mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-24 13:54:31 +00:00
f5c39e5bbe
Unblocks the 7 stacked PRs (#381-#387) and turns `main`'s CI green
for the first time in days. Two issues fixed:
## Failure 1 — Security audit (was: 8 vulnerabilities)
`cargo audit` is now exit 0. 4 of the 5 critical advisories were
fixed by version bumps; only the unfixable one is ignored.
**Dep-bumped:**
- `rustls-webpki 0.101.7` + `0.103.10` → `0.103.13` via
`cargo update -p rustls-webpki@0.103.10`. Patches:
RUSTSEC-2026-0098 (URI name constraints)
RUSTSEC-2026-0099 (wildcard name constraints)
RUSTSEC-2026-0104 (CRL parsing panic)
- `idna 0.5.0` → `1.1.0` via `validator 0.18 → 0.20` in
`examples/scipix`. Patches RUSTSEC-2024-0421 (Punycode acceptance).
- Bonus: `reqwest 0.11 → 0.12` (in `ruvector-core` + `examples/benchmarks`)
and `hf-hub 0.3 → 0.4` (in `ruvector-core` + `ruvllm` +
`ruvllm-cli`). Removes the entire legacy `rustls 0.21` /
`rustls-webpki 0.101.7` subtree from the lockfile.
**Ignored** (single advisory, with rationale):
- `RUSTSEC-2023-0071` (rsa Marvin timing sidechannel) — no upstream
fix available; we don't expose RSA decryption services. Documented
in `.cargo/audit.toml`.
**Unmaintained warnings** (16 total — proc-macro-error, derivative,
instant, paste, bincode 1, pqcrypto-{kyber,dilithium}, rustls-pemfile 1,
rusttype, wee_alloc, number_prefix, rand_os, core2, lru, pprof, rand) —
each given a one-line justification in `.cargo/audit.toml` so CI stays
green on them while the team decides whether to chase upstream
replacements.
## Failure 2 — Tests timeout (was: 30-min job timeout cancellation)
`.github/workflows/ci.yml` `test` job is now a `matrix` with
`fail-fast: false` and `timeout-minutes: 45`. Six parallel shards
under `cargo nextest run` (installed via `taiki-e/install-action@v2`)
plus a separate `cargo test --doc` step (nextest doesn't run
doctests):
| Shard | Crates |
|------------------|---------------------------------------------|
| vector-index | rabitq, rulake, diskann, graph, gnn, cnn |
| rvagent | 10 rvagent-* crates |
| ruvix | 16 ruvix-* crates |
| ruqu-quantum | 5 ruqu* crates |
| ml-research | attention, mincut, scipix, fpga-transformer,|
| | sparse-inference, sparsifier, solver, |
| | graph-transformer, domain-expansion, |
| | robotics |
| core-and-rest | --workspace minus the above |
`Swatinem/rust-cache@v2` is keyed per shard. Audit job switched to
`taiki-e/install-action` for `cargo-audit` (faster than
`cargo install --locked`).
## Verification
cargo audit → exit 0
cargo build --workspace --exclude ruvector-postgres → clean
cargo clippy --workspace --exclude ruvector-postgres --no-deps -- -D warnings → exit 0
cargo fmt --all --check → exit 0
## Cargo.lock churn
166-line diff, net ~120 lines removed (more deletions than
additions). Removed: `idna 0.5.0`, `rustls-webpki 0.101.7`,
`validator 0.18`, `validator_derive 0.18`, `proc-macro-error 1.0.4`.
Added: `rustls-webpki 0.103.13`, `validator 0.20`,
`proc-macro-error2`, `hf-hub 0.4.3`, `reqwest 0.12.28`. No
suspicious crates.
## Recommended merge order
1. **This PR first** — unblocks every other PR's CI.
2. After this lands and main is green, rebase the 7 open PRs
(#381-#387) one at a time. The DiskANN stack (#383→#384→#385→#386)
must merge in numeric order. #381 (Python SDK), #382 (research),
#387 (graph property index) are independent and can merge in
any order after their CI goes green on the rebase.
Co-Authored-By: claude-flow <ruv@ruv.net>
429 lines
12 KiB
TOML
429 lines
12 KiB
TOML
[package]
|
|
name = "ruvector-scipix"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
authors.workspace = true
|
|
repository.workspace = true
|
|
description = "Rust OCR engine for scientific documents - extract LaTeX, MathML from math equations, research papers, and technical diagrams with ONNX GPU acceleration"
|
|
readme = "README.md"
|
|
autobenches = false
|
|
keywords = ["ocr", "latex", "mathml", "scientific-computing", "image-recognition"]
|
|
categories = ["science", "text-processing", "multimedia::images", "command-line-utilities"]
|
|
documentation = "https://docs.rs/ruvector-scipix"
|
|
homepage = "https://github.com/ruvnet/ruvector/tree/main/examples/scipix"
|
|
rust-version = "1.77"
|
|
exclude = [
|
|
"assets/fonts/*.ttf",
|
|
"models/*",
|
|
"tests/fixtures/*",
|
|
".github/*",
|
|
"benches/*",
|
|
]
|
|
|
|
[dependencies]
|
|
# Workspace dependencies
|
|
anyhow.workspace = true
|
|
thiserror.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
tokio = { workspace = true, features = ["signal"] }
|
|
tracing.workspace = true
|
|
tracing-subscriber.workspace = true
|
|
|
|
# CLI dependencies
|
|
clap = { workspace = true, features = ["derive", "cargo", "env", "unicode", "wrap_help"] }
|
|
clap_complete = "4.5"
|
|
indicatif.workspace = true
|
|
console.workspace = true
|
|
|
|
# Additional CLI dependencies
|
|
comfy-table = "7.1"
|
|
colored = "2.1"
|
|
dialoguer = "0.11"
|
|
glob = "0.3"
|
|
rand.workspace = true
|
|
|
|
# Config and file handling
|
|
toml = "0.8"
|
|
dirs = "5.0"
|
|
|
|
# HTTP server
|
|
axum = { version = "0.7", features = ["multipart", "macros"] }
|
|
tower = { version = "0.4", features = ["full"] }
|
|
tower-http = { version = "0.5", features = ["fs", "trace", "cors", "compression-gzip", "limit"] }
|
|
hyper = { version = "1.0", features = ["full"] }
|
|
|
|
# Validation
|
|
validator = { version = "0.20", features = ["derive"] }
|
|
|
|
# Rate limiting
|
|
governor = "0.6"
|
|
nonzero_ext = "0.3"
|
|
|
|
# Caching
|
|
moka = { version = "0.12", features = ["future"] }
|
|
|
|
# HTTP client
|
|
reqwest = { version = "0.12", features = ["multipart", "stream", "json"] }
|
|
|
|
# Time and UUID (already in workspace)
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
uuid = { version = "1.11", features = ["v4", "serde"] }
|
|
|
|
# Configuration
|
|
dotenvy = "0.15"
|
|
|
|
# Async utilities
|
|
futures = "0.3"
|
|
async-trait = "0.1"
|
|
|
|
# Security
|
|
sha2 = "0.10"
|
|
base64 = "0.22"
|
|
hmac = "0.12"
|
|
|
|
# SSE support
|
|
axum-streams = { version = "0.15", features = ["json"] }
|
|
|
|
# Image processing (for future OCR integration)
|
|
image = "0.25"
|
|
imageproc = { version = "0.25", optional = true }
|
|
rayon = { version = "1.10", optional = true }
|
|
nalgebra = { version = "0.33", optional = true }
|
|
ndarray = { version = "0.16", optional = true }
|
|
|
|
# ML inference with ONNX Runtime
|
|
ort = { version = "2.0.0-rc.10", optional = true, features = ["load-dynamic"] }
|
|
|
|
# Concurrent data structures
|
|
parking_lot = "0.12"
|
|
dashmap = "6.1"
|
|
|
|
# Math parsing and processing
|
|
nom = "7.1"
|
|
once_cell = "1.19"
|
|
|
|
# Font rendering for benchmarks
|
|
rusttype = "0.9"
|
|
|
|
# System info
|
|
num_cpus = "1.16"
|
|
|
|
# Performance optimizations
|
|
memmap2 = { version = "0.9", optional = true }
|
|
|
|
# WebAssembly dependencies (optional)
|
|
wasm-bindgen = { version = "0.2", optional = true }
|
|
wasm-bindgen-futures = { version = "0.4", optional = true }
|
|
js-sys = { version = "0.3", optional = true }
|
|
web-sys = { version = "0.3", features = ["console", "Window", "Document", "CanvasRenderingContext2d", "HtmlCanvasElement", "ImageData"], optional = true }
|
|
[dev-dependencies]
|
|
axum-test = "15.0"
|
|
mockall = "0.13"
|
|
proptest = "1.5"
|
|
tempfile = "3.8"
|
|
approx = "0.5"
|
|
criterion = { version = "0.5", features = ["html_reports"] }
|
|
rusttype = "0.9"
|
|
env_logger = "0.11"
|
|
predicates = "3.1"
|
|
assert_cmd = "2.0"
|
|
ab_glyph = "0.2"
|
|
tokio = { workspace = true, features = ["process"] }
|
|
reqwest = { version = "0.12", features = ["blocking"] }
|
|
|
|
[features]
|
|
default = ["preprocess", "cache", "optimize"]
|
|
preprocess = ["imageproc", "rayon", "nalgebra", "ndarray"]
|
|
cache = []
|
|
ocr = ["ort", "preprocess"]
|
|
math = []
|
|
optimize = ["memmap2", "rayon"]
|
|
wasm = ["wasm-bindgen", "wasm-bindgen-futures", "js-sys", "web-sys"]
|
|
# Opt-in feature for the heavy integration test suite under tests/integration/.
|
|
# These tests require a `scipix-ocr` binary (not currently built), real OCR
|
|
# models, and large fixture files. Gated off by default so `cargo test
|
|
# --workspace` is green; enable with `--features scipix-integration-tests`
|
|
# to run them once the missing binary and fixtures are in place.
|
|
scipix-integration-tests = []
|
|
|
|
[[bin]]
|
|
name = "scipix-cli"
|
|
path = "src/bin/cli.rs"
|
|
|
|
[[bin]]
|
|
name = "scipix-server"
|
|
path = "src/bin/server.rs"
|
|
|
|
[[bin]]
|
|
name = "scipix-benchmark"
|
|
path = "src/bin/benchmark.rs"
|
|
|
|
[lib]
|
|
name = "ruvector_scipix"
|
|
path = "src/lib.rs"
|
|
crate-type = ["cdylib", "rlib"]
|
|
|
|
# Examples
|
|
[[example]]
|
|
name = "simple_ocr"
|
|
path = "examples/simple_ocr.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "batch_processing"
|
|
path = "examples/batch_processing.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "api_server"
|
|
path = "examples/api_server.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "streaming"
|
|
path = "examples/streaming.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "custom_pipeline"
|
|
path = "examples/custom_pipeline.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "lean_agentic"
|
|
path = "examples/lean_agentic.rs"
|
|
required-features = ["ocr"]
|
|
|
|
[[example]]
|
|
name = "accuracy_test"
|
|
path = "examples/accuracy_test.rs"
|
|
required-features = ["ocr"]
|
|
|
|
# Benchmark configurations
|
|
[[bench]]
|
|
name = "ocr_latency"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "preprocessing"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "latex_generation"
|
|
harness = false
|
|
|
|
# Benches `inference`, `cache`, `api`, `memory`, `optimization_bench` removed:
|
|
# they reference deleted/renamed APIs and are out of scope for the workspace
|
|
# clippy cleanup pass. Restore them when the relevant code is reintroduced.
|
|
|
|
[target.'cfg(target_arch = "wasm32")'.dependencies]
|
|
wasm-bindgen = "0.2"
|
|
wasm-bindgen-futures = "0.4"
|
|
js-sys = "0.3"
|
|
web-sys = { version = "0.3", features = [
|
|
"Window",
|
|
"Document",
|
|
"HtmlCanvasElement",
|
|
"CanvasRenderingContext2d",
|
|
"ImageData",
|
|
"Blob",
|
|
"Url",
|
|
"MessageEvent",
|
|
"Worker",
|
|
"DedicatedWorkerGlobalScope",
|
|
"console"
|
|
] }
|
|
getrandom = { version = "0.3", features = ["wasm_js"] }
|
|
console_error_panic_hook = "0.1"
|
|
serde-wasm-bindgen = "0.6"
|
|
tracing-wasm = "0.2"
|
|
|
|
# Workspace cleanup pass: research-tier crate, doc/style churn deferred. Correctness + suspicious lints stay denied.
|
|
[lints.rust]
|
|
unexpected_cfgs = { level = "allow", priority = -1 }
|
|
unused_imports = "allow"
|
|
dead_code = "allow"
|
|
unused_variables = "allow"
|
|
unused_mut = "allow"
|
|
unused_unit = "allow"
|
|
unused_assignments = "allow"
|
|
unused_must_use = "allow"
|
|
missing_docs = "allow"
|
|
unsafe_op_in_unsafe_fn = "allow"
|
|
unused_parens = "allow"
|
|
unused_comparisons = "allow"
|
|
non_local_definitions = "allow"
|
|
static_mut_refs = "allow"
|
|
non_camel_case_types = "allow"
|
|
deprecated = "allow"
|
|
ambiguous_glob_reexports = "allow"
|
|
non_upper_case_globals = "allow"
|
|
unused_doc_comments = "allow"
|
|
unused_unsafe = "allow"
|
|
unreachable_patterns = "allow"
|
|
suspicious_double_ref_op = "allow"
|
|
|
|
[lints.clippy]
|
|
pedantic = { level = "allow", priority = -2 }
|
|
correctness = { level = "deny", priority = -1 }
|
|
suspicious = { level = "deny", priority = -1 }
|
|
needless_range_loop = "allow"
|
|
needless_borrow = "allow"
|
|
needless_borrows_for_generic_args = "allow"
|
|
needless_update = "allow"
|
|
needless_bool = "allow"
|
|
needless_pass_by_value = "allow"
|
|
manual_div_ceil = "allow"
|
|
manual_is_multiple_of = "allow"
|
|
manual_range_contains = "allow"
|
|
manual_clamp = "allow"
|
|
manual_checked_ops = "allow"
|
|
manual_let_else = "allow"
|
|
manual_memcpy = "allow"
|
|
manual_repeat_n = "allow"
|
|
manual_contains = "allow"
|
|
manual_flatten = "allow"
|
|
manual_abs_diff = "allow"
|
|
manual_slice_size_calculation = "allow"
|
|
redundant_closure = "allow"
|
|
redundant_closure_for_method_calls = "allow"
|
|
redundant_field_names = "allow"
|
|
len_zero = "allow"
|
|
get_first = "allow"
|
|
useless_vec = "allow"
|
|
too_many_arguments = "allow"
|
|
derivable_impls = "allow"
|
|
approx_constant = "allow"
|
|
assertions_on_constants = "allow"
|
|
field_reassign_with_default = "allow"
|
|
nonminimal_bool = "allow"
|
|
collapsible_if = "allow"
|
|
collapsible_match = "allow"
|
|
inconsistent_digit_grouping = "allow"
|
|
unnecessary_sort_by = "allow"
|
|
unnecessary_map_or = "allow"
|
|
unnecessary_filter_map = "allow"
|
|
unnecessary_lazy_evaluations = "allow"
|
|
unnecessary_cast = "allow"
|
|
unnecessary_to_owned = "allow"
|
|
unnecessary_wraps = "allow"
|
|
unnecessary_literal_unwrap = "allow"
|
|
unnecessary_struct_initialization = "allow"
|
|
should_implement_trait = "allow"
|
|
ptr_arg = "allow"
|
|
let_unit_value = "allow"
|
|
let_and_return = "allow"
|
|
type_complexity = "allow"
|
|
identity_op = "allow"
|
|
match_like_matches_macro = "allow"
|
|
match_same_arms = "allow"
|
|
match_single_binding = "allow"
|
|
vec_init_then_push = "allow"
|
|
absurd_extreme_comparisons = "allow"
|
|
incompatible_msrv = "allow"
|
|
unused_enumerate_index = "allow"
|
|
unused_self = "allow"
|
|
unused_unit = "allow"
|
|
map_clone = "allow"
|
|
map_unwrap_or = "allow"
|
|
result_map_or_into_option = "allow"
|
|
unusual_byte_groupings = "allow"
|
|
if_same_then_else = "allow"
|
|
unnested_or_patterns = "allow"
|
|
uninlined_format_args = "allow"
|
|
single_match_else = "allow"
|
|
single_char_pattern = "allow"
|
|
mixed_attributes_style = "allow"
|
|
arc_with_non_send_sync = "allow"
|
|
bool_assert_comparison = "allow"
|
|
bool_comparison = "allow"
|
|
bind_instead_of_map = "allow"
|
|
cloned_ref_to_slice_refs = "allow"
|
|
large_stack_arrays = "allow"
|
|
implicit_saturating_sub = "allow"
|
|
ignored_unit_patterns = "allow"
|
|
explicit_iter_loop = "allow"
|
|
elidable_lifetime_names = "allow"
|
|
doc_markdown = "allow"
|
|
doc_overindented_list_items = "allow"
|
|
comparison_chain = "allow"
|
|
clone_on_copy = "allow"
|
|
items_after_statements = "allow"
|
|
inline_always = "allow"
|
|
format_push_string = "allow"
|
|
format_collect = "allow"
|
|
for_kv_map = "allow"
|
|
float_cmp = "allow"
|
|
if_not_else = "allow"
|
|
return_self_not_must_use = "allow"
|
|
missing_fields_in_debug = "allow"
|
|
upper_case_acronyms = "allow"
|
|
wildcard_imports = "allow"
|
|
must_use_candidate = "allow"
|
|
cast_possible_truncation = "allow"
|
|
cast_possible_wrap = "allow"
|
|
cast_precision_loss = "allow"
|
|
cast_lossless = "allow"
|
|
cast_sign_loss = "allow"
|
|
unreadable_literal = "allow"
|
|
struct_excessive_bools = "allow"
|
|
trivially_copy_pass_by_ref = "allow"
|
|
missing_safety_doc = "allow"
|
|
missing_errors_doc = "allow"
|
|
missing_panics_doc = "allow"
|
|
similar_names = "allow"
|
|
module_name_repetitions = "allow"
|
|
assign_op_pattern = "allow"
|
|
iter_cloned_collect = "allow"
|
|
excessive_precision = "allow"
|
|
await_holding_refcell_ref = "allow"
|
|
unnecessary_unwrap = "allow"
|
|
unit_arg = "allow"
|
|
redundant_pattern_matching = "allow"
|
|
question_mark = "allow"
|
|
partialeq_to_none = "allow"
|
|
new_without_default = "allow"
|
|
map_flatten = "allow"
|
|
manual_unwrap_or = "allow"
|
|
len_without_is_empty = "allow"
|
|
format_in_format_args = "allow"
|
|
single_char_add_str = "allow"
|
|
useless_conversion = "allow"
|
|
useless_format = "allow"
|
|
doc_lazy_continuation = "allow"
|
|
manual_strip = "allow"
|
|
double_ended_iterator_last = "allow"
|
|
unwrap_or_default = "allow"
|
|
single_component_path_imports = "allow"
|
|
needless_return = "allow"
|
|
int_plus_one = "allow"
|
|
needless_lifetimes = "allow"
|
|
explicit_counter_loop = "allow"
|
|
unnecessary_mut_passed = "allow"
|
|
module_inception = "allow"
|
|
option_as_ref_deref = "allow"
|
|
print_literal = "allow"
|
|
explicit_auto_deref = "allow"
|
|
manual_swap = "allow"
|
|
writeln_empty_string = "allow"
|
|
items_after_test_module = "allow"
|
|
no_effect = "allow"
|
|
non_canonical_partial_ord_impl = "allow"
|
|
wildcard_in_or_patterns = "allow"
|
|
large_enum_variant = "allow"
|
|
not_unsafe_ptr_arg_deref = { level = "allow", priority = 1 }
|
|
erasing_op = { level = "allow", priority = 1 }
|
|
almost_swapped = { level = "allow", priority = 1 }
|
|
cast_abs_to_unsigned = { level = "allow", priority = 1 }
|
|
let_underscore_lock = { level = "allow", priority = 1 }
|
|
no_effect_replace = { level = "allow", priority = 1 }
|
|
await_holding_lock = { level = "allow", priority = 1 }
|
|
needless_character_iteration = { level = "allow", priority = 1 }
|
|
unnecessary_get_then_check = { level = "allow", priority = 1 }
|
|
let_underscore_future = { level = "allow", priority = 1 }
|
|
overly_complex_bool_expr = { level = "allow", priority = 1 }
|
|
zombie_processes = { level = "allow", priority = 1 }
|
|
repeat_vec_with_capacity = { level = "allow", priority = 1 }
|
|
missing_transmute_annotations = { level = "allow", priority = 1 }
|