fabi/Mangalord
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(analysis): add in-process ocrs OCR backend

Browse Source 
Add a CPU-only, English-first OCR engine (the `ocrs` crate on the `rten`
runtime) as an alternative to the local-LLM "vision" backend, which ran
too slowly on the target Raspberry Pi 5.

- `ANALYSIS_BACKEND` (default `ocr`) selects the engine; `vision` keeps the
  existing LLM path. Deploy-time, env-only — not admin-tunable.
- `analysis::ocr` adds an `OcrEngine` trait (testable seam), the `OcrsEngine`
  impl (models loaded once, inference on the blocking pool), and an
  `OcrAnalyzeDispatcher` that plugs into the existing `AnalyzeDispatcher`
  seam and reuses `persist_analysis`, so OCR text lands in `page_ocr_text`
  and the `search_doc` tsvector exactly as the vision path produces them.
- The backend image bakes the two `.rten` models into /models, where
  `OCRS_DETECTION_MODEL` / `OCRS_RECOGNITION_MODEL` default.

Because `/v1/me/page-search` ranks on `search_doc`, OCR text search works
the moment pages are processed. Auto-tagging, scene description and NSFW
flags remain the vision backend's job (deferred).

Bumps to 0.90.0 (minor) in both manifests.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-06-26 07:12:01 +02:00
parent 4fb98e4a1e
commit cb34eeb82e
12 changed files with 752 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

258
backend/Cargo.lock generated
View File

@@ -214,6 +214,12 @@ version = "1.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2af50177e190e07a26ab74f8b1efbfe2ef87da2116221318cb1c2e82baf7de06"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "bitflags"
version = "2.11.1"
@@ -514,6 +520,25 @@ 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"
@@ -638,7 +663,7 @@ version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e0e367e4e7da84520dedcac1901e4da967309406d1e51017ae1abfb97adbd38"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"objc2",
]
@@ -772,6 +797,16 @@ version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
[[package]]
name = "flatbuffers"
version = "24.12.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f1baf0dbf96932ec9a3038d57900329c015b0bfb7b63d904f3bc27e2b02a096"
dependencies = [
"bitflags 1.3.2",
"rustc_version",
]
[[package]]
name = "flate2"
version = "1.1.9"
@@ -1059,6 +1094,12 @@ version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]]
name = "hermit-abi"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
[[package]]
name = "hex"
version = "0.4.3"
@@ -1448,7 +1489,7 @@ version = "0.1.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e02f3bb43d335493c96bf3fd3a321600bf6bd07ed34bc64118e9293bdffea46c"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"libc",
"plain",
"redox_syscall 0.7.5",
@@ -1517,7 +1558,7 @@ checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "mangalord"
version = "0.89.0"
version = "0.90.0"
dependencies = [
"anyhow",
"argon2",
@@ -1537,8 +1578,10 @@ dependencies = [
"infer",
"mime",
"nix 0.29.0",
"ocrs",
"rand 0.8.6",
"reqwest",
"rten",
"scraper",
"serde",
"serde_json",
@@ -1669,7 +1712,7 @@ version = "0.29.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "71e2746dc3a24dd78b3cfcb7be93368c6de9963d30f43a6a73998a9cf4b17b46"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"cfg-if",
"cfg_aliases",
"libc",
@@ -1681,7 +1724,7 @@ version = "0.31.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf20d2fde8ff38632c426f1165ed7436270b44f199fc55284c38276f9db47c3d"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"cfg-if",
"cfg_aliases",
"libc",
@@ -1757,6 +1800,16 @@ dependencies = [
"libm",
]
[[package]]
name = "num_cpus"
version = "1.17.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "91df4bbde75afed763b708b7eee1e8e7651e02d97f6d5dd763e89367e957b23b"
dependencies = [
"hermit-abi",
"libc",
]
[[package]]
name = "objc2"
version = "0.6.4"
@@ -1772,7 +1825,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73ad74d880bb43877038da939b7427bba67e9dd42004a18b809ba7d87cee241c"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"objc2",
"objc2-foundation",
]
@@ -1793,7 +1846,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2a180dd8642fa45cdb7dd721cd4c11b1cadd4929ce112ebd8b9f5803cc79d536"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"dispatch2",
"objc2",
]
@@ -1804,7 +1857,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e022c9d066895efa1345f8e33e584b9f958da2fd4cd116792e15e07e4720a807"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"dispatch2",
"objc2",
"objc2-core-foundation",
@@ -1837,7 +1890,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0cde0dfb48d25d2b4862161a4d5fcc0e3c24367869ad306b0c9ec0073bfed92d"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"objc2",
"objc2-core-foundation",
"objc2-core-graphics",
@@ -1855,7 +1908,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e3e0adef53c21f888deb4fa59fc59f7eb17404926ee8a6f59f5df0fd7f9f3272"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"block2",
"libc",
"objc2",
@@ -1868,7 +1921,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "180788110936d59bab6bd83b6060ffdfffb3b922ba1396b312ae795e1de9d81d"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"objc2",
"objc2-core-foundation",
]
@@ -1879,7 +1932,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "96c1358452b371bf9f104e21ec536d37a650eb10f7ee379fff67d2e08d537f1f"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"objc2",
"objc2-core-foundation",
"objc2-foundation",
@@ -1891,7 +1944,7 @@ version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d87d638e33c06f577498cbcc50491496a3ed4246998a7fbba7ccb98b1e7eab22"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"block2",
"objc2",
"objc2-cloud-kit",
@@ -1916,6 +1969,21 @@ dependencies = [
"objc2-foundation",
]
[[package]]
name = "ocrs"
version = "0.12.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a5379fdd3f11522b5a2ff53017a189463dabf5d0a9c915cb3eb97fabec4ea11c"
dependencies = [
"anyhow",
"rayon",
"rten",
"rten-imageproc",
"rten-tensor",
"thiserror 2.0.18",
"wasm-bindgen",
]
[[package]]
name = "once_cell"
version = "1.21.4"
@@ -2142,7 +2210,7 @@ version = "0.18.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "60769b8b31b2a9f263dae2776c37b1b28ae246943cf719eb6946a1db05128a61"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"crc32fast",
"fdeflate",
"flate2",
@@ -2361,13 +2429,33 @@ dependencies = [
"getrandom 0.3.4",
]
[[package]]
name = "rayon"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb39b166781f92d482534ef4b4b1b2568f42613b53e5b6c160e24cfbfa30926d"
dependencies = [
"either",
"rayon-core",
]
[[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"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
dependencies = [
"bitflags",
"bitflags 2.11.1",
]
[[package]]
@@ -2376,7 +2464,7 @@ version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4666a1a60d8412eab19d94f6d13dcc9cea0a5ef4fdf6a5db306537413c661b1b"
dependencies = [
"bitflags",
"bitflags 2.11.1",
]
[[package]]
@@ -2496,19 +2584,135 @@ dependencies = [
"zeroize",
]
[[package]]
name = "rten"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43c230fa4ade87c913f61dbd911b7eb0d49460ceff3f1e4fabc837fac191137c"
dependencies = [
"flatbuffers",
"num_cpus",
"rayon",
"rten-base",
"rten-gemm",
"rten-model-file",
"rten-onnx",
"rten-shape-inference",
"rten-simd",
"rten-tensor",
"rten-vecmath",
"rustc-hash",
"smallvec",
"typeid",
"wasm-bindgen",
]
[[package]]
name = "rten-base"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2738cf8bb4c27f828ac788d01ccf4e367e8e773cfec6851f81851b5211de6a79"
dependencies = [
"rayon",
]
[[package]]
name = "rten-gemm"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "330a81a0ca209fb5ce21bd17efa0bd287d5881c6cebfbff0b21c4294a1a14a9e"
dependencies = [
"rayon",
"rten-base",
"rten-simd",
"rten-tensor",
]
[[package]]
name = "rten-imageproc"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d5f148e7e941fb5727b9046a5fa1b45525543d5105f14b384fd9261df0ee49bc"
dependencies = [
"rten-tensor",
]
[[package]]
name = "rten-model-file"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed2f8d270f07ab1bbfff47250c6039f6caa5da59d6da7d74f66aa48559aa6fea"
dependencies = [
"flatbuffers",
"rten-base",
]
[[package]]
name = "rten-onnx"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "23086eef75bfb55278cb0b45cf9f5a877d466d914914aafebee4ffca9b24d20c"
[[package]]
name = "rten-shape-inference"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e8a913c7ca40e2bfbb2a0cd447cce56b33ab19435f56693271a2ef37cf58984"
dependencies = [
"rten-tensor",
"smallvec",
]
[[package]]
name = "rten-simd"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b19a0032dfcb70dd20960c1c51a37674b237586cbc1ce586f45b46605d108e82"
[[package]]
name = "rten-tensor"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "05dc744a270aa32d154f1a3df8e48740ccc1be9dfbcf23295ada66d83aa98de6"
dependencies = [
"rayon",
"rten-base",
"smallvec",
"typeid",
]
[[package]]
name = "rten-vecmath"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9574ddebf5671bc08ceb76e2e1638fadc57fdeff318634eab2c29e9a803cff64"
dependencies = [
"rten-base",
"rten-simd",
]
[[package]]
name = "rustc-hash"
version = "2.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
[[package]]
name = "rustc_version"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
dependencies = [
"semver",
]
[[package]]
name = "rustix"
version = "0.38.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fdb5bc1ae2baa591800df16c9ca78619bf65c0488b41b96ccec5d11220d8c154"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"errno",
"libc",
"linux-raw-sys 0.4.15",
@@ -2521,7 +2725,7 @@ version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"errno",
"libc",
"linux-raw-sys 0.12.1",
@@ -2603,7 +2807,7 @@ version = "0.25.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4eb30575f3638fc8f6815f448d50cb1a2e255b0897985c8c59f4d37b72a07b06"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"cssparser",
"derive_more",
"fxhash",
@@ -2911,7 +3115,7 @@ checksum = "aa003f0038df784eb8fecbbac13affe3da23b45194bd57dba231c8f48199c526"
dependencies = [
"atoi",
"base64",
"bitflags",
"bitflags 2.11.1",
"byteorder",
"bytes",
"chrono",
@@ -2955,7 +3159,7 @@ checksum = "db58fcd5a53cf07c184b154801ff91347e4c30d17a3562a635ff028ad5deda46"
dependencies = [
"atoi",
"base64",
"bitflags",
"bitflags 2.11.1",
"byteorder",
"chrono",
"crc",
@@ -3317,7 +3521,7 @@ version = "0.6.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "68d6fdd9f81c2819c9a8b0e0cd91660e7746a8e6ea2ba7c6b2b057985f6bcb51"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"bytes",
"futures-util",
"http",
@@ -3428,6 +3632,12 @@ dependencies = [
"utf-8",
]
[[package]]
name = "typeid"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bc7d623258602320d5c55d1bc22793b57daff0ec7efc270ea7d55ce1d5f5471c"
[[package]]
name = "typenum"
version = "1.20.0"
@@ -3668,7 +3878,7 @@ version = "0.244.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "47b807c72e1bac69382b3a6fb3dbe8ea4c0ed87ff5629b8685ae6b9a611028fe"
dependencies = [
"bitflags",
"bitflags 2.11.1",
"hashbrown 0.15.5",
"indexmap",
"semver",
@@ -4096,7 +4306,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9d66ea20e9553b30172b5e831994e35fbde2d165325bec84fc43dbf6f4eb9cb2"
dependencies = [
"anyhow",
"bitflags",
"bitflags 2.11.1",
"indexmap",
"log",
"serde",