cb34eeb82e
Add a CPU-only, English-first OCR engine (the `ocrs` crate on the `rten` runtime) as an alternative to the local-LLM "vision" backend, which ran too slowly on the target Raspberry Pi 5. - `ANALYSIS_BACKEND` (default `ocr`) selects the engine; `vision` keeps the existing LLM path. Deploy-time, env-only — not admin-tunable. - `analysis::ocr` adds an `OcrEngine` trait (testable seam), the `OcrsEngine` impl (models loaded once, inference on the blocking pool), and an `OcrAnalyzeDispatcher` that plugs into the existing `AnalyzeDispatcher` seam and reuses `persist_analysis`, so OCR text lands in `page_ocr_text` and the `search_doc` tsvector exactly as the vision path produces them. - The backend image bakes the two `.rten` models into /models, where `OCRS_DETECTION_MODEL` / `OCRS_RECOGNITION_MODEL` default. Because `/v1/me/page-search` ranks on `search_doc`, OCR text search works the moment pages are processed. Auto-tagging, scene description and NSFW flags remain the vision backend's job (deferred). Bumps to 0.90.0 (minor) in both manifests. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
75 lines
2.4 KiB
TOML
75 lines
2.4 KiB
TOML
[package]
|
||
name = "mangalord"
|
||
version = "0.90.0"
|
||
edition = "2021"
|
||
default-run = "mangalord"
|
||
|
||
[lib]
|
||
path = "src/lib.rs"
|
||
|
||
[[bin]]
|
||
name = "mangalord"
|
||
path = "src/main.rs"
|
||
|
||
[[bin]]
|
||
name = "crawler"
|
||
path = "src/bin/crawler.rs"
|
||
|
||
[dependencies]
|
||
axum = { version = "0.7", features = ["macros", "multipart"] }
|
||
tokio = { version = "1", features = ["full"] }
|
||
sqlx = { version = "0.8", features = ["runtime-tokio", "postgres", "uuid", "chrono", "macros", "migrate"] }
|
||
serde = { version = "1", features = ["derive"] }
|
||
serde_json = "1"
|
||
uuid = { version = "1", features = ["v4", "serde"] }
|
||
chrono = { version = "0.4", features = ["serde"] }
|
||
chrono-tz = "0.9"
|
||
tracing = "0.1"
|
||
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
||
tower = { version = "0.5", features = ["util"] }
|
||
tower-http = { version = "0.6", features = ["trace", "cors"] }
|
||
thiserror = "1"
|
||
anyhow = "1"
|
||
async-trait = "0.1"
|
||
dotenvy = "0.15"
|
||
argon2 = "0.5"
|
||
rand = "0.8"
|
||
sha2 = "0.10"
|
||
subtle = "2"
|
||
base64 = "0.22"
|
||
# Image decode + downscale for the analysis worker (keep the page image
|
||
# under the local vision model's token budget). Only the manga page formats.
|
||
image = { version = "0.25", default-features = false, features = ["jpeg", "png", "webp"] }
|
||
axum-extra = { version = "0.9", features = ["cookie", "typed-header"] }
|
||
time = "0.3"
|
||
infer = "0.16"
|
||
tokio-util = { version = "0.7", features = ["io"] }
|
||
futures-core = "0.3"
|
||
futures-util = "0.3"
|
||
bytes = "1"
|
||
chromiumoxide = { version = "0.7", features = ["tokio-runtime", "_fetcher-rusttls-tokio"], default-features = false }
|
||
sysinfo = { version = "0.32", default-features = false, features = ["system", "component"] }
|
||
nix = { version = "0.29", features = ["fs"] }
|
||
scraper = "0.20"
|
||
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "socks", "cookies", "stream", "json"] }
|
||
ocrs = "0.12"
|
||
rten = "0.24"
|
||
|
||
[dev-dependencies]
|
||
tempfile = "3"
|
||
tower = { version = "0.5", features = ["util"] }
|
||
http-body-util = "0.1"
|
||
mime = "0.3"
|
||
futures-util = "0.3"
|
||
tokio = { version = "1", features = ["test-util"] }
|
||
|
||
# Trim debug builds: keep line numbers in panics / backtraces but drop the
|
||
# full DWARF info (variable-level inspection in gdb/lldb). With a sqlx +
|
||
# axum + tokio dep tree the default ("full") leaves backend/target on the
|
||
# order of tens of GiB; this typically cuts ~50–70% off that.
|
||
[profile.dev]
|
||
debug = "line-tables-only"
|
||
|
||
[profile.test]
|
||
debug = "line-tables-only"
|