f7b61f7da9
Module 5 phase 1 (docs/kb/modules/05-documents-ingest.md): pulls a sample of PDF attachments (>50KB, last year, LIMIT 150) out of the Gmail .eml archive and drops them into Paperless consume/ for OCR, so the RAG layer has real documents to work with before the full Paperless/Nextcloud envelope adapter is built. sha256-first attachment matching (manifest filenames can carry raw RFC 2047 encoded-word artifacts that don't byte-match what email.policy.default decodes today — confirmed against live data, ~10% of candidates were affected). Idempotent via a sha256-keyed JSON registry; dry-run by default, --apply to write. Verified end-to-end on PIHA: dry-run + --apply both run against live kb-postgres/archive, 185/222 candidate PDFs written to consume/ (37 in-run duplicates correctly deduped), Paperless picked them up and started OCR immediately.
23 lines
422 B
TOML
23 lines
422 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",
|
|
]
|
|
|
|
[project.scripts]
|
|
documents-ingest = "documents_ingest.extractor:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|