From fbf636868c549aa687b5090fc157584316e277c8 Mon Sep 17 00:00:00 2001 From: Fam Zheng Date: Sun, 1 Mar 2026 08:31:31 +0000 Subject: [PATCH] Switch from fastembed to Python sentence-transformers for embedding ort (ONNX Runtime) has no prebuilt binaries for aarch64-musl. Use a Python subprocess with sentence-transformers instead: - scripts/embed.py: reads JSON stdin, outputs embeddings - kb.rs: calls Python script via tokio subprocess - Dockerfile: install python3 + sentence-transformers Co-Authored-By: Claude Opus 4.6 --- Cargo.lock | 761 +---------------------------------------------- Cargo.toml | 1 - Dockerfile | 4 +- scripts/embed.py | 26 ++ src/kb.rs | 60 +++- 5 files changed, 86 insertions(+), 766 deletions(-) create mode 100644 scripts/embed.py diff --git a/Cargo.lock b/Cargo.lock index af35f4f..778f640 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2,26 +2,6 @@ # 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" -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", -] - [[package]] name = "aho-corasick" version = "1.1.4" @@ -80,7 +60,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8b52af3cb4058c895d37317bb27508dccc8e5f2d39454016b297bf4a400597b8" dependencies = [ "axum-core", - "base64 0.22.1", + "base64", "bytes", "form_urlencoded", "futures-util", @@ -128,12 +108,6 @@ dependencies = [ "tracing", ] -[[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" @@ -182,15 +156,6 @@ 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 = "1.2.56" @@ -227,21 +192,6 @@ dependencies = [ "windows-link", ] -[[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 = "concurrent-queue" version = "2.5.0" @@ -251,19 +201,6 @@ dependencies = [ "crossbeam-utils", ] -[[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 = "const-oid" version = "0.9.6" @@ -300,34 +237,6 @@ version = "2.4.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "19d374276b40fb8bbdee95aef7c7fa6b5316ec764510eb64b8dd0e2ed0d7e7f5" -[[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-deque" -version = "0.8.6" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51" -dependencies = [ - "crossbeam-epoch", - "crossbeam-utils", -] - -[[package]] -name = "crossbeam-epoch" -version = "0.9.18" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e" -dependencies = [ - "crossbeam-utils", -] - [[package]] name = "crossbeam-queue" version = "0.3.12" @@ -353,50 +262,6 @@ dependencies = [ "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 = "0.3.8" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "06d2e3287df1c007e74221c49ca10a95d557349e54b3a75dc2fb14712c751f04" -dependencies = [ - "serde", -] - [[package]] name = "data-encoding" version = "2.10.0" @@ -414,37 +279,6 @@ dependencies = [ "zeroize", ] -[[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" @@ -457,27 +291,6 @@ dependencies = [ "subtle", ] -[[package]] -name = "dirs" -version = "6.0.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c3e8aa94d75141228480295a7d0e7feb620b1a5ad9f12bc40be62411e38cce4e" -dependencies = [ - "dirs-sys", -] - -[[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", - "windows-sys 0.61.2", -] - [[package]] name = "displaydoc" version = "0.2.5" @@ -504,12 +317,6 @@ dependencies = [ "serde", ] -[[package]] -name = "encode_unicode" -version = "1.0.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0" - [[package]] name = "equivalent" version = "1.0.2" @@ -526,12 +333,6 @@ 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 = "etcetera" version = "0.8.0" @@ -554,38 +355,12 @@ dependencies = [ "pin-project-lite", ] -[[package]] -name = "fastembed" -version = "5.11.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b4339d45a80579ab8305616a501eacdbf18fb0f7def7fa6e4c0b75941416d5b0" -dependencies = [ - "anyhow", - "hf-hub", - "ndarray", - "ort", - "safetensors", - "serde", - "serde_json", - "tokenizers", -] - [[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 = "flume" version = "0.11.1" @@ -597,24 +372,12 @@ dependencies = [ "spin", ] -[[package]] -name = "fnv" -version = "1.0.7" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" - [[package]] name = "foldhash" version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2" -[[package]] -name = "foldhash" -version = "0.2.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb" - [[package]] name = "form_urlencoded" version = "1.2.2" @@ -781,7 +544,7 @@ checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1" dependencies = [ "allocator-api2", "equivalent", - "foldhash 0.1.5", + "foldhash", ] [[package]] @@ -789,13 +552,6 @@ name = "hashbrown" version = "0.16.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100" -dependencies = [ - "allocator-api2", - "equivalent", - "foldhash 0.2.0", - "serde", - "serde_core", -] [[package]] name = "hashlink" @@ -818,26 +574,6 @@ version = "0.4.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70" -[[package]] -name = "hf-hub" -version = "0.4.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97" -dependencies = [ - "dirs", - "http", - "indicatif", - "libc", - "log", - "rand 0.9.2", - "reqwest", - "serde", - "serde_json", - "thiserror", - "ureq 2.12.1", - "windows-sys 0.60.2", -] - [[package]] name = "hkdf" version = "0.12.4" @@ -856,12 +592,6 @@ dependencies = [ "digest", ] -[[package]] -name = "hmac-sha256" -version = "1.1.14" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ec9d92d097f4749b64e8cc33d924d9f40a2d4eb91402b458014b781f5733d60f" - [[package]] name = "home" version = "0.5.12" @@ -958,7 +688,7 @@ dependencies = [ "tokio", "tokio-rustls", "tower-service", - "webpki-roots 1.0.4", + "webpki-roots", ] [[package]] @@ -967,7 +697,7 @@ version = "0.1.20" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0" dependencies = [ - "base64 0.22.1", + "base64", "bytes", "futures-channel", "futures-util", @@ -1095,12 +825,6 @@ 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" @@ -1134,19 +858,6 @@ 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 = "ipnet" version = "2.11.0" @@ -1163,15 +874,6 @@ dependencies = [ "serde", ] -[[package]] -name = "itertools" -version = "0.14.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285" -dependencies = [ - "either", -] - [[package]] name = "itoa" version = "1.0.17" @@ -1264,28 +966,6 @@ version = "0.1.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154" -[[package]] -name = "lzma-rust2" -version = "0.15.7" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1670343e58806300d87950e3401e820b519b9384281bbabfb15e3636689ffd69" - -[[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 = "matchers" version = "0.2.0" @@ -1301,16 +981,6 @@ version = "0.8.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "47e1ffaa40ddd1f3ed91f717a33c8c0ee23fff369e3aa8772b9605cc1d22f4c3" -[[package]] -name = "matrixmultiply" -version = "0.3.10" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08" -dependencies = [ - "autocfg", - "rawpointer", -] - [[package]] name = "md-5" version = "0.10.6" @@ -1343,22 +1013,6 @@ dependencies = [ "unicase", ] -[[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 = "1.1.1" @@ -1370,43 +1024,6 @@ dependencies = [ "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 = "ndarray" -version = "0.17.2" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "520080814a7a6b4a6e9070823bb24b4531daac8c4627e08ba5de8c5ef2f2752d" -dependencies = [ - "matrixmultiply", - "num-complex", - "num-integer", - "num-traits", - "portable-atomic", - "portable-atomic-util", - "rawpointer", -] - [[package]] name = "nix" version = "0.29.0" @@ -1419,16 +1036,6 @@ dependencies = [ "libc", ] -[[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 = "nu-ansi-term" version = "0.50.3" @@ -1454,15 +1061,6 @@ dependencies = [ "zeroize", ] -[[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-integer" version = "0.1.46" @@ -1493,70 +1091,12 @@ dependencies = [ "libm", ] -[[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 = "1.21.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d" -[[package]] -name = "onig" -version = "6.5.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "336b9c63443aceef14bea841b899035ae3abe89b7c486aaf4c5bd8aafedac3f0" -dependencies = [ - "bitflags", - "libc", - "once_cell", - "onig_sys", -] - -[[package]] -name = "onig_sys" -version = "69.9.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c7f86c6eef3d6df15f23bcfb6af487cbd2fed4e5581d58d5bf1f5f8b7f6727dc" -dependencies = [ - "cc", - "pkg-config", -] - -[[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.11" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4a5df903c0d2c07b56950f1058104ab0c8557159f2741782223704de9be73c3c" -dependencies = [ - "ndarray", - "ort-sys", - "smallvec", - "tracing", - "ureq 3.2.0", -] - -[[package]] -name = "ort-sys" -version = "2.0.0-rc.11" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "06503bb33f294c5f1ba484011e053bfa6ae227074bdb841e9863492dc5960d4b" -dependencies = [ - "hmac-sha256", - "lzma-rust2", - "ureq 3.2.0", -] - [[package]] name = "parking" version = "2.2.1" @@ -1586,12 +1126,6 @@ dependencies = [ "windows-link", ] -[[package]] -name = "paste" -version = "1.0.15" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" - [[package]] name = "pem-rfc7468" version = "0.7.0" @@ -1646,21 +1180,6 @@ version = "0.3.32" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c" -[[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 = "0.2.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7a9db96d7fa8782dd8c15ce32ffe8680bbd1e978a43bf51a34d39483540495f5" -dependencies = [ - "portable-atomic", -] - [[package]] name = "potential_utf" version = "0.1.4" @@ -1827,43 +1346,6 @@ dependencies = [ "getrandom 0.3.4", ] -[[package]] -name = "rawpointer" -version = "0.2.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3" - -[[package]] -name = "rayon" -version = "1.11.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "368f01d005bf8fd9b1206fb6fa653e6c4a81ceb1466406b81792d87c5677a58f" -dependencies = [ - "either", - "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" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "22e18b0f0062d30d4230b2e85ff77fdfe4326feb054b9783a3460d8435c8ab91" -dependencies = [ - "crossbeam-deque", - "crossbeam-utils", -] - [[package]] name = "redox_syscall" version = "0.5.18" @@ -1882,29 +1364,6 @@ dependencies = [ "bitflags", ] -[[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", -] - -[[package]] -name = "regex" -version = "1.12.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276" -dependencies = [ - "aho-corasick", - "memchr", - "regex-automata", - "regex-syntax", -] - [[package]] name = "regex-automata" version = "0.4.14" @@ -1928,7 +1387,7 @@ version = "0.12.28" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147" dependencies = [ - "base64 0.22.1", + "base64", "bytes", "futures-core", "futures-util", @@ -1960,7 +1419,7 @@ dependencies = [ "wasm-bindgen-futures", "wasm-streams", "web-sys", - "webpki-roots 1.0.4", + "webpki-roots", ] [[package]] @@ -2009,7 +1468,6 @@ version = "0.23.37" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "758025cb5fccfd3bc2fd74708fd4682be41d99e5dff73c377c0646c6012c73a4" dependencies = [ - "log", "once_cell", "ring", "rustls-pki-types", @@ -2051,17 +1509,6 @@ version = "1.0.23" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f" -[[package]] -name = "safetensors" -version = "0.7.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "675656c1eabb620b921efea4f9199f97fc86e36dd6ffd1fbbe48d0f59a4987f5" -dependencies = [ - "hashbrown 0.16.1", - "serde", - "serde_json", -] - [[package]] name = "scopeguard" version = "1.2.0" @@ -2210,12 +1657,6 @@ dependencies = [ "rand_core 0.6.4", ] -[[package]] -name = "simd-adler32" -version = "0.3.8" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e320a6c5ad31d271ad523dcf3ad13e2767ad8b1cb8f047f75a8aeaf8da139da2" - [[package]] name = "slab" version = "0.4.12" @@ -2241,17 +1682,6 @@ dependencies = [ "windows-sys 0.60.2", ] -[[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 = "spin" version = "0.9.8" @@ -2271,18 +1701,6 @@ dependencies = [ "der", ] -[[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", - "serde", - "unicode-segmentation", -] - [[package]] name = "sqlx" version = "0.8.6" @@ -2302,7 +1720,7 @@ version = "0.8.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ee6798b1838b6a0f69c007c133b8df5866302197e404e8b6ee8ed3e3a5e68dc6" dependencies = [ - "base64 0.22.1", + "base64", "bytes", "crc", "crossbeam-queue", @@ -2375,7 +1793,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "aa003f0038df784eb8fecbbac13affe3da23b45194bd57dba231c8f48199c526" dependencies = [ "atoi", - "base64 0.22.1", + "base64", "bitflags", "byteorder", "bytes", @@ -2417,7 +1835,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "db58fcd5a53cf07c184b154801ff91347e4c30d17a3562a635ff028ad5deda46" dependencies = [ "atoi", - "base64 0.22.1", + "base64", "bitflags", "byteorder", "crc", @@ -2477,12 +1895,6 @@ 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 = "stringprep" version = "0.1.5" @@ -2494,12 +1906,6 @@ dependencies = [ "unicode-properties", ] -[[package]] -name = "strsim" -version = "0.11.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" - [[package]] name = "subtle" version = "2.6.1" @@ -2591,39 +1997,6 @@ version = "0.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" -[[package]] -name = "tokenizers" -version = "0.22.2" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b238e22d44a15349529690fb07bd645cf58149a1b1e44d6cb5bd1641ff1a6223" -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 0.9.2", - "rayon", - "rayon-cond", - "regex", - "regex-syntax", - "serde", - "serde_json", - "spm_precompiled", - "thiserror", - "unicode-normalization-alignments", - "unicode-segmentation", - "unicode_categories", -] - [[package]] name = "tokio" version = "1.49.0" @@ -2705,7 +2078,6 @@ dependencies = [ "anyhow", "axum", "chrono", - "fastembed", "futures", "mime_guess", "nix", @@ -2895,45 +2267,18 @@ 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-properties" version = "0.1.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7df058c713841ad818f1dc5d3fd88063241cc61f49f5fbea4b951e8cf5a8d71d" -[[package]] -name = "unicode-segmentation" -version = "1.12.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493" - -[[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" @@ -2946,54 +2291,6 @@ 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", - "once_cell", - "rustls", - "rustls-pki-types", - "serde", - "serde_json", - "socks", - "url", - "webpki-roots 0.26.11", -] - -[[package]] -name = "ureq" -version = "3.2.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "fdc97a28575b85cfedf2a7e7d3cc64b3e11bd8ac766666318003abbacc7a21fc" -dependencies = [ - "base64 0.22.1", - "log", - "percent-encoding", - "rustls", - "rustls-pki-types", - "socks", - "ureq-proto", - "utf-8", - "webpki-roots 1.0.4", -] - -[[package]] -name = "ureq-proto" -version = "0.5.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d81f9efa9df032be5934a46a068815a10a042b494b6a58cb0a1a97bb5467ed6f" -dependencies = [ - "base64 0.22.1", - "http", - "httparse", - "log", -] - [[package]] name = "url" version = "2.5.8" @@ -3212,15 +2509,6 @@ dependencies = [ "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 1.0.4", -] - [[package]] name = "webpki-roots" version = "1.0.4" @@ -3240,28 +2528,6 @@ dependencies = [ "wasite", ] -[[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-x86_64-pc-windows-gnu" -version = "0.4.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" - [[package]] name = "windows-core" version = "0.62.2" @@ -3339,15 +2605,6 @@ 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" diff --git a/Cargo.toml b/Cargo.toml index edbc278..cbff9d1 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -26,4 +26,3 @@ uuid = { version = "1", features = ["v4"] } anyhow = "1" mime_guess = "2" nix = { version = "0.29", features = ["signal"] } -fastembed = { version = "5", default-features = false, features = ["hf-hub", "hf-hub-rustls-tls", "ort-download-binaries-rustls-tls"] } diff --git a/Dockerfile b/Dockerfile index dfdf015..416e49e 100644 --- a/Dockerfile +++ b/Dockerfile @@ -8,13 +8,15 @@ RUN npm run build # Stage 2: Runtime FROM alpine:3.21 -RUN apk add --no-cache ca-certificates curl bash +RUN apk add --no-cache ca-certificates curl bash python3 py3-pip RUN curl -LsSf https://astral.sh/uv/install.sh | sh ENV PATH="/root/.local/bin:$PATH" +RUN pip3 install --break-system-packages sentence-transformers RUN mkdir -p /app/data/workspaces WORKDIR /app COPY target/aarch64-unknown-linux-musl/release/tori . COPY --from=frontend /app/web/dist ./web/dist/ +COPY scripts/embed.py ./scripts/ COPY config.yaml . EXPOSE 3000 diff --git a/scripts/embed.py b/scripts/embed.py new file mode 100644 index 0000000..886251e --- /dev/null +++ b/scripts/embed.py @@ -0,0 +1,26 @@ +#!/usr/bin/env python3 +"""Generate embeddings for text chunks. Reads JSON from stdin, writes JSON to stdout. + +Input: {"texts": ["text1", "text2", ...]} +Output: {"embeddings": [[0.1, 0.2, ...], [0.3, 0.4, ...], ...]} +""" +import json +import sys +from sentence_transformers import SentenceTransformer + +MODEL_NAME = "all-MiniLM-L6-v2" + +def main(): + data = json.loads(sys.stdin.read()) + texts = data["texts"] + + if not texts: + print(json.dumps({"embeddings": []})) + return + + model = SentenceTransformer(MODEL_NAME) + embeddings = model.encode(texts, normalize_embeddings=True) + print(json.dumps({"embeddings": embeddings.tolist()})) + +if __name__ == "__main__": + main() diff --git a/src/kb.rs b/src/kb.rs index 8902e72..73a2fc7 100644 --- a/src/kb.rs +++ b/src/kb.rs @@ -1,11 +1,10 @@ use anyhow::Result; use sqlx::sqlite::SqlitePool; -use std::sync::Mutex; +use std::process::Stdio; const TOP_K: usize = 5; pub struct KbManager { - embedder: Mutex, pool: SqlitePool, } @@ -25,14 +24,10 @@ struct Chunk { impl KbManager { pub fn new(pool: SqlitePool) -> Result { - let embedder = fastembed::TextEmbedding::try_new( - fastembed::InitOptions::new(fastembed::EmbeddingModel::AllMiniLML6V2) - .with_show_download_progress(true), - )?; - Ok(Self { embedder: Mutex::new(embedder), pool }) + Ok(Self { pool }) } - /// Re-index: chunk the content, embed, store in SQLite + /// Re-index: chunk the content, embed via Python, store in SQLite pub async fn index(&self, content: &str) -> Result<()> { // Clear old chunks sqlx::query("DELETE FROM kb_chunks") @@ -45,7 +40,7 @@ impl KbManager { } let texts: Vec = chunks.iter().map(|c| c.content.clone()).collect(); - let embeddings = self.embedder.lock().unwrap().embed(texts, None)?; + let embeddings = compute_embeddings(&texts).await?; for (chunk, embedding) in chunks.iter().zip(embeddings.into_iter()) { let vec_bytes = embedding_to_bytes(&embedding); @@ -66,7 +61,7 @@ impl KbManager { /// Search KB by query, returns top-k results pub async fn search(&self, query: &str) -> Result> { - let query_embeddings = self.embedder.lock().unwrap().embed(vec![query.to_string()], None)?; + let query_embeddings = compute_embeddings(&[query.to_string()]).await?; let query_vec = query_embeddings .into_iter() .next() @@ -102,7 +97,50 @@ impl KbManager { } } +/// Call Python script to compute embeddings +async fn compute_embeddings(texts: &[String]) -> Result>> { + let input = serde_json::json!({ "texts": texts }); + + let mut child = tokio::process::Command::new("python3") + .arg("/app/scripts/embed.py") + .stdin(Stdio::piped()) + .stdout(Stdio::piped()) + .stderr(Stdio::piped()) + .spawn()?; + + if let Some(mut stdin) = child.stdin.take() { + use tokio::io::AsyncWriteExt; + stdin.write_all(input.to_string().as_bytes()).await?; + } + + let output = child.wait_with_output().await?; + + if !output.status.success() { + let stderr = String::from_utf8_lossy(&output.stderr); + anyhow::bail!("Embedding script failed: {}", stderr); + } + + let result: serde_json::Value = serde_json::from_slice(&output.stdout)?; + let embeddings: Vec> = result["embeddings"] + .as_array() + .ok_or_else(|| anyhow::anyhow!("Invalid embedding output"))? + .iter() + .map(|arr| { + arr.as_array() + .unwrap_or(&vec![]) + .iter() + .map(|v| v.as_f64().unwrap_or(0.0) as f32) + .collect() + }) + .collect(); + + Ok(embeddings) +} + fn cosine_similarity(a: &[f32], b: &[f32]) -> f32 { + if a.len() != b.len() || a.is_empty() { + return 0.0; + } let dot: f32 = a.iter().zip(b.iter()).map(|(x, y)| x * y).sum(); let norm_a: f32 = a.iter().map(|x| x * x).sum::().sqrt(); let norm_b: f32 = b.iter().map(|x| x * x).sum::().sqrt(); @@ -131,7 +169,6 @@ fn split_chunks(content: &str) -> Vec { for line in content.lines() { if line.starts_with("## ") { - // Save previous chunk let text = current_lines.join("\n").trim().to_string(); if !text.is_empty() { chunks.push(Chunk { @@ -150,7 +187,6 @@ fn split_chunks(content: &str) -> Vec { } } - // Last chunk let text = current_lines.join("\n").trim().to_string(); if !text.is_empty() { chunks.push(Chunk {