diff --git a/Cargo.lock b/Cargo.lock index 8ca9e2c..1899cf3 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2,6 +2,12 @@ # It is not intended for manual editing. version = 4 +[[package]] +name = "adler2" +version = "2.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa" + [[package]] name = "ahash" version = "0.8.12" @@ -9,7 +15,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75" dependencies = [ "cfg-if", + "getrandom 0.3.4", "once_cell", + "serde", "version_check", "zerocopy", ] @@ -23,6 +31,24 @@ dependencies = [ "memchr", ] +[[package]] +name = "aligned" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee4508988c62edf04abd8d92897fca0c2995d907ce1dfeaf369dac3716a40685" +dependencies = [ + "as-slice", +] + +[[package]] +name = "aligned-vec" +version = "0.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dc890384c8602f339876ded803c97ad529f3842aba97f6392b3dba0dd171769b" +dependencies = [ + "equator", +] + [[package]] name = "anstream" version = "1.0.0" @@ -79,6 +105,23 @@ version = "1.0.102" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c" +[[package]] +name = "arbitrary" +version = "1.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1" + +[[package]] +name = "arg_enum_proc_macro" +version = "0.3.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0ae92a5119aa49cdbcf6b9f893fe4e1d98b04ccbf82ee0584ad948a44a734dea" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + [[package]] name = "arrayref" version = "0.3.9" @@ -91,6 +134,15 @@ version = "0.7.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" +[[package]] +name = "as-slice" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "516b6b4f0e40d50dcda9365d53964ec74560ad4284da2e7fc97122cd83174516" +dependencies = [ + "stable_deref_trait", +] + [[package]] name = "async-trait" version = "0.1.89" @@ -102,12 +154,73 @@ dependencies = [ "syn", ] +[[package]] +name = "atomic-waker" +version = "1.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0" + [[package]] name = "autocfg" version = "1.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8" +[[package]] +name = "av-scenechange" +version = "0.14.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0f321d77c20e19b92c39e7471cf986812cbb46659d2af674adc4331ef3f18394" +dependencies = [ + "aligned", + "anyhow", + "arg_enum_proc_macro", + "arrayvec", + "log", + "num-rational", + "num-traits", + "pastey", + "rayon", + "thiserror 2.0.18", + "v_frame", + "y4m", +] + +[[package]] +name = "av1-grain" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8cfddb07216410377231960af4fcab838eaa12e013417781b78bd95ee22077f8" +dependencies = [ + "anyhow", + "arrayvec", + "log", + "nom 8.0.0", + "num-rational", + "v_frame", +] + +[[package]] +name = "avif-serialize" +version = "0.8.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "375082f007bd67184fb9c0374614b29f9aaa604ec301635f72338bb65386a53d" +dependencies = [ + "arrayvec", +] + +[[package]] +name = "base64" +version = "0.13.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8" + +[[package]] +name = "base64" +version = "0.22.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6" + [[package]] name = "bit-set" version = "0.8.0" @@ -123,12 +236,27 @@ version = "0.8.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5e764a1d40d510daf35e07be9eb06e75770908c27d411ee6c92109c9840eaaf7" +[[package]] +name = "bit_field" +version = "0.10.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e4b40c7323adcfc0a41c4b88143ed58346ff65a288fc144329c5c45e05d70c6" + [[package]] name = "bitflags" version = "2.11.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3" +[[package]] +name = "bitstream-io" +version = "4.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7eff00be299a18769011411c9def0d827e8f2d7bf0c3dbf53633147a8867fd1f" +dependencies = [ + "no_std_io2", +] + [[package]] name = "blake3" version = "1.8.5" @@ -140,7 +268,16 @@ dependencies = [ "cc", "cfg-if", "constant_time_eq", - "cpufeatures", + "cpufeatures 0.3.0", +] + +[[package]] +name = "block-buffer" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71" +dependencies = [ + "generic-array", ] [[package]] @@ -153,12 +290,51 @@ dependencies = [ "serde", ] +[[package]] +name = "built" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f4ad8f11f288f48ca24471bbd51ac257aaeaaa07adae295591266b792902ae64" + [[package]] name = "bumpalo" version = "3.20.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb" +[[package]] +name = "bytemuck" +version = "1.25.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8efb64bd706a16a1bdde310ae86b351e4d21550d98d056f22f8a7f7a2183fec" + +[[package]] +name = "byteorder" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" + +[[package]] +name = "byteorder-lite" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495" + +[[package]] +name = "bytes" +version = "1.11.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33" + +[[package]] +name = "castaway" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dec551ab6e7578819132c713a93c022a05d60159dc86e7a7050223577484c55a" +dependencies = [ + "rustversion", +] + [[package]] name = "cc" version = "1.2.61" @@ -166,6 +342,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d16d90359e986641506914ba71350897565610e87ce0ad9e6f28569db3dd5c6d" dependencies = [ "find-msvc-tools", + "jobserver", + "libc", "shlex", ] @@ -215,18 +393,78 @@ version = "1.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9" +[[package]] +name = "color_quant" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b" + [[package]] name = "colorchoice" version = "1.0.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570" +[[package]] +name = "compact_str" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3fdb1325a1cece981e8a296ab8f0f9b63ae357bd0784a9faaf548cc7b480707a" +dependencies = [ + "castaway", + "cfg-if", + "itoa", + "rustversion", + "ryu", + "serde", + "static_assertions", +] + +[[package]] +name = "console" +version = "0.15.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "054ccb5b10f9f2cbf51eb355ca1d05c2d279ce1804688d0db74b4733a5aeafd8" +dependencies = [ + "encode_unicode", + "libc", + "once_cell", + "unicode-width", + "windows-sys 0.59.0", +] + [[package]] name = "constant_time_eq" version = "0.4.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b" +[[package]] +name = "core-foundation" +version = "0.9.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "91e195e091a93c46f7102ec7818a2aa394e1e1771c3ab4825963fa03e45afb8f" +dependencies = [ + "core-foundation-sys", + "libc", +] + +[[package]] +name = "core-foundation" +version = "0.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b2a6cd9ae233e7f62ba4e9353e81a88df7fc8a5987b8d445b4d90c879bd156f6" +dependencies = [ + "core-foundation-sys", + "libc", +] + +[[package]] +name = "core-foundation-sys" +version = "0.8.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b" + [[package]] name = "counter" version = "0.7.1" @@ -236,6 +474,15 @@ dependencies = [ "num-traits", ] +[[package]] +name = "cpufeatures" +version = "0.2.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280" +dependencies = [ + "libc", +] + [[package]] name = "cpufeatures" version = "0.3.0" @@ -245,6 +492,15 @@ dependencies = [ "libc", ] +[[package]] +name = "crc32fast" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511" +dependencies = [ + "cfg-if", +] + [[package]] name = "crossbeam-channel" version = "0.5.15" @@ -279,6 +535,66 @@ version = "0.8.21" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28" +[[package]] +name = "crunchy" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5" + +[[package]] +name = "crypto-common" +version = "0.1.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a" +dependencies = [ + "generic-array", + "typenum", +] + +[[package]] +name = "darling" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc7f46116c46ff9ab3eb1597a45688b6715c6e628b5c133e288e709a29bcb4ee" +dependencies = [ + "darling_core", + "darling_macro", +] + +[[package]] +name = "darling_core" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0d00b9596d185e565c2207a0b01f8bd1a135483d02d9b7b0a54b11da8d53412e" +dependencies = [ + "fnv", + "ident_case", + "proc-macro2", + "quote", + "strsim", + "syn", +] + +[[package]] +name = "darling_macro" +version = "0.20.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc34b93ccb385b40dc71c6fceac4b2ad23662c7eeb248cf10d529b7e055b6ead" +dependencies = [ + "darling_core", + "quote", + "syn", +] + +[[package]] +name = "dary_heap" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b1e3a325bc115f096c8b77bbf027a7c2592230e70be2d985be950d3d5e60ebe" +dependencies = [ + "serde", +] + [[package]] name = "dashmap" version = "6.1.0" @@ -303,13 +619,63 @@ dependencies = [ "serde_core", ] +[[package]] +name = "derive_builder" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "507dfb09ea8b7fa618fcf76e953f4f5e192547945816d5358edffe39f6f94947" +dependencies = [ + "derive_builder_macro", +] + +[[package]] +name = "derive_builder_core" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2d5bcf7b024d6835cfb3d473887cd966994907effbe9227e8c8219824d06c4e8" +dependencies = [ + "darling", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "derive_builder_macro" +version = "0.20.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c" +dependencies = [ + "derive_builder_core", + "syn", +] + +[[package]] +name = "digest" +version = "0.10.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292" +dependencies = [ + "block-buffer", + "crypto-common", +] + [[package]] name = "dirs" version = "5.0.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225" dependencies = [ - "dirs-sys", + "dirs-sys 0.4.1", +] + +[[package]] +name = "dirs" +version = "6.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c3e8aa94d75141228480295a7d0e7feb620b1a5ad9f12bc40be62411e38cce4e" +dependencies = [ + "dirs-sys 0.5.0", ] [[package]] @@ -320,10 +686,22 @@ checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c" dependencies = [ "libc", "option-ext", - "redox_users", + "redox_users 0.4.6", "windows-sys 0.48.0", ] +[[package]] +name = "dirs-sys" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e01a3366d27ee9890022452ee61b2b63a67e6f13f58900b651ff5665f0bb1fab" +dependencies = [ + "libc", + "option-ext", + "redox_users 0.5.2", + "windows-sys 0.61.2", +] + [[package]] name = "displaydoc" version = "0.2.5" @@ -341,6 +719,41 @@ version = "1.15.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719" +[[package]] +name = "encode_unicode" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0" + +[[package]] +name = "encoding_rs" +version = "0.8.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "equator" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4711b213838dfee0117e3be6ac926007d7f433d7bbe33595975d4190cb07e6fc" +dependencies = [ + "equator-macro", +] + +[[package]] +name = "equator-macro" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "44f23cf4b44bfce11a86ace86f8a73ffdec849c9fd00a386a53d278bd9e81fb3" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + [[package]] name = "equivalent" version = "1.0.2" @@ -357,6 +770,27 @@ dependencies = [ "windows-sys 0.61.2", ] +[[package]] +name = "esaxx-rs" +version = "0.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6" + +[[package]] +name = "exr" +version = "1.74.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4300e043a56aa2cb633c01af81ca8f699a321879a7854d3896a0ba89056363be" +dependencies = [ + "bit_field", + "half", + "lebe", + "miniz_oxide", + "rayon-core", + "smallvec", + "zune-inflate", +] + [[package]] name = "fallible-iterator" version = "0.3.0" @@ -369,6 +803,23 @@ version = "0.1.9" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a" +[[package]] +name = "fastembed" +version = "4.9.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "04c269a76bfc6cea69553b7d040acb16c793119cebd97c756d21e08d0f075ff8" +dependencies = [ + "anyhow", + "hf-hub", + "image", + "ndarray", + "ort", + "ort-sys", + "rayon", + "serde_json", + "tokenizers", +] + [[package]] name = "fastrand" version = "2.4.1" @@ -378,12 +829,48 @@ dependencies = [ "getrandom 0.3.4", ] +[[package]] +name = "fax" +version = "0.2.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "caf1079563223d5d59d83c85886a56e586cfd5c1a26292e971a0fa266531ac5a" + +[[package]] +name = "fdeflate" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e6853b52649d4ac5c0bd02320cddc5ba956bdb407c4b75a2c6b75bf51500f8c" +dependencies = [ + "simd-adler32", +] + +[[package]] +name = "filetime" +version = "0.2.27" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f98844151eee8917efc50bd9e8318cb963ae8b297431495d3f758616ea5c57db" +dependencies = [ + "cfg-if", + "libc", + "libredox", +] + [[package]] name = "find-msvc-tools" version = "0.1.9" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582" +[[package]] +name = "flate2" +version = "1.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c" +dependencies = [ + "crc32fast", + "miniz_oxide", +] + [[package]] name = "fnv" version = "1.0.7" @@ -396,6 +883,21 @@ version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2" +[[package]] +name = "foreign-types" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f6f339eb8adc052cd2ca78910fda869aefa38d22d5cb648e6485e4d3fc06f3b1" +dependencies = [ + "foreign-types-shared", +] + +[[package]] +name = "foreign-types-shared" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "00b0228411908ca8685dba7fc2cdd70ec9990a6e753e89b6ac91a84c40fbaf4b" + [[package]] name = "form_urlencoded" version = "1.2.2" @@ -411,12 +913,44 @@ version = "0.4.7" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7ab85b9b05e3978cc9a9cf8fea7f01b494e1a09ed3037e16ba39edc7a29eb61a" +[[package]] +name = "futures-channel" +version = "0.3.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07bbe89c50d7a535e539b8c17bc0b49bdb77747034daa8087407d655f3f7cc1d" +dependencies = [ + "futures-core", +] + [[package]] name = "futures-core" version = "0.3.32" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d" +[[package]] +name = "futures-io" +version = "0.3.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cecba35d7ad927e23624b22ad55235f2239cfa44fd10428eecbeba6d6a717718" + +[[package]] +name = "futures-macro" +version = "0.3.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e835b70203e41293343137df5c0664546da5745f82ec9b84d40be8336958447b" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "futures-sink" +version = "0.3.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c39754e157331b013978ec91992bde1ac089843443c49cbc7f46150b0fad0893" + [[package]] name = "futures-task" version = "0.3.32" @@ -430,11 +964,25 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6" dependencies = [ "futures-core", + "futures-io", + "futures-macro", + "futures-sink", "futures-task", + "memchr", "pin-project-lite", "slab", ] +[[package]] +name = "generic-array" +version = "0.14.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a" +dependencies = [ + "typenum", + "version_check", +] + [[package]] name = "getrandom" version = "0.2.17" @@ -473,6 +1021,16 @@ dependencies = [ "wasip3", ] +[[package]] +name = "gif" +version = "0.14.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee8cfcc411d9adbbaba82fb72661cc1bcca13e8bba98b364e62b2dba8f960159" +dependencies = [ + "color_quant", + "weezl", +] + [[package]] name = "globset" version = "0.4.18" @@ -486,6 +1044,36 @@ dependencies = [ "regex-syntax", ] +[[package]] +name = "h2" +version = "0.4.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54" +dependencies = [ + "atomic-waker", + "bytes", + "fnv", + "futures-core", + "futures-sink", + "http", + "indexmap", + "slab", + "tokio", + "tokio-util", + "tracing", +] + +[[package]] +name = "half" +version = "2.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b" +dependencies = [ + "cfg-if", + "crunchy", + "zerocopy", +] + [[package]] name = "hashbrown" version = "0.14.5" @@ -525,6 +1113,143 @@ version = "0.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" +[[package]] +name = "hf-hub" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97" +dependencies = [ + "dirs 6.0.0", + "http", + "indicatif", + "libc", + "log", + "native-tls", + "rand", + "reqwest", + "serde", + "serde_json", + "thiserror 2.0.18", + "ureq", + "windows-sys 0.60.2", +] + +[[package]] +name = "http" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3ba2a386d7f85a81f119ad7498ebe444d2e22c2af0b86b069416ace48b3311a" +dependencies = [ + "bytes", + "itoa", +] + +[[package]] +name = "http-body" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184" +dependencies = [ + "bytes", + "http", +] + +[[package]] +name = "http-body-util" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a" +dependencies = [ + "bytes", + "futures-core", + "http", + "http-body", + "pin-project-lite", +] + +[[package]] +name = "httparse" +version = "1.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87" + +[[package]] +name = "hyper" +version = "1.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6299f016b246a94207e63da54dbe807655bf9e00044f73ded42c3ac5305fbcca" +dependencies = [ + "atomic-waker", + "bytes", + "futures-channel", + "futures-core", + "h2", + "http", + "http-body", + "httparse", + "itoa", + "pin-project-lite", + "smallvec", + "tokio", + "want", +] + +[[package]] +name = "hyper-rustls" +version = "0.27.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f" +dependencies = [ + "http", + "hyper", + "hyper-util", + "rustls", + "tokio", + "tokio-rustls", + "tower-service", +] + +[[package]] +name = "hyper-tls" +version = "0.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0" +dependencies = [ + "bytes", + "http-body-util", + "hyper", + "hyper-util", + "native-tls", + "tokio", + "tokio-native-tls", + "tower-service", +] + +[[package]] +name = "hyper-util" +version = "0.1.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0" +dependencies = [ + "base64 0.22.1", + "bytes", + "futures-channel", + "futures-util", + "http", + "http-body", + "hyper", + "ipnet", + "libc", + "percent-encoding", + "pin-project-lite", + "socket2", + "system-configuration", + "tokio", + "tower-service", + "tracing", + "windows-registry", +] + [[package]] name = "icu_collections" version = "2.1.1" @@ -612,6 +1337,12 @@ version = "2.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954" +[[package]] +name = "ident_case" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39" + [[package]] name = "idna" version = "1.1.0" @@ -649,6 +1380,46 @@ dependencies = [ "winapi-util", ] +[[package]] +name = "image" +version = "0.25.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e6506c6c10786659413faa717ceebcb8f70731c0a60cbae39795fdf114519c1a" +dependencies = [ + "bytemuck", + "byteorder-lite", + "color_quant", + "exr", + "gif", + "image-webp", + "moxcms", + "num-traits", + "png", + "qoi", + "ravif", + "rayon", + "rgb", + "tiff", + "zune-core 0.5.1", + "zune-jpeg 0.5.15", +] + +[[package]] +name = "image-webp" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "525e9ff3e1a4be2fbea1fdf0e98686a6d98b4d8f937e1bf7402245af1909e8c3" +dependencies = [ + "byteorder-lite", + "quick-error 2.0.1", +] + +[[package]] +name = "imgref" +version = "1.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "40fac9d56ed6437b198fddba683305e8e2d651aa42647f00f5ae542e7f5c94a2" + [[package]] name = "include_dir" version = "0.7.4" @@ -680,6 +1451,46 @@ dependencies = [ "serde_core", ] +[[package]] +name = "indicatif" +version = "0.17.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "183b3088984b400f4cfac3620d5e076c84da5364016b4f49473de574b2586235" +dependencies = [ + "console", + "number_prefix", + "portable-atomic", + "unicode-width", + "web-time", +] + +[[package]] +name = "interpolate_name" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c34819042dc3d3971c46c2190835914dfbe0c3c13f61449b2997f4e9722dfa60" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "ipnet" +version = "2.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d98f6fed1fde3f8c21bc40a1abb88dd75e67924f9cffc3ef95607bad8017f8e2" + +[[package]] +name = "iri-string" +version = "0.7.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "25e659a4bb38e810ebc252e53b5814ff908a8c58c2a9ce2fae1bbec24cbf4e20" +dependencies = [ + "memchr", + "serde", +] + [[package]] name = "is_terminal_polyfill" version = "1.70.2" @@ -701,6 +1512,16 @@ version = "1.0.18" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682" +[[package]] +name = "jobserver" +version = "0.1.34" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33" +dependencies = [ + "getrandom 0.3.4", + "libc", +] + [[package]] name = "js-sys" version = "0.3.97" @@ -718,7 +1539,7 @@ name = "kb-app" version = "0.1.0" dependencies = [ "anyhow", - "dirs", + "dirs 5.0.1", "kb-config", "kb-core", "serde", @@ -761,7 +1582,7 @@ name = "kb-config" version = "0.1.0" dependencies = [ "anyhow", - "dirs", + "dirs 5.0.1", "kb-core", "serde", "serde_json", @@ -796,6 +1617,19 @@ dependencies = [ "tracing", ] +[[package]] +name = "kb-embed-local" +version = "0.1.0" +dependencies = [ + "anyhow", + "fastembed", + "kb-config", + "kb-embed", + "serde_json", + "tempfile", + "tracing", +] + [[package]] name = "kb-normalize" version = "0.1.0" @@ -901,19 +1735,38 @@ version = "0.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2" +[[package]] +name = "lebe" +version = "0.5.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a79a3332a6609480d7d0c9eab957bca6b455b91bb84e66d19f5ff66294b85b8" + [[package]] name = "libc" version = "0.2.186" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66" +[[package]] +name = "libfuzzer-sys" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f12a681b7dd8ce12bff52488013ba614b869148d54dd79836ab85aafdd53f08d" +dependencies = [ + "arbitrary", + "cc", +] + [[package]] name = "libredox" version = "0.1.16" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e02f3bb43d335493c96bf3fd3a321600bf6bd07ed34bc64118e9293bdffea46c" dependencies = [ + "bitflags", "libc", + "plain", + "redox_syscall 0.7.4", ] [[package]] @@ -1016,6 +1869,31 @@ version = "0.4.29" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897" +[[package]] +name = "loop9" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fae87c125b03c1d2c0150c90365d7d6bcc53fb73a9acaef207d2d065860f062" +dependencies = [ + "imgref", +] + +[[package]] +name = "macro_rules_attribute" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "65049d7923698040cd0b1ddcced9b0eb14dd22c5f86ae59c3740eab64a676520" +dependencies = [ + "macro_rules_attribute-proc_macro", + "paste", +] + +[[package]] +name = "macro_rules_attribute-proc_macro" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "670fdfda89751bc4a84ac13eaa63e205cf0fd22b4c9a5fbfa085b63c1f1d3a30" + [[package]] name = "maplit" version = "1.0.2" @@ -1031,12 +1909,169 @@ dependencies = [ "regex-automata", ] +[[package]] +name = "matrixmultiply" +version = "0.3.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08" +dependencies = [ + "autocfg", + "rawpointer", +] + +[[package]] +name = "maybe-rayon" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ea1f30cedd69f0a2954655f7188c6a834246d2bcf1e315e2ac40c4b24dc9519" +dependencies = [ + "cfg-if", + "rayon", +] + [[package]] name = "memchr" version = "2.8.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79" +[[package]] +name = "mime" +version = "0.3.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a" + +[[package]] +name = "minimal-lexical" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a" + +[[package]] +name = "miniz_oxide" +version = "0.8.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316" +dependencies = [ + "adler2", + "simd-adler32", +] + +[[package]] +name = "mio" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "50b7e5b27aa02a74bac8c3f23f448f8d87ff11f92d3aac1a6ed369ee08cc56c1" +dependencies = [ + "libc", + "wasi", + "windows-sys 0.61.2", +] + +[[package]] +name = "monostate" +version = "0.1.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3341a273f6c9d5bef1908f17b7267bbab0e95c9bf69a0d4dcf8e9e1b2c76ef67" +dependencies = [ + "monostate-impl", + "serde", + "serde_core", +] + +[[package]] +name = "monostate-impl" +version = "0.1.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e4db6d5580af57bf992f59068d4ea26fd518574ff48d7639b255a36f9de6e7e9" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "moxcms" +version = "0.7.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ac9557c559cd6fc9867e122e20d2cbefc9ca29d80d027a8e39310920ed2f0a97" +dependencies = [ + "num-traits", + "pxfm", +] + +[[package]] +name = "native-tls" +version = "0.2.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "465500e14ea162429d264d44189adc38b199b62b1c21eea9f69e4b73cb03bbf2" +dependencies = [ + "libc", + "log", + "openssl", + "openssl-probe", + "openssl-sys", + "schannel", + "security-framework", + "security-framework-sys", + "tempfile", +] + +[[package]] +name = "ndarray" +version = "0.16.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "882ed72dce9365842bf196bdeedf5055305f11fc8c03dee7bb0194a6cad34841" +dependencies = [ + "matrixmultiply", + "num-complex", + "num-integer", + "num-traits", + "portable-atomic", + "portable-atomic-util", + "rawpointer", +] + +[[package]] +name = "new_debug_unreachable" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086" + +[[package]] +name = "no_std_io2" +version = "0.9.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b51ed7824b6e07d354605f4abb3d9d300350701299da96642ee084f5ce631550" +dependencies = [ + "memchr", +] + +[[package]] +name = "nom" +version = "7.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a" +dependencies = [ + "memchr", + "minimal-lexical", +] + +[[package]] +name = "nom" +version = "8.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df9761775871bdef83bee530e60050f7e54b1105350d6884eb0fb4f46c2f9405" +dependencies = [ + "memchr", +] + +[[package]] +name = "noop_proc_macro" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0676bb32a98c1a483ce53e500a81ad9c3d5b3f7c920c28c24e9cb0980d0b5bc8" + [[package]] name = "nu-ansi-term" version = "0.50.3" @@ -1046,12 +2081,62 @@ dependencies = [ "windows-sys 0.61.2", ] +[[package]] +name = "num-bigint" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a5e44f723f1133c9deac646763579fdb3ac745e418f2a7af9cd0c431da1f20b9" +dependencies = [ + "num-integer", + "num-traits", +] + +[[package]] +name = "num-complex" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495" +dependencies = [ + "num-traits", +] + [[package]] name = "num-conv" version = "0.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9" +[[package]] +name = "num-derive" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ed3955f1a9c7c0c15e092f9c887db08b1fc683305fdf6eb6684f22555355e202" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "num-integer" +version = "0.1.46" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f" +dependencies = [ + "num-traits", +] + +[[package]] +name = "num-rational" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824" +dependencies = [ + "num-bigint", + "num-integer", + "num-traits", +] + [[package]] name = "num-traits" version = "0.2.19" @@ -1061,6 +2146,12 @@ dependencies = [ "autocfg", ] +[[package]] +name = "number_prefix" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3" + [[package]] name = "once_cell" version = "1.21.4" @@ -1073,12 +2164,102 @@ version = "1.70.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe" +[[package]] +name = "onig" +version = "6.5.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0cc3cbf698f9438986c11a880c90a6d04b9de27575afd28bbf45b154b6c709e2" +dependencies = [ + "bitflags", + "libc", + "once_cell", + "onig_sys", +] + +[[package]] +name = "onig_sys" +version = "69.9.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e68317604e77e53b85896388e1a803c1d21b74c899ec9e5e1112db90735edd7" +dependencies = [ + "cc", + "pkg-config", +] + +[[package]] +name = "openssl" +version = "0.10.78" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f38c4372413cdaaf3cc79dd92d29d7d9f5ab09b51b10dded508fb90bb70b9222" +dependencies = [ + "bitflags", + "cfg-if", + "foreign-types", + "libc", + "once_cell", + "openssl-macros", + "openssl-sys", +] + +[[package]] +name = "openssl-macros" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "openssl-probe" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe" + +[[package]] +name = "openssl-sys" +version = "0.9.114" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13ce1245cd07fcc4cfdb438f7507b0c7e4f3849a69fd84d52374c66d83741bb6" +dependencies = [ + "cc", + "libc", + "pkg-config", + "vcpkg", +] + [[package]] name = "option-ext" version = "0.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d" +[[package]] +name = "ort" +version = "2.0.0-rc.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "52afb44b6b0cffa9bf45e4d37e5a4935b0334a51570658e279e9e3e6cf324aa5" +dependencies = [ + "ndarray", + "ort-sys", + "tracing", +] + +[[package]] +name = "ort-sys" +version = "2.0.0-rc.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c41d7757331aef2d04b9cb09b45583a59217628beaf91895b7e76187b6e8c088" +dependencies = [ + "flate2", + "pkg-config", + "sha2", + "tar", + "ureq", +] + [[package]] name = "parking_lot_core" version = "0.9.12" @@ -1087,11 +2268,23 @@ checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1" dependencies = [ "cfg-if", "libc", - "redox_syscall", + "redox_syscall 0.5.18", "smallvec", "windows-link", ] +[[package]] +name = "paste" +version = "1.0.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" + +[[package]] +name = "pastey" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "35fb2e5f958ec131621fdd531e9fc186ed768cbe395337403ae56c17a74c68ec" + [[package]] name = "percent-encoding" version = "2.3.2" @@ -1110,6 +2303,40 @@ version = "0.3.33" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e" +[[package]] +name = "plain" +version = "0.2.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b4596b6d070b27117e987119b4dac604f3c58cfb0b191112e24771b2faeac1a6" + +[[package]] +name = "png" +version = "0.18.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "60769b8b31b2a9f263dae2776c37b1b28ae246943cf719eb6946a1db05128a61" +dependencies = [ + "bitflags", + "crc32fast", + "fdeflate", + "flate2", + "miniz_oxide", +] + +[[package]] +name = "portable-atomic" +version = "1.13.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49" + +[[package]] +name = "portable-atomic-util" +version = "0.2.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c2a106d1259c23fac8e543272398ae0e3c0b8d33c88ed73d0cc71b0f1d902618" +dependencies = [ + "portable-atomic", +] + [[package]] name = "potential_utf" version = "0.1.5" @@ -1153,6 +2380,25 @@ dependencies = [ "unicode-ident", ] +[[package]] +name = "profiling" +version = "1.0.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3eb8486b569e12e2c32ad3e204dbaba5e4b5b216e9367044f25f1dba42341773" +dependencies = [ + "profiling-procmacros", +] + +[[package]] +name = "profiling-procmacros" +version = "1.0.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "52717f9a02b6965224f95ca2a81e2e0c5c43baacd28ca057577988930b6c3d5b" +dependencies = [ + "quote", + "syn", +] + [[package]] name = "proptest" version = "1.11.0" @@ -1183,12 +2429,33 @@ dependencies = [ "unicase", ] +[[package]] +name = "pxfm" +version = "0.1.29" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e0c5ccf5294c6ccd63a74f1565028353830a9c2f5eb0c682c355c471726a6e3f" + +[[package]] +name = "qoi" +version = "0.4.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f6d64c71eb498fe9eae14ce4ec935c555749aef511cca85b5568910d6e48001" +dependencies = [ + "bytemuck", +] + [[package]] name = "quick-error" version = "1.2.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0" +[[package]] +name = "quick-error" +version = "2.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3" + [[package]] name = "quote" version = "1.0.45" @@ -1248,6 +2515,62 @@ dependencies = [ "rand_core", ] +[[package]] +name = "rav1e" +version = "0.8.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "43b6dd56e85d9483277cde964fd1bdb0428de4fec5ebba7540995639a21cb32b" +dependencies = [ + "aligned-vec", + "arbitrary", + "arg_enum_proc_macro", + "arrayvec", + "av-scenechange", + "av1-grain", + "bitstream-io", + "built", + "cfg-if", + "interpolate_name", + "itertools", + "libc", + "libfuzzer-sys", + "log", + "maybe-rayon", + "new_debug_unreachable", + "noop_proc_macro", + "num-derive", + "num-traits", + "paste", + "profiling", + "rand", + "rand_chacha", + "simd_helpers", + "thiserror 2.0.18", + "v_frame", + "wasm-bindgen", +] + +[[package]] +name = "ravif" +version = "0.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ef69c1990ceef18a116855938e74793a5f7496ee907562bd0857b6ac734ab285" +dependencies = [ + "avif-serialize", + "imgref", + "loop9", + "quick-error 2.0.1", + "rav1e", + "rayon", + "rgb", +] + +[[package]] +name = "rawpointer" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3" + [[package]] name = "rayon" version = "1.12.0" @@ -1258,6 +2581,17 @@ dependencies = [ "rayon-core", ] +[[package]] +name = "rayon-cond" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2964d0cf57a3e7a06e8183d14a8b527195c706b7983549cd5462d5aa3747438f" +dependencies = [ + "either", + "itertools", + "rayon", +] + [[package]] name = "rayon-core" version = "1.13.0" @@ -1277,6 +2611,15 @@ dependencies = [ "bitflags", ] +[[package]] +name = "redox_syscall" +version = "0.7.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f450ad9c3b1da563fb6948a8e0fb0fb9269711c9c73d9ea1de5058c79c8d643a" +dependencies = [ + "bitflags", +] + [[package]] name = "redox_users" version = "0.4.6" @@ -1288,6 +2631,17 @@ dependencies = [ "thiserror 1.0.69", ] +[[package]] +name = "redox_users" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a4e608c6638b9c18977b00b475ac1f28d14e84b27d8d42f70e0bf1e3dec127ac" +dependencies = [ + "getrandom 0.2.17", + "libredox", + "thiserror 2.0.18", +] + [[package]] name = "refinery" version = "0.8.16" @@ -1361,6 +2715,69 @@ version = "0.8.10" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a" +[[package]] +name = "reqwest" +version = "0.12.28" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147" +dependencies = [ + "base64 0.22.1", + "bytes", + "encoding_rs", + "futures-core", + "futures-util", + "h2", + "http", + "http-body", + "http-body-util", + "hyper", + "hyper-rustls", + "hyper-tls", + "hyper-util", + "js-sys", + "log", + "mime", + "native-tls", + "percent-encoding", + "pin-project-lite", + "rustls-pki-types", + "serde", + "serde_json", + "serde_urlencoded", + "sync_wrapper", + "tokio", + "tokio-native-tls", + "tokio-util", + "tower", + "tower-http", + "tower-service", + "url", + "wasm-bindgen", + "wasm-bindgen-futures", + "wasm-streams", + "web-sys", +] + +[[package]] +name = "rgb" +version = "0.8.53" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "47b34b781b31e5d73e9fbc8689c70551fd1ade9a19e3e28cfec8580a79290cc4" + +[[package]] +name = "ring" +version = "0.17.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7" +dependencies = [ + "cc", + "cfg-if", + "getrandom 0.2.17", + "libc", + "untrusted", + "windows-sys 0.52.0", +] + [[package]] name = "rusqlite" version = "0.32.1" @@ -1388,6 +2805,41 @@ dependencies = [ "windows-sys 0.61.2", ] +[[package]] +name = "rustls" +version = "0.23.40" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ef86cd5876211988985292b91c96a8f2d298df24e75989a43a3c73f2d4d8168b" +dependencies = [ + "log", + "once_cell", + "ring", + "rustls-pki-types", + "rustls-webpki", + "subtle", + "zeroize", +] + +[[package]] +name = "rustls-pki-types" +version = "1.14.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "30a7197ae7eb376e574fe940d068c30fe0462554a3ddbe4eca7838e049c937a9" +dependencies = [ + "zeroize", +] + +[[package]] +name = "rustls-webpki" +version = "0.103.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e" +dependencies = [ + "ring", + "rustls-pki-types", + "untrusted", +] + [[package]] name = "rustversion" version = "1.0.22" @@ -1401,7 +2853,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "cc6bf79ff24e648f6da1f8d1f011e9cac26491b619e6b9280f2b47f1774e6ee2" dependencies = [ "fnv", - "quick-error", + "quick-error 1.2.3", "tempfile", "wait-timeout", ] @@ -1427,12 +2879,44 @@ dependencies = [ "winapi-util", ] +[[package]] +name = "schannel" +version = "0.1.29" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939" +dependencies = [ + "windows-sys 0.61.2", +] + [[package]] name = "scopeguard" version = "1.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" +[[package]] +name = "security-framework" +version = "3.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d" +dependencies = [ + "bitflags", + "core-foundation 0.10.1", + "core-foundation-sys", + "libc", + "security-framework-sys", +] + +[[package]] +name = "security-framework-sys" +version = "2.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ce2691df843ecc5d231c0b14ece2acc3efb62c0a398c7e1d875f3983ce020e3" +dependencies = [ + "core-foundation-sys", + "libc", +] + [[package]] name = "semver" version = "1.0.28" @@ -1513,6 +2997,18 @@ dependencies = [ "serde", ] +[[package]] +name = "serde_urlencoded" +version = "0.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd" +dependencies = [ + "form_urlencoded", + "itoa", + "ryu", + "serde", +] + [[package]] name = "serde_yaml_ng" version = "0.10.0" @@ -1526,6 +3022,17 @@ dependencies = [ "unsafe-libyaml", ] +[[package]] +name = "sha2" +version = "0.10.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283" +dependencies = [ + "cfg-if", + "cpufeatures 0.2.17", + "digest", +] + [[package]] name = "sharded-slab" version = "0.1.7" @@ -1541,6 +3048,21 @@ version = "1.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64" +[[package]] +name = "simd-adler32" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214" + +[[package]] +name = "simd_helpers" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "95890f873bec569a0362c235787f3aca6e1e887302ba4840839bcc6459c42da6" +dependencies = [ + "quote", +] + [[package]] name = "siphasher" version = "1.0.2" @@ -1559,12 +3081,51 @@ version = "1.15.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03" +[[package]] +name = "socket2" +version = "0.6.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3a766e1110788c36f4fa1c2b71b387a7815aa65f88ce0229841826633d93723e" +dependencies = [ + "libc", + "windows-sys 0.61.2", +] + +[[package]] +name = "socks" +version = "0.3.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f0c3dbbd9ae980613c6dd8e28a9407b50509d3803b57624d5dfe8315218cd58b" +dependencies = [ + "byteorder", + "libc", + "winapi", +] + +[[package]] +name = "spm_precompiled" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5851699c4033c63636f7ea4cf7b7c1f1bf06d0cc03cfb42e711de5a5c46cf326" +dependencies = [ + "base64 0.13.1", + "nom 7.1.3", + "serde", + "unicode-segmentation", +] + [[package]] name = "stable_deref_trait" version = "1.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596" +[[package]] +name = "static_assertions" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f" + [[package]] name = "strsim" version = "0.11.1" @@ -1589,6 +3150,12 @@ dependencies = [ "syn", ] +[[package]] +name = "subtle" +version = "2.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292" + [[package]] name = "symlink" version = "0.1.0" @@ -1606,6 +3173,15 @@ dependencies = [ "unicode-ident", ] +[[package]] +name = "sync_wrapper" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263" +dependencies = [ + "futures-core", +] + [[package]] name = "synstructure" version = "0.13.2" @@ -1617,6 +3193,38 @@ dependencies = [ "syn", ] +[[package]] +name = "system-configuration" +version = "0.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a13f3d0daba03132c0aa9767f98351b3488edc2c100cda2d2ec2b04f3d8d3c8b" +dependencies = [ + "bitflags", + "core-foundation 0.9.4", + "system-configuration-sys", +] + +[[package]] +name = "system-configuration-sys" +version = "0.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e1d1b10ced5ca923a1fcb8d03e96b8d3268065d724548c0211415ff6ac6bac4" +dependencies = [ + "core-foundation-sys", + "libc", +] + +[[package]] +name = "tar" +version = "0.4.45" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "22692a6476a21fa75fdfc11d452fda482af402c008cdbaf3476414e122040973" +dependencies = [ + "filetime", + "libc", + "xattr", +] + [[package]] name = "tempfile" version = "3.27.0" @@ -1679,6 +3287,20 @@ dependencies = [ "cfg-if", ] +[[package]] +name = "tiff" +version = "0.10.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "af9605de7fee8d9551863fd692cce7637f548dbd9db9180fcc07ccc6d26c336f" +dependencies = [ + "fax", + "flate2", + "half", + "quick-error 2.0.1", + "weezl", + "zune-jpeg 0.4.21", +] + [[package]] name = "time" version = "0.3.45" @@ -1735,6 +3357,86 @@ version = "0.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" +[[package]] +name = "tokenizers" +version = "0.21.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a620b996116a59e184c2fa2dfd8251ea34a36d0a514758c6f966386bd2e03476" +dependencies = [ + "ahash", + "aho-corasick", + "compact_str", + "dary_heap", + "derive_builder", + "esaxx-rs", + "getrandom 0.3.4", + "itertools", + "log", + "macro_rules_attribute", + "monostate", + "onig", + "paste", + "rand", + "rayon", + "rayon-cond", + "regex", + "regex-syntax", + "serde", + "serde_json", + "spm_precompiled", + "thiserror 2.0.18", + "unicode-normalization-alignments", + "unicode-segmentation", + "unicode_categories", +] + +[[package]] +name = "tokio" +version = "1.52.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b67dee974fe86fd92cc45b7a95fdd2f99a36a6d7b0d431a231178d3d670bbcc6" +dependencies = [ + "bytes", + "libc", + "mio", + "pin-project-lite", + "socket2", + "windows-sys 0.61.2", +] + +[[package]] +name = "tokio-native-tls" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2" +dependencies = [ + "native-tls", + "tokio", +] + +[[package]] +name = "tokio-rustls" +version = "0.26.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1729aa945f29d91ba541258c8df89027d5792d85a8841fb65e8bf0f4ede4ef61" +dependencies = [ + "rustls", + "tokio", +] + +[[package]] +name = "tokio-util" +version = "0.7.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ae9cec805b01e8fc3fd2fe289f89149a9b66dd16786abd8b19cfa7b48cb0098" +dependencies = [ + "bytes", + "futures-core", + "futures-sink", + "pin-project-lite", + "tokio", +] + [[package]] name = "toml" version = "0.8.23" @@ -1776,6 +3478,51 @@ version = "0.1.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801" +[[package]] +name = "tower" +version = "0.5.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ebe5ef63511595f1344e2d5cfa636d973292adc0eec1f0ad45fae9f0851ab1d4" +dependencies = [ + "futures-core", + "futures-util", + "pin-project-lite", + "sync_wrapper", + "tokio", + "tower-layer", + "tower-service", +] + +[[package]] +name = "tower-http" +version = "0.6.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d4e6559d53cc268e5031cd8429d05415bc4cb4aefc4aa5d6cc35fbf5b924a1f8" +dependencies = [ + "bitflags", + "bytes", + "futures-util", + "http", + "http-body", + "iri-string", + "pin-project-lite", + "tower", + "tower-layer", + "tower-service", +] + +[[package]] +name = "tower-layer" +version = "0.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e" + +[[package]] +name = "tower-service" +version = "0.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3" + [[package]] name = "tracing" version = "0.1.44" @@ -1863,6 +3610,18 @@ dependencies = [ "tracing-serde", ] +[[package]] +name = "try-lock" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b" + +[[package]] +name = "typenum" +version = "1.20.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "40ce102ab67701b8526c123c1bab5cbe42d7040ccfd0f64af1a385808d2f43de" + [[package]] name = "unarray" version = "0.1.4" @@ -1890,18 +3649,71 @@ dependencies = [ "tinyvec", ] +[[package]] +name = "unicode-normalization-alignments" +version = "0.1.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "43f613e4fa046e69818dd287fdc4bc78175ff20331479dab6e1b0f98d57062de" +dependencies = [ + "smallvec", +] + +[[package]] +name = "unicode-segmentation" +version = "1.13.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9629274872b2bfaf8d66f5f15725007f635594914870f65218920345aa11aa8c" + +[[package]] +name = "unicode-width" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254" + [[package]] name = "unicode-xid" version = "0.2.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853" +[[package]] +name = "unicode_categories" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e" + [[package]] name = "unsafe-libyaml" version = "0.2.11" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861" +[[package]] +name = "untrusted" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1" + +[[package]] +name = "ureq" +version = "2.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "02d1a66277ed75f640d608235660df48c8e3c19f3b4edb6a263315626cc3c01d" +dependencies = [ + "base64 0.22.1", + "flate2", + "log", + "native-tls", + "once_cell", + "rustls", + "rustls-pki-types", + "serde", + "serde_json", + "socks", + "url", + "webpki-roots 0.26.11", +] + [[package]] name = "url" version = "2.5.8" @@ -1926,6 +3738,17 @@ version = "0.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" +[[package]] +name = "v_frame" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "666b7727c8875d6ab5db9533418d7c764233ac9c0cff1d469aec8fa127597be2" +dependencies = [ + "aligned-vec", + "num-traits", + "wasm-bindgen", +] + [[package]] name = "valuable" version = "0.1.1" @@ -1963,6 +3786,15 @@ dependencies = [ "winapi-util", ] +[[package]] +name = "want" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e" +dependencies = [ + "try-lock", +] + [[package]] name = "wasi" version = "0.11.1+wasi-snapshot-preview1" @@ -2000,6 +3832,16 @@ dependencies = [ "wasm-bindgen-shared", ] +[[package]] +name = "wasm-bindgen-futures" +version = "0.4.70" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "af934872acec734c2d80e6617bbb5ff4f12b052dd8e6332b0817bce889516084" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + [[package]] name = "wasm-bindgen-macro" version = "0.2.120" @@ -2054,6 +3896,19 @@ dependencies = [ "wasmparser", ] +[[package]] +name = "wasm-streams" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "15053d8d85c7eccdbefef60f06769760a563c7f0a9d6902a13d35c7800b0ad65" +dependencies = [ + "futures-util", + "js-sys", + "wasm-bindgen", + "wasm-bindgen-futures", + "web-sys", +] + [[package]] name = "wasmparser" version = "0.244.0" @@ -2066,6 +3921,66 @@ dependencies = [ "semver", ] +[[package]] +name = "web-sys" +version = "0.3.97" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2eadbac71025cd7b0834f20d1fe8472e8495821b4e9801eb0a60bd1f19827602" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "web-time" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "webpki-roots" +version = "0.26.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "521bc38abb08001b01866da9f51eb7c5d647a19260e00054a8c7fd5f9e57f7a9" +dependencies = [ + "webpki-roots 1.0.7", +] + +[[package]] +name = "webpki-roots" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "52f5ee44c96cf55f1b349600768e3ece3a8f26010c05265ab73f945bb1a2eb9d" +dependencies = [ + "rustls-pki-types", +] + +[[package]] +name = "weezl" +version = "0.1.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a28ac98ddc8b9274cb41bb4d9d4d5c425b6020c50c46f25559911905610b4a88" + +[[package]] +name = "winapi" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419" +dependencies = [ + "winapi-i686-pc-windows-gnu", + "winapi-x86_64-pc-windows-gnu", +] + +[[package]] +name = "winapi-i686-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6" + [[package]] name = "winapi-util" version = "0.1.11" @@ -2075,19 +3990,81 @@ dependencies = [ "windows-sys 0.61.2", ] +[[package]] +name = "winapi-x86_64-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" + [[package]] name = "windows-link" version = "0.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5" +[[package]] +name = "windows-registry" +version = "0.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "02752bf7fbdcce7f2a27a742f798510f3e5ad88dbe84871e5168e2120c3d5720" +dependencies = [ + "windows-link", + "windows-result", + "windows-strings", +] + +[[package]] +name = "windows-result" +version = "0.4.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5" +dependencies = [ + "windows-link", +] + +[[package]] +name = "windows-strings" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091" +dependencies = [ + "windows-link", +] + [[package]] name = "windows-sys" version = "0.48.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9" dependencies = [ - "windows-targets", + "windows-targets 0.48.5", +] + +[[package]] +name = "windows-sys" +version = "0.52.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d" +dependencies = [ + "windows-targets 0.52.6", +] + +[[package]] +name = "windows-sys" +version = "0.59.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b" +dependencies = [ + "windows-targets 0.52.6", +] + +[[package]] +name = "windows-sys" +version = "0.60.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f2f500e4d28234f72040990ec9d39e3a6b950f9f22d3dba18416c35882612bcb" +dependencies = [ + "windows-targets 0.53.5", ] [[package]] @@ -2105,13 +4082,46 @@ version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c" dependencies = [ - "windows_aarch64_gnullvm", - "windows_aarch64_msvc", - "windows_i686_gnu", - "windows_i686_msvc", - "windows_x86_64_gnu", - "windows_x86_64_gnullvm", - "windows_x86_64_msvc", + "windows_aarch64_gnullvm 0.48.5", + "windows_aarch64_msvc 0.48.5", + "windows_i686_gnu 0.48.5", + "windows_i686_msvc 0.48.5", + "windows_x86_64_gnu 0.48.5", + "windows_x86_64_gnullvm 0.48.5", + "windows_x86_64_msvc 0.48.5", +] + +[[package]] +name = "windows-targets" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" +dependencies = [ + "windows_aarch64_gnullvm 0.52.6", + "windows_aarch64_msvc 0.52.6", + "windows_i686_gnu 0.52.6", + "windows_i686_gnullvm 0.52.6", + "windows_i686_msvc 0.52.6", + "windows_x86_64_gnu 0.52.6", + "windows_x86_64_gnullvm 0.52.6", + "windows_x86_64_msvc 0.52.6", +] + +[[package]] +name = "windows-targets" +version = "0.53.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4945f9f551b88e0d65f3db0bc25c33b8acea4d9e41163edf90dcd0b19f9069f3" +dependencies = [ + "windows-link", + "windows_aarch64_gnullvm 0.53.1", + "windows_aarch64_msvc 0.53.1", + "windows_i686_gnu 0.53.1", + "windows_i686_gnullvm 0.53.1", + "windows_i686_msvc 0.53.1", + "windows_x86_64_gnu 0.53.1", + "windows_x86_64_gnullvm 0.53.1", + "windows_x86_64_msvc 0.53.1", ] [[package]] @@ -2120,42 +4130,138 @@ version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8" +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a9d8416fa8b42f5c947f8482c43e7d89e73a173cead56d044f6a56104a6d1b53" + [[package]] name = "windows_aarch64_msvc" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc" +[[package]] +name = "windows_aarch64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b9d782e804c2f632e395708e99a94275910eb9100b2114651e04744e9b125006" + [[package]] name = "windows_i686_gnu" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e" +[[package]] +name = "windows_i686_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" + +[[package]] +name = "windows_i686_gnu" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "960e6da069d81e09becb0ca57a65220ddff016ff2d6af6a223cf372a506593a3" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa7359d10048f68ab8b09fa71c3daccfb0e9b559aed648a8f95469c27057180c" + [[package]] name = "windows_i686_msvc" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406" +[[package]] +name = "windows_i686_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" + +[[package]] +name = "windows_i686_msvc" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e7ac75179f18232fe9c285163565a57ef8d3c89254a30685b57d83a38d326c2" + [[package]] name = "windows_x86_64_gnu" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e" +[[package]] +name = "windows_x86_64_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c3842cdd74a865a8066ab39c8a7a473c0778a3f29370b5fd6b4b9aa7df4a499" + [[package]] name = "windows_x86_64_gnullvm" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc" +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0ffa179e2d07eee8ad8f57493436566c7cc30ac536a3379fdf008f47f6bb7ae1" + [[package]] name = "windows_x86_64_msvc" version = "0.48.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538" +[[package]] +name = "windows_x86_64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.53.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d6bbff5f0aada427a1e5a6da5f1f98158182f26556f345ac9e04d36d0ebed650" + [[package]] name = "winnow" version = "0.7.15" @@ -2265,6 +4371,22 @@ version = "0.6.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4" +[[package]] +name = "xattr" +version = "1.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32e45ad4206f6d2479085147f02bc2ef834ac85886624a23575ae137c8aa8156" +dependencies = [ + "libc", + "rustix", +] + +[[package]] +name = "y4m" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a5a4b21e1a62b67a2970e6831bc091d7b87e119e7f9791aef9702e3bef04448" + [[package]] name = "yoke" version = "0.8.2" @@ -2329,6 +4451,12 @@ dependencies = [ "synstructure", ] +[[package]] +name = "zeroize" +version = "1.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0" + [[package]] name = "zerotrie" version = "0.2.4" @@ -2367,3 +4495,42 @@ name = "zmij" version = "1.0.21" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa" + +[[package]] +name = "zune-core" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f423a2c17029964870cfaabb1f13dfab7d092a62a29a89264f4d36990ca414a" + +[[package]] +name = "zune-core" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cb8a0807f7c01457d0379ba880ba6322660448ddebc890ce29bb64da71fb40f9" + +[[package]] +name = "zune-inflate" +version = "0.2.54" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "73ab332fe2f6680068f3582b16a24f90ad7096d5d39b974d1c0aff0125116f02" +dependencies = [ + "simd-adler32", +] + +[[package]] +name = "zune-jpeg" +version = "0.4.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29ce2c8a9384ad323cf564b67da86e21d3cfdff87908bc1223ed5c99bc792713" +dependencies = [ + "zune-core 0.4.12", +] + +[[package]] +name = "zune-jpeg" +version = "0.5.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "27bc9d5b815bc103f142aa054f561d9187d191692ec7c2d1e2b4737f8dbd7296" +dependencies = [ + "zune-core 0.5.1", +] diff --git a/Cargo.toml b/Cargo.toml index 3e81b7d..dad33db 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -11,6 +11,7 @@ members = [ "crates/kb-store-sqlite", "crates/kb-search", "crates/kb-embed", + "crates/kb-embed-local", "crates/kb-app", "crates/kb-cli", ] @@ -37,3 +38,8 @@ rusqlite = { version = "0.32", features = ["bundled"] } globset = "0.4" tempfile = "3" proptest = "1" +# fastembed-rs ships ONNX runtime via the `ort-download-binaries` feature +# in its default set (which also pulls `hf-hub` for first-run model +# downloads). Pinned to the 4.x line per task p3-2 (current 5.x release +# remains untested for this workspace). +fastembed = "4.9" diff --git a/crates/kb-embed-local/Cargo.toml b/crates/kb-embed-local/Cargo.toml new file mode 100644 index 0000000..3a32217 --- /dev/null +++ b/crates/kb-embed-local/Cargo.toml @@ -0,0 +1,22 @@ +[package] +name = "kb-embed-local" +version = { workspace = true } +edition = { workspace = true } +rust-version = { workspace = true } +license = { workspace = true } +repository = { workspace = true } +description = "Local fastembed-rs adapter implementing kb_core::Embedder (multilingual-e5-small default)" + +[dependencies] +kb-config = { path = "../kb-config" } +kb-embed = { path = "../kb-embed" } +# Default features bring `ort-download-binaries` (bundled ONNX runtime) +# and `hf-hub-native-tls` (first-run model download). No extra features +# needed for the multilingual-e5-small path. +fastembed = { workspace = true } +tracing = { workspace = true } +anyhow = { workspace = true } + +[dev-dependencies] +tempfile = { workspace = true } +serde_json = { workspace = true } diff --git a/crates/kb-embed-local/src/lib.rs b/crates/kb-embed-local/src/lib.rs new file mode 100644 index 0000000..1d3e2d0 --- /dev/null +++ b/crates/kb-embed-local/src/lib.rs @@ -0,0 +1,433 @@ +//! `kb-embed-local` — `FastembedEmbedder`, a local ONNX-backed +//! [`Embedder`](kb_embed::Embedder) implementation. +//! +//! Wraps [`fastembed::TextEmbedding`] for the default `multilingual-e5-small` +//! (384-dim) model. Honors `config.models.embedding.batch_size` and applies +//! the e5 prefix convention (§11.3 of the design report): +//! +//! * `EmbeddingKind::Document` → `"passage: "` prefix +//! * `EmbeddingKind::Query` → `"query: "` prefix +//! +//! The underlying fastembed `TextEmbedding::embed` already L2-normalizes each +//! row (see `fastembed::text_embedding::output::transformer_with_precedence`), +//! so we do not re-normalize; the unit-norm test in `tests/` keeps that +//! invariant pinned in case fastembed changes its default. +//! +//! Model files are cached under +//! `config.storage.model_dir/fastembed/`. The `model_dir` template +//! (default `"{data_dir}/models"`) is resolved with the same expansion +//! rules `kb-store-sqlite` applies to `data_dir` (`${XDG_DATA_HOME:-…}`, +//! leading `~`, `{data_dir}` substitution). +//! +//! See `docs/superpowers/specs/2026-04-27-kb-final-form-design.md` +//! §7.2 (Embedder), §6.4 ([models.embedding]), §9 (versioning). + +use std::path::PathBuf; +use std::sync::Mutex; + +use anyhow::{Context, Result}; +use fastembed::{EmbeddingModel, InitOptions, TextEmbedding}; +use kb_embed::{Embedder, EmbeddingInput, EmbeddingKind, EmbeddingModelId, EmbeddingVersion}; + +/// Subdirectory under `config.storage.model_dir` where the fastembed +/// adapter writes / reads ONNX + tokenizer files. Hard-coded per task +/// spec ("Model files cached under `config.storage.model_dir/fastembed/`"). +const FASTEMBED_CACHE_SUBDIR: &str = "fastembed"; + +/// Local fastembed-rs adapter. +/// +/// Construct via [`FastembedEmbedder::new`]. The constructor performs the +/// (potentially network-bound) model download on first use, so prefer to +/// share an instance across calls. +pub struct FastembedEmbedder { + // Mutex serializes calls into TextEmbedding's underlying ONNX session. + // fastembed::TextEmbedding::embed is `&self` in 4.9 and ORT Session is + // Send + Sync, so this Mutex is conservative — it serializes inference + // where parallel ORT calls would in principle work. Acceptable here + // because callers (kb-app indexer) batch sequentially anyway. Revisit + // in P3-3+ if profiling shows contention. + inner: Mutex, + model_id: EmbeddingModelId, + version: EmbeddingVersion, + dimensions: usize, + batch_size: usize, +} + +impl FastembedEmbedder { + /// Build an embedder from `Config`. Validates that + /// `config.models.embedding.dimensions` matches the model's actual + /// dim BEFORE returning, so a mismatch fails at construction (not on + /// first `embed`). + pub fn new(config: &kb_config::Config) -> Result { + // 1. Resolve `{data_dir}/models/fastembed/` from the config + // templates. `kb-config` does not expose a public path + // resolver yet, so we hand-roll a tiny one mirroring + // kb-store-sqlite's `expand_data_dir`. + let data_dir = expand_path(&config.storage.data_dir, ""); + let model_dir = expand_path(&config.storage.model_dir, &data_dir.to_string_lossy()); + let cache_dir = model_dir.join(FASTEMBED_CACHE_SUBDIR); + std::fs::create_dir_all(&cache_dir) + .with_context(|| format!("create fastembed cache dir {}", cache_dir.display()))?; + + // 2. Resolve the fastembed enum variant from + // `config.models.embedding.model`. Currently only the default + // `multilingual-e5-small` is wired; other model names error + // out with a clear message rather than silently misconfiguring. + let model_name = resolve_model(&config.models.embedding.model)?; + + // 3. Verify dim match BEFORE loading the model — if the config + // is wrong we want to fail without paying the ONNX + // initialization cost. + let model_info = TextEmbedding::get_model_info(&model_name) + .context("fastembed: get_model_info")?; + check_dim(model_info.dim, config.models.embedding.dimensions)?; + + tracing::info!( + target: "kb-embed-local", + cache_dir = %cache_dir.display(), + model = %config.models.embedding.model, + dims = model_info.dim, + "initializing FastembedEmbedder" + ); + + // 4. Build the underlying TextEmbedding. `show_download_progress` + // is forced to `false` so test output stays clean; first-run + // download progress is surfaced via the `tracing::info!` + // pair around `TextEmbedding::try_new` instead. + let opts = InitOptions::new(model_name.clone()) + .with_cache_dir(cache_dir.clone()) + .with_show_download_progress(false); + tracing::info!( + target: "kb-embed-local", + model = %config.models.embedding.model, + cache_dir = %cache_dir.display(), + "loading embedding model (first run will download ~470MB)" + ); + let inner = TextEmbedding::try_new(opts) + .context("fastembed: TextEmbedding::try_new")?; + let dimensions = model_info.dim; + tracing::info!( + target: "kb-embed-local", + model = %config.models.embedding.model, + dimensions, + "embedding model loaded" + ); + + Ok(Self { + inner: Mutex::new(inner), + model_id: EmbeddingModelId(config.models.embedding.model.clone()), + version: EmbeddingVersion(config.models.embedding.version.clone()), + dimensions, + batch_size: config.models.embedding.batch_size, + }) + } +} + +impl Embedder for FastembedEmbedder { + fn model_id(&self) -> EmbeddingModelId { + self.model_id.clone() + } + + fn model_version(&self) -> EmbeddingVersion { + self.version.clone() + } + + fn dimensions(&self) -> usize { + self.dimensions + } + + fn embed(&self, inputs: &[EmbeddingInput<'_>]) -> Result>> { + if inputs.is_empty() { + return Ok(Vec::new()); + } + + // Apply e5 prefix per §11.3 BEFORE tokenization. The fastembed + // model is unaware of the document/query distinction; the prefix + // is the only signal that lets it produce different embeddings + // for the same surface text in different roles. + let prefixed: Vec = inputs.iter().map(prefix_input).collect(); + + // We run our own batch loop on top of fastembed's internal one + // so that `config.models.embedding.batch_size` is honored + // exactly. fastembed's `embed(_, Some(batch_size))` does the + // same internally; calling once with our batch size matches + // intent and avoids an extra per-batch allocation. + let mut out: Vec> = Vec::with_capacity(prefixed.len()); + for chunk in prefixed.chunks(self.batch_size) { + let chunk_vec: Vec<&str> = chunk.iter().map(String::as_str).collect(); + let guard = self + .inner + .lock() + .unwrap_or_else(|p| p.into_inner()); + let batch: Vec> = guard + .embed(chunk_vec, Some(self.batch_size)) + .context("fastembed: embed")?; + drop(guard); + // Defensive shape check — every returned vector must match + // the configured `dimensions`. Mismatch here means fastembed + // and our config drifted at runtime (extremely unlikely; + // would have been caught at construction). + for v in &batch { + if v.len() != self.dimensions { + anyhow::bail!( + "fastembed returned vector of length {} but adapter expects {}", + v.len(), + self.dimensions + ); + } + } + out.extend(batch); + } + + debug_assert_eq!(out.len(), inputs.len()); + Ok(out) + } +} + +/// Build the prefixed string for one [`EmbeddingInput`]. Free function so +/// the unit test can pin the exact format without going through `embed`. +fn prefix_input(input: &EmbeddingInput<'_>) -> String { + match input.kind { + EmbeddingKind::Document => format!("passage: {}", input.text), + EmbeddingKind::Query => format!("query: {}", input.text), + } +} + +/// Resolve a `config.models.embedding.model` string to a fastembed +/// `EmbeddingModel` enum variant. Only `multilingual-e5-small` is wired +/// for p3-2; additional model names should be added (and their dims +/// pinned in tests) as needed. +fn resolve_model(name: &str) -> Result { + match name { + "multilingual-e5-small" => Ok(EmbeddingModel::MultilingualE5Small), + other => anyhow::bail!( + "kb-embed-local: unsupported embedding model {other:?}; \ + this adapter currently only ships `multilingual-e5-small`. \ + Add a new arm to `resolve_model` (and a fastembed feature \ + flag if needed) to support more." + ), + } +} + +/// Compare model dim against the configured dim. Extracted so a unit +/// test can exercise the error branch without loading ONNX. +pub(crate) fn check_dim(model_dim: usize, cfg_dim: usize) -> Result<()> { + if model_dim != cfg_dim { + anyhow::bail!( + "dimension mismatch: model={model_dim}, config={cfg_dim}; \ + update `config.models.embedding.dimensions` to match the model \ + (or pick a different model)." + ); + } + Ok(()) +} + +/// Expand the limited template language `kb-config` uses for storage +/// paths. +/// +/// Supported substitutions, applied in order: +/// 1. `{data_dir}` → `data_dir` (caller-supplied resolved string). This +/// is a no-op when `data_dir` is empty (used by the recursive call +/// that resolves `data_dir` itself). +/// 2. `${XDG_DATA_HOME:-~/.local/share}` (and the bare +/// `${XDG_DATA_HOME}`) → env var if set, else the default after +/// `:-`. +/// 3. Leading `~` → `$HOME`. +/// +/// Mirrors `kb-store-sqlite::store::expand_data_dir`. Kept private to +/// this crate; promoting it to a public `kb-config` API is a separate +/// task (see task p3-2 risks: "don't expand kb-config's public API"). +fn expand_path(raw: &str, data_dir: &str) -> PathBuf { + let mut s = raw.to_string(); + + if !data_dir.is_empty() { + s = s.replace("{data_dir}", data_dir); + } + + // ${XDG_DATA_HOME:-~/.local/share}: respect env override, else fall + // back to the suffix after `:-`. + if let Some(start) = s.find("${XDG_DATA_HOME") { + if let Some(rel_end) = s[start..].find('}') { + let end = start + rel_end + 1; // include trailing '}' + let inner = &s[start + 2..end - 1]; // strip ${ and } + let replacement = match std::env::var("XDG_DATA_HOME") { + Ok(v) if !v.is_empty() => v, + _ => { + if let Some((_, default)) = inner.split_once(":-") { + default.to_string() + } else { + String::new() + } + } + }; + s.replace_range(start..end, &replacement); + } + } + + // Leading `~` → $HOME. + if let Some(rest) = s.strip_prefix('~') { + if let Some(home) = std::env::var_os("HOME").map(PathBuf::from) { + return home.join(rest.trim_start_matches('/')); + } + } + + PathBuf::from(s) +} + +#[cfg(test)] +mod tests { + use super::*; + use kb_embed::EmbeddingInput; + + // ── check_dim ──────────────────────────────────────────────────── + // + // Exercises the construction-time dim mismatch branch WITHOUT + // loading the real model. The integration test that builds a full + // FastembedEmbedder is `#[ignore]`d (loads ~470 MB of weights). + + #[test] + fn check_dim_match_ok() { + check_dim(384, 384).expect("matching dims must pass"); + } + + #[test] + fn check_dim_mismatch_errors() { + let err = check_dim(384, 512).expect_err("mismatch must error"); + let msg = format!("{err}"); + assert!(msg.contains("dimension mismatch"), "msg={msg}"); + assert!(msg.contains("384"), "msg={msg}"); + assert!(msg.contains("512"), "msg={msg}"); + } + + // ── prefix_input ───────────────────────────────────────────────── + // + // Pin the exact e5 prefix strings; a silent regression here + // degrades retrieval quality without any test failing in the + // dim/norm/snapshot suite. + + #[test] + fn prefix_document_uses_passage() { + let input = EmbeddingInput { + text: "hello world", + kind: EmbeddingKind::Document, + }; + assert_eq!(prefix_input(&input), "passage: hello world"); + } + + #[test] + fn prefix_query_uses_query() { + let input = EmbeddingInput { + text: "hello world", + kind: EmbeddingKind::Query, + }; + assert_eq!(prefix_input(&input), "query: hello world"); + } + + #[test] + fn prefix_handles_empty_text() { + let doc = EmbeddingInput { + text: "", + kind: EmbeddingKind::Document, + }; + let qry = EmbeddingInput { + text: "", + kind: EmbeddingKind::Query, + }; + assert_eq!(prefix_input(&doc), "passage: "); + assert_eq!(prefix_input(&qry), "query: "); + } + + // ── resolve_model ──────────────────────────────────────────────── + + #[test] + fn resolve_default_model_ok() { + // The exact enum variant is opaque, but `is_ok` plus a + // round-trip through the fastembed metadata gives confidence + // we hit the right arm. + resolve_model("multilingual-e5-small").expect("default model resolves"); + } + + #[test] + fn resolve_unknown_model_errors() { + let err = resolve_model("not-a-real-model").expect_err("unknown model errors"); + let msg = format!("{err}"); + assert!(msg.contains("unsupported embedding model"), "msg={msg}"); + } + + // ── expand_path ────────────────────────────────────────────────── + + #[test] + fn expand_path_substitutes_data_dir_template() { + let p = expand_path("{data_dir}/models", "/tmp/kbtest"); + assert_eq!(p, PathBuf::from("/tmp/kbtest/models")); + } + + #[test] + fn expand_path_no_op_without_template() { + let p = expand_path("/abs/path", "/tmp/kbtest"); + assert_eq!(p, PathBuf::from("/abs/path")); + } + + // ── expand_path: XDG_DATA_HOME fallback ────────────────────────── + // + // These two tests mutate the process-wide `XDG_DATA_HOME` env var, + // which is unsafe under edition 2024 and racy under cargo's default + // parallel test runner. The shared `ENV_LOCK` serializes them; each + // test snapshots the prior value and restores it on exit. + + use std::sync::Mutex as StdMutex; + static ENV_LOCK: StdMutex<()> = StdMutex::new(()); + + /// RAII guard: snapshots `XDG_DATA_HOME` on construction, restores + /// it on drop. Pair with the `ENV_LOCK` guard for serial access. + struct XdgGuard { + prior: Option, + } + + impl XdgGuard { + fn capture() -> Self { + Self { + prior: std::env::var("XDG_DATA_HOME").ok(), + } + } + } + + impl Drop for XdgGuard { + fn drop(&mut self) { + // SAFETY: edition 2024 marks `set_var`/`remove_var` unsafe + // because env mutation is not thread-safe. Callers hold + // `ENV_LOCK` for the duration of the test, so no other + // thread observes the mutation. + unsafe { + match &self.prior { + Some(v) => std::env::set_var("XDG_DATA_HOME", v), + None => std::env::remove_var("XDG_DATA_HOME"), + } + } + } + } + + #[test] + fn expand_path_xdg_data_home_set() { + let _lock = ENV_LOCK.lock().unwrap_or_else(|p| p.into_inner()); + let _guard = XdgGuard::capture(); + // SAFETY: lock held for the duration of this test. + unsafe { std::env::set_var("XDG_DATA_HOME", "/custom/path") }; + + let p = expand_path("${XDG_DATA_HOME:-~/.local/share}/kb", ""); + assert_eq!(p, PathBuf::from("/custom/path/kb")); + } + + #[test] + fn expand_path_xdg_data_home_unset_falls_back_to_home() { + let _lock = ENV_LOCK.lock().unwrap_or_else(|p| p.into_inner()); + let _guard = XdgGuard::capture(); + // SAFETY: lock held for the duration of this test. + unsafe { std::env::remove_var("XDG_DATA_HOME") }; + + let home = std::env::var("HOME").expect("HOME must be set in tests"); + let expected = PathBuf::from(home).join(".local/share/kb"); + let p = expand_path("${XDG_DATA_HOME:-~/.local/share}/kb", ""); + assert_eq!(p, expected); + } +} diff --git a/crates/kb-embed-local/tests/embed_model.rs b/crates/kb-embed-local/tests/embed_model.rs new file mode 100644 index 0000000..b2af074 --- /dev/null +++ b/crates/kb-embed-local/tests/embed_model.rs @@ -0,0 +1,284 @@ +//! Integration tests for [`FastembedEmbedder`] that load the real ONNX +//! model. +//! +//! ## Why every test in this file is `#[ignore]` +//! +//! The first call to `FastembedEmbedder::new` downloads ~470 MB of +//! weights from Hugging Face into `data_dir/models/fastembed/`. Doing +//! that on every `cargo test` invocation is wasteful, so the bare +//! invocation skips this file entirely. +//! +//! Run the full suite with: +//! ```text +//! cargo test -p kb-embed-local -- --ignored +//! ``` +//! +//! All tests share a `OnceLock` so the model loads +//! exactly once per process invocation (ONNX runtime first-load latency +//! is 1-2 s on M-series Macs per design risks list). + +use std::collections::hash_map::DefaultHasher; +use std::hash::{Hash, Hasher}; +use std::sync::OnceLock; +use std::time::Instant; + +use kb_embed::{Embedder, EmbeddingInput, EmbeddingKind}; +use kb_embed_local::FastembedEmbedder; + +/// Build a `Config` whose `data_dir` lives in a per-process temp dir so +/// the test never writes into the developer's real `~/.local/share/kb`. +/// Returns the `Config` and the `TempDir` guard (caller keeps the guard +/// alive for the test duration). +fn test_config() -> (kb_config::Config, tempfile::TempDir) { + let tmp = tempfile::tempdir().expect("create tempdir"); + let mut cfg = kb_config::Config::defaults(); + cfg.storage.data_dir = tmp.path().to_string_lossy().into_owned(); + // model_dir keeps its default `{data_dir}/models` template; the + // adapter resolves it itself. + (cfg, tmp) +} + +/// Single shared embedder for the `--ignored` lane. Held behind a +/// `OnceLock` so we pay the ~1-2 s ONNX init + (first run only) the +/// network download just once. +fn shared_embedder() -> &'static FastembedEmbedder { + static EMBEDDER: OnceLock = OnceLock::new(); + EMBEDDER.get_or_init(|| { + let (cfg, _tmp) = test_config(); + // We deliberately leak `_tmp` here: the OnceLock outlives the + // function scope so the cache directory must persist for the + // process. (`tempfile::TempDir`'s `Drop` would erase the cache + // and wreck subsequent calls.) The OS will reclaim the leaked + // path when the test process exits. + let _ = std::mem::ManuallyDrop::new(_tmp); + FastembedEmbedder::new(&cfg).expect("init FastembedEmbedder") + }) +} + +// ─── construction ───────────────────────────────────────────────────── + +#[test] +#[ignore = "downloads ~470MB ONNX model on first run; CI-only"] +fn default_config_constructs_with_dims_384() { + let emb = shared_embedder(); + assert_eq!(emb.dimensions(), 384); + assert_eq!(emb.model_id().0, "multilingual-e5-small"); + assert_eq!(emb.model_version().0, "v1"); +} + +#[test] +#[ignore = "downloads ~470MB ONNX model on first run; CI-only"] +fn mismatched_dims_in_config_errors_at_construction() { + let (mut cfg, _tmp) = test_config(); + cfg.models.embedding.dimensions = 512; // model is 384 + // `FastembedEmbedder` deliberately does not implement `Debug` + // (its inner ONNX session has no useful debug shape), so we + // can't use `expect_err`; match the Result manually. + let err = match FastembedEmbedder::new(&cfg) { + Ok(_) => panic!("dim mismatch must error"), + Err(e) => e, + }; + let msg = format!("{err}"); + assert!(msg.contains("dimension mismatch"), "msg={msg}"); + assert!(msg.contains("384"), "msg={msg}"); + assert!(msg.contains("512"), "msg={msg}"); +} + +// ─── e5 prefix differentiation ──────────────────────────────────────── + +#[test] +#[ignore = "loads ONNX model; CI-only"] +fn document_and_query_yield_different_vectors() { + let emb = shared_embedder(); + let text = "The quick brown fox jumps over the lazy dog."; + let out = emb + .embed(&[ + EmbeddingInput { + text, + kind: EmbeddingKind::Document, + }, + EmbeddingInput { + text, + kind: EmbeddingKind::Query, + }, + ]) + .expect("embed two inputs"); + assert_eq!(out.len(), 2); + assert_eq!(out[0].len(), 384); + assert_eq!(out[1].len(), 384); + + // Both vectors are L2-normalized → cosine similarity == dot product. + let cos: f32 = out[0] + .iter() + .zip(out[1].iter()) + .map(|(a, b)| a * b) + .sum(); + // Same text, different prefix → vectors must NOT be identical. + assert!( + cos < 0.9999, + "expected distinct vectors for Document vs Query, got cos={cos}" + ); +} + +// ─── L2 normalization ───────────────────────────────────────────────── + +#[test] +#[ignore = "loads ONNX model; CI-only"] +fn output_vectors_are_l2_normalized() { + let emb = shared_embedder(); + let inputs = [ + EmbeddingInput { + text: "hello world", + kind: EmbeddingKind::Document, + }, + EmbeddingInput { + text: "vector search", + kind: EmbeddingKind::Document, + }, + EmbeddingInput { + text: "embedding model", + kind: EmbeddingKind::Query, + }, + ]; + let out = emb.embed(&inputs).expect("embed"); + // Per `kb_embed::assert_unit_norm` docs: `5e-4` is the safe bound at + // 384 dims (f32::EPSILON × √384 ≈ 2.3e-6, but ONNX kernels add + // their own per-component noise; 1e-3 is very generous and matches + // the spec's `± 1e-3`). + kb_embed::assert_unit_norm(&out, 1e-3); + kb_embed::assert_vector_shape(&out, 384); +} + +// ─── determinism ────────────────────────────────────────────────────── + +#[test] +#[ignore = "loads ONNX model; CI-only"] +fn identical_input_yields_identical_output() { + let emb = shared_embedder(); + let inputs = [ + EmbeddingInput { + text: "deterministic embedding test", + kind: EmbeddingKind::Document, + }, + EmbeddingInput { + text: "second sentence for variety", + kind: EmbeddingKind::Document, + }, + ]; + let a = emb.embed(&inputs).expect("first embed"); + let b = emb.embed(&inputs).expect("second embed"); + assert_eq!(a, b, "two calls with the same inputs must be byte-equal"); +} + +// ─── performance ────────────────────────────────────────────────────── + +#[test] +#[ignore = "performance test; downloads model and runs 64-vec batch"] +fn batch_of_64_short_inputs_under_5s() { + let emb = shared_embedder(); + // 64 distinct short strings → forces the full default batch_size + // through one fastembed call. + let texts: Vec = (0..64) + .map(|i| format!("perf-test sentence number {i}")) + .collect(); + let inputs: Vec> = texts + .iter() + .map(|t| EmbeddingInput { + text: t.as_str(), + kind: EmbeddingKind::Document, + }) + .collect(); + let t0 = Instant::now(); + let out = emb.embed(&inputs).expect("embed batch of 64"); + let elapsed = t0.elapsed(); + assert_eq!(out.len(), 64); + assert!( + elapsed.as_secs_f32() < 5.0, + "batch-64 took {elapsed:?}, expected < 5s" + ); +} + +// ─── snapshot ───────────────────────────────────────────────────────── + +/// Aggregate hash of vectors for the 5 fixture sentences. +/// +/// Computed by: +/// 1. embed each sentence as `EmbeddingKind::Document`, +/// 2. round each `f32` component to 4 decimal places (multiply by 1e4, +/// round, store as `i32`), +/// 3. write the rounded i32 components into a `DefaultHasher` in row- +/// major order, +/// 4. read out the `u64` finish value. +/// +/// The 4-decimal tolerance is intentional float-tolerance per task spec: +/// exact f32 equality is too strict given ONNX kernel + hardware +/// variation. +/// +/// **Pinning workflow** (a snapshot test must FAIL UNTIL PINNED): +/// 1. With `SNAPSHOT_HASH_BASELINE = 0`, run +/// `cargo test -p kb-embed-local -- --ignored snapshot`. The test +/// panics with a message containing the captured hash. +/// 2. Paste the printed hex value into `SNAPSHOT_HASH_BASELINE` below. +/// 3. Re-run the same command — the test now asserts equality and +/// passes, confirming the pin. +/// +/// On a genuine model upgrade, reset to `0`, re-pin, and bump +/// `EmbeddingVersion` per design §9 in the same PR. +const SNAPSHOT_HASH_BASELINE: u64 = 0; + +#[test] +#[ignore = "loads ONNX model; CI-only"] +fn snapshot_aggregate_hash_is_stable() { + let emb = shared_embedder(); + let fixture_path = + std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/fixtures/embed/known-sentences.json"); + let raw = std::fs::read_to_string(&fixture_path).expect("read fixture"); + let json: serde_json::Value = serde_json::from_str(&raw).expect("parse fixture json"); + let sentences: Vec = json["sentences"] + .as_array() + .expect("`sentences` array") + .iter() + .map(|v| v.as_str().expect("sentence is str").to_string()) + .collect(); + assert_eq!(sentences.len(), 5, "fixture must have exactly 5 sentences"); + + let inputs: Vec> = sentences + .iter() + .map(|s| EmbeddingInput { + text: s.as_str(), + kind: EmbeddingKind::Document, + }) + .collect(); + let out = emb.embed(&inputs).expect("embed snapshot fixture"); + + // Round every component to 4 decimal places, hash deterministically. + let mut hasher = DefaultHasher::new(); + for (i, v) in out.iter().enumerate() { + assert_eq!(v.len(), 384, "row {i} dim mismatch"); + for x in v { + let rounded: i32 = (*x * 1.0e4).round() as i32; + rounded.hash(&mut hasher); + } + } + let observed = hasher.finish(); + if SNAPSHOT_HASH_BASELINE == 0 { + // Unpinned baseline: panic with the captured hash. A snapshot + // test that silently passes on first run defeats its purpose, + // so we hard-fail until a maintainer commits the pin. Both + // hex (paste-friendly) and decimal forms are printed. + eprintln!( + "kb-embed-local snapshot baseline (paste into SNAPSHOT_HASH_BASELINE): \ + {observed:#x} ({observed})" + ); + panic!( + "snapshot baseline unpinned — paste {observed:#x} into \ + SNAPSHOT_HASH_BASELINE then re-run" + ); + } + assert_eq!( + observed, SNAPSHOT_HASH_BASELINE, + "snapshot drift: model output for the fixture sentences changed; \ + either fastembed weights changed (bump EmbeddingVersion per §9) \ + or there's an ONNX kernel diff." + ); +} diff --git a/crates/kb-embed-local/tests/fixtures/embed/known-sentences.json b/crates/kb-embed-local/tests/fixtures/embed/known-sentences.json new file mode 100644 index 0000000..9994109 --- /dev/null +++ b/crates/kb-embed-local/tests/fixtures/embed/known-sentences.json @@ -0,0 +1,10 @@ +{ + "_comment": "Snapshot fixture for FastembedEmbedder. Five short sentences in mixed languages chosen so the multilingual-e5-small model exercises both Latin and CJK token paths. The kb-embed-local snapshot test embeds these as `EmbeddingKind::Document`, rounds each f32 component to 4 decimal places, and checks an aggregate hash against a constant baked into the test source. The 4-decimal tolerance hides the per-platform ONNX kernel jitter we observed during P3 bring-up; tighter tolerances would make the test flaky across hardware.", + "sentences": [ + "The quick brown fox jumps over the lazy dog.", + "Vector search is fast on small models.", + "Knowledge bases benefit from hybrid retrieval.", + "한국어 문장도 임베딩이 잘 됩니다.", + "Embeddings should be deterministic given the same input." + ] +}