eSlider
678a1d1dba
- bin/mail/sync.go: async Go sync engine (8 workers, paginated Gmail via API + OnlyOffice IMAP); Gmail attachments key off body.attachmentId, not MIME partId; ICS sidecars Latin-1->UTF-8 normalized (TestICSToMarkdownNormalizesLatin1) - bin/mail/import: message.json -> markdown; PDFs via pdftotext -layout fast path with docling subprocess fallback for the ~5% textless files - bin/mail/index_mail: fresh-rebuild indexer (repo corpus + mail) avoiding ladybug WAL corruption on bulk-insert into indexed DBs; split from import - bin/kb/index: keep FTS/VECTOR indexes across incremental runs (drop+recreate leaves stale backing tables killing the vector index) - docs: README/PLAN/AGENTS cover the mail pipeline Result: 17,835 messages -> 28,918 info leafs, FTS+HNSW healthy.
18 lines
513 B
TOML
18 lines
513 B
TOML
[project]
|
|
name = "2dph"
|
|
version = "0.1.0"
|
|
description = "Evidence-first brain: LadybugDB knowledge graph + hybrid RAG over the ops stack. Facts need two sources or they are (not confirmed)."
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
license = { text = "MIT" }
|
|
dependencies = [
|
|
"docling>=2.119.0",
|
|
"ladybug==0.19.1",
|
|
"markitdown[docx,epub,html,image-exif,pdf,pptx,xlsx,zip]>=0.1.7",
|
|
"mistune==3.3.4",
|
|
"model2vec==0.8.2",
|
|
"numpy>=2.5.2",
|
|
"pyyaml>=6.0.3",
|
|
"requests>=2.34.2",
|
|
]
|