|
requires = ["setuptools>=68"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "documents-ingest"
|
|
version = "0.1.0"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"asyncpg>=0.29",
|
|
"structlog>=24.1",
|
|
"aiohttp>=3.9",
|
|
"kb-mail",
|
|
"kb-retrieval",
|
|
"PyYAML>=6.0",
|
|
"anthropic>=0.40",
|
|
]
|
|
|
|
[project.scripts]
|
|
documents-ingest = "documents_ingest.extractor:main"
|
|
documents-ingest-paperless = "documents_ingest.paperless_adapter:main"
|
|
documents-ingest-embed = "documents_ingest.chunk_embed:main"
|
|
documents-ingest-summarize = "documents_ingest.summarize:main"
|
|
documents-ingest-cyclic = "documents_ingest.cyclic_ingest:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|