9b53dcb94f
Single-file ingest entry. Copies bytes to _external/<hash12>.<ext>
via crate::external::copy_to_external, runs the per-medium pipeline on
that single asset (reuses ingest_with_config_opts via a SourceScope
{ root: _external/, include: [<filename>], exclude:
config.workspace.exclude }).
`.kebabignore` matches log a stderr warn line and proceed (explicit
ingest is bypass intent). Internal helper `check_kebabignore_match`
uses the `ignore` crate's GitignoreBuilder.
Returns the standard IngestReport (incremental ingest from fb-23
handles re-ingest as `unchanged`).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
73 lines
3.5 KiB
TOML
73 lines
3.5 KiB
TOML
[package]
|
|
name = "kebab-app"
|
|
version = { workspace = true }
|
|
edition = { workspace = true }
|
|
rust-version = { workspace = true }
|
|
license = { workspace = true }
|
|
repository = { workspace = true }
|
|
description = "Facade — orchestrates components for kb-cli/tui/desktop"
|
|
|
|
[dependencies]
|
|
kebab-core = { path = "../kebab-core" }
|
|
kebab-config = { path = "../kebab-config" }
|
|
kebab-source-fs = { path = "../kebab-source-fs" }
|
|
kebab-parse-md = { path = "../kebab-parse-md" }
|
|
kebab-parse-types = { path = "../kebab-parse-types" }
|
|
kebab-normalize = { path = "../kebab-normalize" }
|
|
kebab-chunk = { path = "../kebab-chunk" }
|
|
kebab-store-sqlite = { path = "../kebab-store-sqlite" }
|
|
kebab-store-vector = { path = "../kebab-store-vector" }
|
|
kebab-search = { path = "../kebab-search" }
|
|
kebab-embed = { path = "../kebab-embed" }
|
|
kebab-embed-local = { path = "../kebab-embed-local" }
|
|
kebab-llm = { path = "../kebab-llm" }
|
|
kebab-llm-local = { path = "../kebab-llm-local" }
|
|
kebab-rag = { path = "../kebab-rag" }
|
|
# P6-4: image extractor + OCR + caption adapters live here. App
|
|
# threads them into the per-asset dispatch (see `ingest_one_asset`
|
|
# image branch). Trait-only consumption — no `kebab-parse-image`
|
|
# internals leak into kb-app code.
|
|
kebab-parse-image = { path = "../kebab-parse-image" }
|
|
# P7-3: PDF text extractor lives here. App threads it into the
|
|
# per-asset dispatch (see `ingest_one_asset` PDF branch) and runs the
|
|
# resulting `CanonicalDocument` through `kebab-chunk::PdfPageV1Chunker`.
|
|
kebab-parse-pdf = { path = "../kebab-parse-pdf" }
|
|
anyhow = { workspace = true }
|
|
blake3 = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
time = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt", "json"] }
|
|
tracing-appender = "0.2"
|
|
toml = "0.8"
|
|
dirs = "5"
|
|
# p9-fb-19: in-process LRU cache for `App::search`. Capacity from
|
|
# `config.search.cache_capacity` (default 256, ~1.3 MB cap).
|
|
lru = { workspace = true }
|
|
# p9-fb-19: NFKC-normalize cache-key queries so `"Foo"` / `"FOO"` /
|
|
# `" foo "` collapse to one entry. Same crate kebab-normalize +
|
|
# kebab-core already use, no version drift.
|
|
unicode-normalization = "0.1"
|
|
# p9-fb-31: GitignoreBuilder for .kebabignore matching in ingest_file_with_config.
|
|
# Same version as kebab-source-fs (0.4) to avoid duplicate dep versions.
|
|
ignore = "0.4"
|
|
|
|
[dev-dependencies]
|
|
rusqlite = { workspace = true }
|
|
tempfile = { workspace = true }
|
|
# Image-pipeline integration tests use wiremock to stub Ollama for OCR
|
|
# / caption HTTP calls. Async runtime to host the mock server only;
|
|
# the kb-app code under test stays sync.
|
|
wiremock = { workspace = true }
|
|
tokio = { workspace = true, features = ["rt-multi-thread"] }
|
|
image = { version = "0.25", default-features = false, features = ["png"] }
|
|
# P7-3 PDF integration tests build in-memory PDF fixtures via the same
|
|
# lopdf builder pattern `kebab-parse-pdf::tests::common` uses; pinned
|
|
# to the same major (0.32) so byte output is identical between the two
|
|
# fixture surfaces.
|
|
lopdf = "0.32"
|
|
# error_wire::tests::llm_unreachable_classifies_to_model_unreachable needs a real
|
|
# reqwest::Error (private constructor) — built from a connect-refused call.
|
|
reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
|