add/fix: add search functionalities and refactor some modules

Cargo.lock

@@ -46,17 +46,19 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "axum 0.8.4",
- "candle-core",
- "candle-transformers",
  "deadpool-diesel",
  "diesel",
  "futures",
  "hf-hub",
+ "prost 0.14.1",
  "qdrant-client",
  "rayon",
  "serde",
  "tokenizers",
  "tokio",
+ "tonic 0.14.1",
+ "tonic-prost",
+ "tonic-prost-build",
  "tower 0.5.2",
  "tower-http",
  "tracing",
@@ -254,38 +256,6 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
-[[package]]
-name = "bindgen_cuda"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1f8489af5b7d17a81bffe37e0f4d6e1e4de87c87329d05447f22c35d95a1227d"
-dependencies = [
- "glob",
- "num_cpus",
- "rayon",
-]
-
-[[package]]
-name = "bit-set"
-version = "0.5.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0700ddab506f33b20a03b13996eccd309a48e5ff77d0d95926aa0210fb4e95f1"
-dependencies = [
- "bit-vec",
-]
-
-[[package]]
-name = "bit-vec"
-version = "0.6.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb"
-
-[[package]]
-name = "bitflags"
-version = "1.3.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
-
 [[package]]
 name = "bitflags"
 version = "2.9.2"
@@ -307,26 +277,6 @@ version = "3.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
 
-[[package]]
-name = "bytemuck"
-version = "1.23.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3995eaeebcdf32f91f980d360f78732ddc061097ab4e39991ae7a6ace9194677"
-dependencies = [
- "bytemuck_derive",
-]
-
-[[package]]
-name = "bytemuck_derive"
-version = "1.10.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f154e572231cb6ba2bd1176980827e3d5dc04cc183a75dea38109fbdd672d29"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "byteorder"
 version = "1.5.0"
@@ -339,74 +289,6 @@ version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
 
-[[package]]
-name = "candle-core"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9f51e2ecf6efe9737af8f993433c839f956d2b6ed4fd2dd4a7c6d8b0fa667ff"
-dependencies = [
- "byteorder",
- "candle-kernels",
- "cudarc",
- "gemm 0.17.1",
- "half",
- "memmap2",
- "num-traits",
- "num_cpus",
- "rand 0.9.2",
- "rand_distr",
- "rayon",
- "safetensors",
- "thiserror 1.0.69",
- "ug",
- "ug-cuda",
- "yoke 0.7.5",
- "zip 1.1.4",
-]
-
-[[package]]
-name = "candle-kernels"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fcd989c2143aa754370b5bfee309e35fbd259e83d9ecf7a73d23d8508430775"
-dependencies = [
- "bindgen_cuda",
-]
-
-[[package]]
-name = "candle-nn"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c1980d53280c8f9e2c6cbe1785855d7ff8010208b46e21252b978badf13ad69d"
-dependencies = [
- "candle-core",
- "half",
- "num-traits",
- "rayon",
- "safetensors",
- "serde",
- "thiserror 1.0.69",
-]
-
-[[package]]
-name = "candle-transformers"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "186cb80045dbe47e0b387ea6d3e906f02fb3056297080d9922984c90e90a72b0"
-dependencies = [
- "byteorder",
- "candle-core",
- "candle-nn",
- "fancy-regex",
- "num-traits",
- "rand 0.9.2",
- "rayon",
- "serde",
- "serde_json",
- "serde_plain",
- "tracing",
-]
-
 [[package]]
 name = "castaway"
 version = "0.2.4"
@@ -534,12 +416,6 @@ 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 = "0.1.6"
@@ -550,16 +426,6 @@ dependencies = [
  "typenum",
 ]
 
-[[package]]
-name = "cudarc"
-version = "0.16.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "17200eb07e7d85a243aa1bf4569a7aa998385ba98d14833973a817a63cc86e92"
-dependencies = [
- "half",
- "libloading",
-]
-
 [[package]]
 name = "darling"
 version = "0.20.11"
@@ -692,7 +558,7 @@ version = "2.2.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "229850a212cd9b84d4f0290ad9d294afc0ae70fccaa8949dbe8b43ffafa1e20c"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "byteorder",
  "diesel_derives",
  "itoa",
@@ -777,25 +643,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "dyn-stack"
-version = "0.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "56e53799688f5632f364f8fb387488dd05db9fe45db7011be066fc20e7027f8b"
-dependencies = [
- "bytemuck",
- "reborrow",
-]
-
-[[package]]
-name = "dyn-stack"
-version = "0.13.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "490bd48eb68fffcfed519b4edbfd82c69cbe741d175b84f0e0cbe8c57cbe0bdd"
-dependencies = [
- "bytemuck",
-]
-
 [[package]]
 name = "either"
 version = "1.15.0"
@@ -817,18 +664,6 @@ dependencies = [
  "cfg-if",
 ]
 
-[[package]]
-name = "enum-as-inner"
-version = "0.6.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1e6a265c649f3f5979b601d26f1d05ada116434c87741c9493cb56218f76cbc"
-dependencies = [
- "heck",
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "equivalent"
 version = "1.0.2"
@@ -854,23 +689,18 @@ dependencies = [
  "cc",
 ]
 
-[[package]]
-name = "fancy-regex"
-version = "0.13.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2"
-dependencies = [
- "bit-set",
- "regex-automata 0.4.9",
- "regex-syntax 0.8.5",
-]
-
 [[package]]
 name = "fastrand"
 version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
 
+[[package]]
+name = "fixedbitset"
+version = "0.5.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d674e81391d1e1ab681a28d99df07927c6d4aa5b027d7da16ba32d1d21ecd99"
+
 [[package]]
 name = "flate2"
 version = "1.1.2"
@@ -1001,243 +831,6 @@ dependencies = [
  "slab",
 ]
 
-[[package]]
-name = "gemm"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ab24cc62135b40090e31a76a9b2766a501979f3070fa27f689c27ec04377d32"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-c32 0.17.1",
- "gemm-c64 0.17.1",
- "gemm-common 0.17.1",
- "gemm-f16 0.17.1",
- "gemm-f32 0.17.1",
- "gemm-f64 0.17.1",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ab96b703d31950f1aeddded248bc95543c9efc7ac9c4a21fda8703a83ee35451"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-c32 0.18.2",
- "gemm-c64 0.18.2",
- "gemm-common 0.18.2",
- "gemm-f16 0.18.2",
- "gemm-f32 0.18.2",
- "gemm-f64 0.18.2",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-c32"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9c030d0b983d1e34a546b86e08f600c11696fde16199f971cd46c12e67512c0"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-common 0.17.1",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-c32"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f6db9fd9f40421d00eea9dd0770045a5603b8d684654816637732463f4073847"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-common 0.18.2",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-c64"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbb5f2e79fefb9693d18e1066a557b4546cd334b226beadc68b11a8f9431852a"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-common 0.17.1",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-c64"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfcad8a3d35a43758330b635d02edad980c1e143dc2f21e6fd25f9e4eada8edf"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-common 0.18.2",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-common"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a2e7ea062c987abcd8db95db917b4ffb4ecdfd0668471d8dc54734fdff2354e8"
-dependencies = [
- "bytemuck",
- "dyn-stack 0.10.0",
- "half",
- "num-complex",
- "num-traits",
- "once_cell",
- "paste",
- "pulp 0.18.22",
- "raw-cpuid 10.7.0",
- "rayon",
- "seq-macro",
- "sysctl 0.5.5",
-]
-
-[[package]]
-name = "gemm-common"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a352d4a69cbe938b9e2a9cb7a3a63b7e72f9349174a2752a558a8a563510d0f3"
-dependencies = [
- "bytemuck",
- "dyn-stack 0.13.0",
- "half",
- "libm",
- "num-complex",
- "num-traits",
- "once_cell",
- "paste",
- "pulp 0.21.5",
- "raw-cpuid 11.5.0",
- "rayon",
- "seq-macro",
- "sysctl 0.6.0",
-]
-
-[[package]]
-name = "gemm-f16"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ca4c06b9b11952071d317604acb332e924e817bd891bec8dfb494168c7cedd4"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-common 0.17.1",
- "gemm-f32 0.17.1",
- "half",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "rayon",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-f16"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cff95ae3259432f3c3410eaa919033cd03791d81cebd18018393dc147952e109"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-common 0.18.2",
- "gemm-f32 0.18.2",
- "half",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "rayon",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-f32"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e9a69f51aaefbd9cf12d18faf273d3e982d9d711f60775645ed5c8047b4ae113"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-common 0.17.1",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-f32"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc8d3d4385393304f407392f754cd2dc4b315d05063f62cf09f47b58de276864"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-common 0.18.2",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-f64"
-version = "0.17.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa397a48544fadf0b81ec8741e5c0fba0043008113f71f2034def1935645d2b0"
-dependencies = [
- "dyn-stack 0.10.0",
- "gemm-common 0.17.1",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 10.7.0",
- "seq-macro",
-]
-
-[[package]]
-name = "gemm-f64"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35b2a4f76ce4b8b16eadc11ccf2e083252d8237c1b589558a49b0183545015bd"
-dependencies = [
- "dyn-stack 0.13.0",
- "gemm-common 0.18.2",
- "num-complex",
- "num-traits",
- "paste",
- "raw-cpuid 11.5.0",
- "seq-macro",
-]
-
 [[package]]
 name = "generic-array"
 version = "0.14.7"
@@ -1281,12 +874,6 @@ version = "0.31.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f"
 
-[[package]]
-name = "glob"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
-
 [[package]]
 name = "h2"
 version = "0.4.12"
@@ -1306,20 +893,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "half"
-version = "2.6.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9"
-dependencies = [
- "bytemuck",
- "cfg-if",
- "crunchy",
- "num-traits",
- "rand 0.9.2",
- "rand_distr",
-]
-
 [[package]]
 name = "hashbrown"
 version = "0.12.3"
@@ -1517,7 +1090,7 @@ checksum = "200072f5d0e3614556f94a9930d5dc3e0662a652823904c3a75dc3b0af7fee47"
 dependencies = [
  "displaydoc",
  "potential_utf",
- "yoke 0.8.0",
+ "yoke",
  "zerofrom",
  "zerovec",
 ]
@@ -1589,7 +1162,7 @@ dependencies = [
  "stable_deref_trait",
  "tinystr",
  "writeable",
- "yoke 0.8.0",
+ "yoke",
  "zerofrom",
  "zerotrie",
  "zerovec",
@@ -1662,7 +1235,7 @@ version = "0.7.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d93587f37623a1a17d94ef2bc9ada592f5465fe7732084ab7beefabe5c77c0c4"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "cfg-if",
  "libc",
 ]
@@ -1720,29 +1293,13 @@ version = "0.2.175"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a82ae493e598baaea5209805c49bbf2ea7de956d50d7da0da1164f9c6d28543"
 
-[[package]]
-name = "libloading"
-version = "0.8.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "07033963ba89ebaf1584d767badaa2e8fcec21aedea6b8c0346d487d49c28667"
-dependencies = [
- "cfg-if",
- "windows-targets 0.53.3",
-]
-
-[[package]]
-name = "libm"
-version = "0.2.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
-
 [[package]]
 name = "libredox"
 version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "391290121bad3d37fbddad76d8f5d1c1c314cfc646d143d7e07a3086ddff0ce3"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "libc",
 ]
 
@@ -1822,16 +1379,6 @@ version = "2.7.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a282da65faaf38286cf3be983213fcf1d2e2a58700e808f83f4ea9a4804bc0"
 
-[[package]]
-name = "memmap2"
-version = "0.9.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "483758ad303d734cec05e5c12b41d7e93e6a6390c5e9dae6bdeb7c1259012d28"
-dependencies = [
- "libc",
- "stable_deref_trait",
-]
-
 [[package]]
 name = "mime"
 version = "0.3.17"
@@ -1895,6 +1442,12 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "multimap"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d87ecb2933e8aeadb3e3a02b828fed80a7528047e68b4f424523a0981a3a084"
+
 [[package]]
 name = "native-tls"
 version = "0.2.14"
@@ -1932,81 +1485,6 @@ dependencies = [
  "winapi",
 ]
 
-[[package]]
-name = "num"
-version = "0.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35bd024e8b2ff75562e5f34e7f4905839deb4b22955ef5e73d2fea1b9813cb23"
-dependencies = [
- "num-bigint",
- "num-complex",
- "num-integer",
- "num-iter",
- "num-rational",
- "num-traits",
-]
-
-[[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 = [
- "bytemuck",
- "num-traits",
-]
-
-[[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-iter"
-version = "0.1.45"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1429034a0490724d0075ebb2bc9e875d6503c3cf69e235a8941aa757d83ef5bf"
-dependencies = [
- "autocfg",
- "num-integer",
- "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"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
-dependencies = [
- "autocfg",
- "libm",
-]
-
 [[package]]
 name = "num_cpus"
 version = "1.17.0"
@@ -2017,28 +1495,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "num_enum"
-version = "0.7.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a973b4e44ce6cad84ce69d797acf9a044532e4184c4f267913d1b546a0727b7a"
-dependencies = [
- "num_enum_derive",
- "rustversion",
-]
-
-[[package]]
-name = "num_enum_derive"
-version = "0.7.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77e878c846a8abae00dd069496dbe8751b16ac1c3d6bd2a7283a938e8228f90d"
-dependencies = [
- "proc-macro-crate",
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "number_prefix"
 version = "0.4.0"
@@ -2066,7 +1522,7 @@ version = "6.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "336b9c63443aceef14bea841b899035ae3abe89b7c486aaf4c5bd8aafedac3f0"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "libc",
  "once_cell",
  "onig_sys",
@@ -2088,7 +1544,7 @@ version = "0.10.73"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8505734d46c8ab1e19a1dce3aef597ad87dcb4c37e7188231769bd6bd51cebf8"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "cfg-if",
  "foreign-types",
  "libc",
@@ -2150,6 +1606,16 @@ version = "2.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
 
+[[package]]
+name = "petgraph"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3672b37090dbd86368a4145bc067582552b29c27377cad4e0a306c97f9bd7772"
+dependencies = [
+ "fixedbitset",
+ "indexmap 2.10.0",
+]
+
 [[package]]
 name = "pin-project"
 version = "1.1.10"
@@ -2223,12 +1689,13 @@ dependencies = [
 ]
 
 [[package]]
-name = "proc-macro-crate"
-version = "3.3.0"
+name = "prettyplease"
+version = "0.2.37"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "edce586971a4dfaa28950c6f18ed55e0406c1ab88bbce2c6f6293a7aaba73d35"
+checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
 dependencies = [
- "toml_edit",
+ "proc-macro2",
+ "syn",
 ]
 
 [[package]]
@@ -2247,7 +1714,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2796faa41db3ec313a31f7624d9286acf277b52de526150b7e69f3debf891ee5"
 dependencies = [
  "bytes",
- "prost-derive",
+ "prost-derive 0.13.5",
+]
+
+[[package]]
+name = "prost"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7231bd9b3d3d33c86b58adbac74b5ec0ad9f496b19d22801d773636feaa95f3d"
+dependencies = [
+ "bytes",
+ "prost-derive 0.14.1",
+]
+
+[[package]]
+name = "prost-build"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac6c3320f9abac597dcbc668774ef006702672474aad53c6d596b62e487b40b1"
+dependencies = [
+ "heck",
+ "itertools",
+ "log",
+ "multimap",
+ "once_cell",
+ "petgraph",
+ "prettyplease",
+ "prost 0.14.1",
+ "prost-types 0.14.1",
+ "pulldown-cmark",
+ "pulldown-cmark-to-cmark",
+ "regex",
+ "syn",
+ "tempfile",
 ]
 
 [[package]]
@@ -2263,39 +1762,55 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "prost-derive"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9120690fafc389a67ba3803df527d0ec9cbbc9cc45e4cc20b332996dfb672425"
+dependencies = [
+ "anyhow",
+ "itertools",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "prost-types"
 version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "52c2c1bf36ddb1a1c396b3601a3cec27c2462e45f07c386894ec3ccf5332bd16"
 dependencies = [
- "prost",
+ "prost 0.13.5",
 ]
 
 [[package]]
-name = "pulp"
-version = "0.18.22"
+name = "prost-types"
+version = "0.14.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0a01a0dc67cf4558d279f0c25b0962bd08fc6dec0137699eae304103e882fe6"
+checksum = "b9b4db3d6da204ed77bb26ba83b6122a73aeb2e87e25fbf7ad2e84c4ccbf8f72"
 dependencies = [
- "bytemuck",
- "libm",
- "num-complex",
- "reborrow",
+ "prost 0.14.1",
 ]
 
 [[package]]
-name = "pulp"
-version = "0.21.5"
+name = "pulldown-cmark"
+version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96b86df24f0a7ddd5e4b95c94fc9ed8a98f1ca94d3b01bdce2824097e7835907"
+checksum = "1e8bbe1a966bd2f362681a44f6edce3c2310ac21e4d5067a6e7ec396297a6ea0"
 dependencies = [
- "bytemuck",
- "cfg-if",
- "libm",
- "num-complex",
- "reborrow",
- "version_check",
+ "bitflags",
+ "memchr",
+ "unicase",
+]
+
+[[package]]
+name = "pulldown-cmark-to-cmark"
+version = "21.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5b6a0769a491a08b31ea5c62494a8f144ee0987d86d670a8af4df1e1b7cde75"
+dependencies = [
+ "pulldown-cmark",
 ]
 
 [[package]]
@@ -2308,15 +1823,15 @@ dependencies = [
  "derive_builder",
  "futures",
  "futures-util",
- "prost",
- "prost-types",
+ "prost 0.13.5",
+ "prost-types 0.13.5",
  "reqwest",
  "semver",
  "serde",
  "serde_json",
  "thiserror 1.0.69",
  "tokio",
- "tonic",
+ "tonic 0.12.3",
 ]
 
 [[package]]
@@ -2448,34 +1963,6 @@ dependencies = [
  "getrandom 0.3.3",
 ]
 
-[[package]]
-name = "rand_distr"
-version = "0.5.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a8615d50dcf34fa31f7ab52692afec947c4dd0ab803cc87cb3b0b4570ff7463"
-dependencies = [
- "num-traits",
- "rand 0.9.2",
-]
-
-[[package]]
-name = "raw-cpuid"
-version = "10.7.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c297679cb867470fa8c9f67dbba74a78d78e3e98d7cf2b08d6d71540f797332"
-dependencies = [
- "bitflags 1.3.2",
-]
-
-[[package]]
-name = "raw-cpuid"
-version = "11.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c6df7ab838ed27997ba19a4664507e6f82b41fe6e20be42929332156e5e85146"
-dependencies = [
- "bitflags 2.9.2",
-]
-
 [[package]]
 name = "rayon"
 version = "1.11.0"
@@ -2507,12 +1994,6 @@ dependencies = [
  "crossbeam-utils",
 ]
 
-[[package]]
-name = "reborrow"
-version = "0.5.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03251193000f4bd3b042892be858ee50e8b3719f2b08e5833ac4353724632430"
-
 [[package]]
 name = "redox_users"
 version = "0.5.2"
@@ -2681,7 +2162,7 @@ version = "1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "11181fbabf243db407ef8df94a6ce0b2f9a733bd8be4ad02b4eda9602296cac8"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "errno",
  "libc",
  "linux-raw-sys",
@@ -2757,16 +2238,6 @@ version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
 
-[[package]]
-name = "safetensors"
-version = "0.4.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44560c11236a6130a46ce36c836a62936dc81ebf8c36a37947423571be0e55b6"
-dependencies = [
- "serde",
- "serde_json",
-]
-
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -2791,7 +2262,7 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "core-foundation 0.9.4",
  "core-foundation-sys",
  "libc",
@@ -2804,7 +2275,7 @@ version = "3.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "80fb1d92c5028aa318b4b8bd7302a5bfcf48be96a37fc6fc790f806b0004ee0c"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "core-foundation 0.10.1",
  "core-foundation-sys",
  "libc",
@@ -2827,12 +2298,6 @@ version = "1.0.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "56e6fa9c48d24d85fb3de5ad847117517440f6beceb7798af16b4a87d616b8d0"
 
-[[package]]
-name = "seq-macro"
-version = "0.3.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
-
 [[package]]
 name = "serde"
 version = "1.0.219"
@@ -2875,15 +2340,6 @@ dependencies = [
  "serde",
 ]
 
-[[package]]
-name = "serde_plain"
-version = "1.0.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ce1fc6db65a611022b23a0dec6975d63fb80a302cb3388835ff02c097258d50"
-dependencies = [
- "serde",
-]
-
 [[package]]
 name = "serde_urlencoded"
 version = "0.7.1"
@@ -3038,41 +2494,13 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "sysctl"
-version = "0.5.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec7dddc5f0fee506baf8b9fdb989e242f17e4b11c61dfbb0635b705217199eea"
-dependencies = [
- "bitflags 2.9.2",
- "byteorder",
- "enum-as-inner",
- "libc",
- "thiserror 1.0.69",
- "walkdir",
-]
-
-[[package]]
-name = "sysctl"
-version = "0.6.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "01198a2debb237c62b6826ec7081082d951f46dbb64b0e8c7649a452230d1dfc"
-dependencies = [
- "bitflags 2.9.2",
- "byteorder",
- "enum-as-inner",
- "libc",
- "thiserror 1.0.69",
- "walkdir",
-]
-
 [[package]]
 name = "system-configuration"
 version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3c879d448e9d986b661742763247d3693ed13609438cf3d006f51f5368a5ba6b"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "core-foundation 0.9.4",
  "system-configuration-sys",
 ]
@@ -3281,23 +2709,6 @@ dependencies = [
  "tokio",
 ]
 
-[[package]]
-name = "toml_datetime"
-version = "0.6.11"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
-
-[[package]]
-name = "toml_edit"
-version = "0.22.27"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
-dependencies = [
- "indexmap 2.10.0",
- "toml_datetime",
- "winnow",
-]
-
 [[package]]
 name = "tonic"
 version = "0.12.3"
@@ -3319,7 +2730,7 @@ dependencies = [
  "hyper-util",
  "percent-encoding",
  "pin-project",
- "prost",
+ "prost 0.13.5",
  "rustls-native-certs",
  "rustls-pemfile",
  "socket2 0.5.10",
@@ -3332,6 +2743,74 @@ dependencies = [
  "tracing",
 ]
 
+[[package]]
+name = "tonic"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67ac5a8627ada0968acec063a4746bf79588aa03ccb66db2f75d7dce26722a40"
+dependencies = [
+ "async-trait",
+ "axum 0.8.4",
+ "base64 0.22.1",
+ "bytes",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-timeout",
+ "hyper-util",
+ "percent-encoding",
+ "pin-project",
+ "socket2 0.6.0",
+ "sync_wrapper",
+ "tokio",
+ "tokio-stream",
+ "tower 0.5.2",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "tonic-build"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49e323d8bba3be30833707e36d046deabf10a35ae8ad3cae576943ea8933e25d"
+dependencies = [
+ "prettyplease",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tonic-prost"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9c511b9a96d40cb12b7d5d00464446acf3b9105fd3ce25437cfe41c92b1c87d"
+dependencies = [
+ "bytes",
+ "prost 0.14.1",
+ "tonic 0.14.1",
+]
+
+[[package]]
+name = "tonic-prost-build"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ef298fcd01b15e135440c4b8c974460ceca4e6a5af7f1c933b08e4d2875efa1"
+dependencies = [
+ "prettyplease",
+ "proc-macro2",
+ "prost-build",
+ "prost-types 0.14.1",
+ "quote",
+ "syn",
+ "tempfile",
+ "tonic-build",
+]
+
 [[package]]
 name = "tower"
 version = "0.4.13"
@@ -3360,9 +2839,12 @@ checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9"
 dependencies = [
  "futures-core",
  "futures-util",
+ "indexmap 2.10.0",
  "pin-project-lite",
+ "slab",
  "sync_wrapper",
  "tokio",
+ "tokio-util",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -3374,7 +2856,7 @@ version = "0.6.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "adc82fd73de2a9722ac5da747f12383d2bfdb93591ee6c58486e0097890f05f2"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
  "bytes",
  "futures-util",
  "http",
@@ -3473,40 +2955,6 @@ version = "1.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1dccffe3ce07af9386bfd29e80c0ab1a8205a2fc34e4bcd40364df902cfa8f3f"
 
-[[package]]
-name = "ug"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90b70b37e9074642bc5f60bb23247fd072a84314ca9e71cdf8527593406a0dd3"
-dependencies = [
- "gemm 0.18.2",
- "half",
- "libloading",
- "memmap2",
- "num",
- "num-traits",
- "num_cpus",
- "rayon",
- "safetensors",
- "serde",
- "thiserror 1.0.69",
- "tracing",
- "yoke 0.7.5",
-]
-
-[[package]]
-name = "ug-cuda"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14053653d0b7fa7b21015aa9a62edc8af2f60aa6f9c54e66386ecce55f22ed29"
-dependencies = [
- "cudarc",
- "half",
- "serde",
- "thiserror 1.0.69",
- "ug",
-]
-
 [[package]]
 name = "unicase"
 version = "2.8.1"
@@ -3640,7 +3088,7 @@ dependencies = [
  "serde_json",
  "url",
  "utoipa",
- "zip 3.0.0",
+ "zip",
 ]
 
 [[package]]
@@ -4039,22 +3487,13 @@ version = "0.53.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
 
-[[package]]
-name = "winnow"
-version = "0.7.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3edebf492c8125044983378ecb5766203ad3b4c2f7a922bd7dd207f6d443e95"
-dependencies = [
- "memchr",
-]
-
 [[package]]
 name = "wit-bindgen-rt"
 version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
 dependencies = [
- "bitflags 2.9.2",
+ "bitflags",
 ]
 
 [[package]]
@@ -4063,18 +3502,6 @@ version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
 
-[[package]]
-name = "yoke"
-version = "0.7.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40"
-dependencies = [
- "serde",
- "stable_deref_trait",
- "yoke-derive 0.7.5",
- "zerofrom",
-]
-
 [[package]]
 name = "yoke"
 version = "0.8.0"
@@ -4083,22 +3510,10 @@ checksum = "5f41bb01b8226ef4bfd589436a297c53d118f65921786300e427be8d487695cc"
 dependencies = [
  "serde",
  "stable_deref_trait",
- "yoke-derive 0.8.0",
+ "yoke-derive",
  "zerofrom",
 ]
 
-[[package]]
-name = "yoke-derive"
-version = "0.7.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
- "synstructure",
-]
-
 [[package]]
 name = "yoke-derive"
 version = "0.8.0"
@@ -4165,7 +3580,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "36f0bbd478583f79edad978b407914f61b2972f5af6fa089686016be8f9af595"
 dependencies = [
  "displaydoc",
- "yoke 0.8.0",
+ "yoke",
  "zerofrom",
 ]
 
@@ -4175,7 +3590,7 @@ version = "0.11.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e7aa2bd55086f1ab526693ecbe444205da57e25f4489879da80635a46d90e73b"
 dependencies = [
- "yoke 0.8.0",
+ "yoke",
  "zerofrom",
  "zerovec-derive",
 ]
@@ -4191,21 +3606,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "zip"
-version = "1.1.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9cc23c04387f4da0374be4533ad1208cbb091d5c11d070dfef13676ad6497164"
-dependencies = [
- "arbitrary",
- "crc32fast",
- "crossbeam-utils",
- "displaydoc",
- "indexmap 2.10.0",
- "num_enum",
- "thiserror 1.0.69",
-]
-
 [[package]]
 name = "zip"
 version = "3.0.0"

Cargo.toml

@@ -6,17 +6,18 @@ edition = "2024"
 [dependencies]
 anyhow = "1.0.99"
 axum = "0.8.4"
-candle-core = { version = "0.9.1", features = ["cuda"] }
-candle-transformers = { version = "0.9.1", features = ["cuda"] }
 deadpool-diesel = { version = "0.6.1", features = ["postgres"] }
 diesel = { version = "2.2.12", features = ["postgres"] }
 futures = "0.3.31"
 hf-hub = { version = "0.4.3", features = ["tokio"] }
+prost = "0.14.1"
 qdrant-client = "1.15.0"
 rayon = "1.11.0"
 serde = { version = "1.0.219", features = ["derive"] }
 tokenizers = "0.21.4"
 tokio = { version = "1.47.1", features = ["macros", "rt-multi-thread"] }
+tonic = "0.14.1"
+tonic-prost = "0.14.1"
 tower = "0.5.2"
 tower-http = { version = "0.6.6", features = ["cors", "trace"] }
 tracing = "0.1.41"
@@ -24,3 +25,7 @@ tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
 utoipa = "5.4.0"
 utoipa-axum = "0.2.0"
 utoipa-swagger-ui = { version = "9.0.2", features = ["axum"] }
+
+[build-dependencies]
+anyhow = "1.0.99"
+tonic-prost-build = "0.14.1"

build.rs

@@ -0,0 +1,5 @@
+fn main() -> anyhow::Result<()> {
+    println!("cargo::rerun-if-changed=proto/text_embed.proto");
+    tonic_prost_build::compile_protos("proto/text_embed.proto")?;
+    Ok(())
+}

proto/text_embed.proto

@@ -0,0 +1,15 @@
+syntax = "proto3";
+
+package text_embed;
+
+service TextEmbeddingService {
+  rpc GetEmbedding (TextRequest) returns (EmbeddingResponse);
+}
+
+message TextRequest {
+  string text = 1;
+}
+
+message EmbeddingResponse {
+  repeated float embeddings = 1;
+}

src/constants/mod.rs

@@ -1,3 +1,4 @@
-pub const EMBEDDING_MODEL_NAME: &str = "openai/clip-vit-base-patch32";
 pub const QDRANT_KEYFRAME_COLLECTION_NAME: &str = "keyframes";
+pub const QDRANT_KEYFRAME_COLLECTION_IMAGE_VECTOR_NAME: &str = "images";
+pub const QDRANT_KEYFRAME_COLLECTION_OBJECT_VECTOR_NAME: &str = "objects";
 pub const OPENAPI_TAG: &str = "AIC Server";

src/controllers/v1/vectors/keyframes/mod.rs

@@ -7,7 +7,7 @@ use crate::{
         dtos::vectors::keyframes::{VectorizedKeyframeDto, VectorizedKeyframeRequestDto},
         states::AppState,
     },
-    services::vectors::keyframes::VectorizedKeyframeService,
+    services::vector_queries::keyframes::VectorizedKeyframeService,
 };
 
 pub fn router() -> OpenApiRouter<AppState> {

src/models/mod.rs

@@ -1,3 +1,4 @@
 pub mod dtos;
 pub mod entities;
+pub mod protos;
 pub mod states;

src/models/protos/mod.rs

@@ -0,0 +1,3 @@
+pub mod text_embed {
+    tonic::include_proto!("text_embed");
+}

src/models/states/mod.rs

@@ -1,43 +1,22 @@
 use std::sync::Arc;
 
-use candle_core::{DType, Device};
-use candle_transformers::models::{
-    clip::{ClipConfig, ClipModel},
-    mimi::candle_nn::VarBuilder,
-};
 use deadpool_diesel::{
     Runtime,
     postgres::{Manager, Pool},
 };
-use hf_hub::api::tokio::ApiRepo;
-use qdrant_client::{
-    Qdrant,
-    qdrant::{CreateCollectionBuilder, Distance, VectorParamsBuilder},
-};
-use tokenizers::Tokenizer;
-
-use crate::constants::{EMBEDDING_MODEL_NAME, QDRANT_KEYFRAME_COLLECTION_NAME};
+use qdrant_client::Qdrant;
 
 #[derive(Clone)]
 pub struct AppState {
-    device: Arc<Device>,
     diesel_pool: Pool,
-    model: Arc<ClipModel>,
     qdrant_client: Arc<Qdrant>,
-    tokenizer: Arc<Tokenizer>,
 }
 
 impl AppState {
     pub async fn new() -> anyhow::Result<Self> {
-        let api = hf_hub::api::tokio::Api::new()?.model(EMBEDDING_MODEL_NAME.to_owned());
-        let device = Device::cuda_if_available(0)?;
-
         Ok(Self {
             diesel_pool: Self::diesel_pool_helper()?,
             qdrant_client: Self::qdrant_client_helper().await?,
-            model: Self::model_helper(&api, &device).await?,
-            tokenizer: Self::tokenizer_helper(&api).await?,
-            device: Arc::new(device),
         })
     }
 
@@ -50,55 +29,20 @@ impl AppState {
     }
 
     async fn qdrant_client_helper() -> anyhow::Result<Arc<Qdrant>> {
-        let client = Qdrant::from_url(&std::env::var("QDRANT_URL")?).build()?;
-
-        if client
-            .collection_exists(QDRANT_KEYFRAME_COLLECTION_NAME)
-            .await?
-        {
-            client
-                .create_collection(
-                    CreateCollectionBuilder::new(QDRANT_KEYFRAME_COLLECTION_NAME)
-                        .vectors_config(VectorParamsBuilder::new(512, Distance::Cosine)),
-                )
-                .await?;
-        }
-
-        Ok(Arc::new(client))
-    }
-
-    async fn model_helper(api: &ApiRepo, device: &Device) -> anyhow::Result<Arc<ClipModel>> {
-        let model_path = api.get("pytorch_model.bin").await?;
-        let vb = VarBuilder::from_pth(model_path, DType::F32, device)?;
-        let config = ClipConfig::vit_base_patch32();
-
-        Ok(Arc::new(ClipModel::new(vb, &config)?))
-    }
-
-    async fn tokenizer_helper(api: &ApiRepo) -> anyhow::Result<Arc<Tokenizer>> {
-        let tokenizer_file = api.get("tokenizer.json").await?;
-        Ok(Arc::new(
-            Tokenizer::from_file(tokenizer_file).map_err(anyhow::Error::msg)?,
+        let client = Qdrant::from_url(&format!(
+            "http://{}:{}",
+            std::env::var("QDRANT_HOST")?,
+            std::env::var("QDRANT_GRPC_PORT")?
         ))
-    }
-
-    pub fn device(&self) -> &Device {
-        &self.device
+        .build()?;
+        Ok(Arc::new(client))
     }
 
     pub fn diesel_pool(&self) -> &Pool {
         &self.diesel_pool
     }
 
-    pub fn model(&self) -> &ClipModel {
-        &self.model
-    }
-
     pub fn qdrant_client(&self) -> &Qdrant {
         &self.qdrant_client
     }
-
-    pub fn tokenizer(&self) -> &Tokenizer {
-        &self.tokenizer
-    }
 }

src/services/embeddings/mod.rs

@@ -0,0 +1 @@
+pub mod texts;

src/services/embeddings/texts/mod.rs

@@ -0,0 +1,24 @@
+use tonic::Request;
+
+use crate::models::protos::text_embed::{
+    TextRequest, text_embedding_service_client::TextEmbeddingServiceClient,
+};
+
+pub struct TextEmbeddingService {
+    client: TextEmbeddingServiceClient<tonic::transport::Channel>,
+}
+
+impl TextEmbeddingService {
+    pub async fn new() -> anyhow::Result<Self> {
+        Ok(Self {
+            client: TextEmbeddingServiceClient::connect(std::env::var("EMBEDDING_SERVER_URL")?)
+                .await?,
+        })
+    }
+
+    pub async fn embed_text(&mut self, text: &str) -> anyhow::Result<Vec<f32>> {
+        let request = Request::new(TextRequest { text: text.into() });
+        let response = self.client.get_embedding(request).await?;
+        Ok(response.into_inner().embeddings)
+    }
+}

src/services/mod.rs

@@ -1,3 +1,4 @@
+pub mod embeddings;
 pub mod keyframes;
-pub mod vectors;
+pub mod vector_queries;
 pub mod videos;

src/services/{vectors → vector_queries}/keyframes/mod.rs

@@ -1,44 +1,35 @@
-use candle_core::{Device, Tensor};
-use candle_transformers::models::clip::ClipModel;
-use qdrant_client::{Qdrant, qdrant::QueryPointsBuilder};
+use qdrant_client::{
+    Qdrant,
+    qdrant::{PrefetchQueryBuilder, Query, QueryPointsBuilder},
+};
 use rayon::iter::{IntoParallelIterator, ParallelIterator};
-use tokenizers::Tokenizer;
 
-use crate::models::{dtos::vectors::keyframes::VectorizedKeyframeDto, states::AppState};
+use crate::{
+    constants::{
+        QDRANT_KEYFRAME_COLLECTION_IMAGE_VECTOR_NAME, QDRANT_KEYFRAME_COLLECTION_NAME,
+        QDRANT_KEYFRAME_COLLECTION_OBJECT_VECTOR_NAME,
+    },
+    models::{dtos::vectors::keyframes::VectorizedKeyframeDto, states::AppState},
+    services::embeddings::texts::TextEmbeddingService,
+};
 
 #[derive(Clone, Copy)]
 pub struct VectorizedKeyframeService<'a> {
     client: &'a Qdrant,
-    device: &'a Device,
-    model: &'a ClipModel,
-    tokenizer: &'a Tokenizer,
 }
 
 impl<'a> From<&'a AppState> for VectorizedKeyframeService<'a> {
     fn from(value: &'a AppState) -> Self {
         Self {
-            model: value.model(),
-            tokenizer: value.tokenizer(),
-            device: value.device(),
             client: value.qdrant_client(),
         }
     }
 }
 
 impl<'a> VectorizedKeyframeService<'a> {
-    fn embed_text(&self, text: &str) -> anyhow::Result<Tensor> {
-        let input_ids = {
-            let input_ids = self
-                .tokenizer
-                .encode_fast(text, true)
-                .map_err(anyhow::Error::msg)?;
-            Tensor::new(input_ids.get_ids(), self.device)?
-        };
-
-        Ok(self
-            .model
-            .get_text_features(&input_ids.unsqueeze(0)?)
-            .map(|x| x.squeeze(0))??)
+    async fn embed_text(&self, text: &str) -> anyhow::Result<Vec<f32>> {
+        let mut embedding_service = TextEmbeddingService::new().await?;
+        embedding_service.embed_text(text).await
     }
 
     pub async fn find_nearest_top_k_by_text(
@@ -46,13 +37,20 @@ impl<'a> VectorizedKeyframeService<'a> {
         text: &str,
         top_k: u64,
     ) -> anyhow::Result<Vec<VectorizedKeyframeDto>> {
-        let embeddings = self.embed_text(text)?;
+        let embeddings = self.embed_text(text).await?;
 
         let query_result = self
             .client
             .query(
-                QueryPointsBuilder::new("keyframes")
-                    .query(embeddings.squeeze(0)?.to_vec1::<f32>()?)
+                QueryPointsBuilder::new(QDRANT_KEYFRAME_COLLECTION_NAME)
+                    .add_prefetch(
+                        PrefetchQueryBuilder::default()
+                            .query(Query::new_nearest(embeddings.clone()))
+                            .using(QDRANT_KEYFRAME_COLLECTION_IMAGE_VECTOR_NAME)
+                            .limit(100u64),
+                    )
+                    .query(Query::new_nearest(embeddings))
+                    .using(QDRANT_KEYFRAME_COLLECTION_OBJECT_VECTOR_NAME)
                     .limit(top_k),
             )
             .await?