Nomad changes

2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
--- a/packages/ruby/.rubocop.yml
+++ b/packages/ruby/.rubocop.yml
@@ -0,0 +1,60 @@
+plugins:
+  - rubocop-performance
+  - rubocop-rspec
+
+AllCops:
+  TargetRubyVersion: 3.2
+  NewCops: enable
+  SuggestExtensions: false
+  Exclude:
+    - "vendor/**/*"
+    - "tmp/**/*"
+    - "lib/**/*.bundle"
+    - "lib/**/*.rb"
+    - "ext/**/*"
+
+Style/FrozenStringLiteralComment:
+  Enabled: true
+  EnforcedStyle: always
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/Documentation:
+  Enabled: false
+
+Layout/LineLength:
+  Max: 120
+  AllowedPatterns:
+    - '\A\s*#'
+  Exclude:
+    - "spec/**/*"
+
+Metrics/MethodLength:
+  Max: 20
+  Exclude:
+    - "spec/**/*"
+
+Metrics/BlockLength:
+  Enabled: true
+  Max: 350
+  CountComments: false
+
+Metrics/AbcSize:
+  Max: 20
+  Exclude:
+    - "spec/**/*"
+
+RSpec/ExampleLength:
+  Max: 50
+
+RSpec/MultipleExpectations:
+  Max: 25
+
+RSpec/NestedGroups:
+  Max: 6
--- a/packages/ruby/Gemfile
+++ b/packages/ruby/Gemfile
@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gemspec
+
+group :development do
+  gem "rake-compiler", "~> 1.2"
+  gem "rb_sys", "~> 0.9"
+  gem "rspec", "~> 3.0"
+  gem "rubocop", "~> 1.0"
+  gem "rubocop-performance", "~> 1.0"
+  gem "rubocop-rspec", "~> 3.0"
+  gem "steep", "~> 1.0"
+end
--- a/packages/ruby/Gemfile.lock
+++ b/packages/ruby/Gemfile.lock
@@ -0,0 +1,232 @@
+PATH
+  remote: .
+  specs:
+    kreuzberg (5.0.0.pre.rc.3)
+      rb_sys (~> 0.9)
+      sorbet-runtime (~> 0.5)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (8.1.3)
+      base64
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.3.1)
+      connection_pool (>= 2.2.5)
+      drb
+      i18n (>= 1.6, < 2)
+      json
+      logger (>= 1.4.2)
+      minitest (>= 5.1)
+      securerandom (>= 0.3)
+      tzinfo (~> 2.0, >= 2.0.5)
+      uri (>= 0.13.1)
+    ast (2.4.3)
+    base64 (0.3.0)
+    bigdecimal (4.1.2)
+    concurrent-ruby (1.3.6)
+    connection_pool (3.0.2)
+    csv (3.3.5)
+    diff-lcs (1.6.2)
+    drb (2.2.3)
+    ffi (1.17.4)
+    ffi (1.17.4-aarch64-linux-gnu)
+    ffi (1.17.4-aarch64-linux-musl)
+    ffi (1.17.4-arm-linux-gnu)
+    ffi (1.17.4-arm-linux-musl)
+    ffi (1.17.4-arm64-darwin)
+    ffi (1.17.4-x86-linux-gnu)
+    ffi (1.17.4-x86-linux-musl)
+    ffi (1.17.4-x86_64-darwin)
+    ffi (1.17.4-x86_64-linux-gnu)
+    ffi (1.17.4-x86_64-linux-musl)
+    fileutils (1.8.0)
+    i18n (1.14.8)
+      concurrent-ruby (~> 1.0)
+    json (2.19.7)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    listen (3.10.0)
+      logger
+      rb-fsevent (~> 0.10, >= 0.10.3)
+      rb-inotify (~> 0.9, >= 0.9.10)
+    logger (1.7.0)
+    minitest (6.0.6)
+      drb (~> 2.0)
+      prism (~> 1.5)
+    mutex_m (0.3.0)
+    parallel (2.1.0)
+    parser (3.3.11.1)
+      ast (~> 2.4.1)
+      racc
+    prism (1.9.0)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    rake (13.4.2)
+    rake-compiler (1.3.1)
+      rake
+    rake-compiler-dock (1.12.0)
+    rb-fsevent (0.11.2)
+    rb-inotify (0.11.1)
+      ffi (~> 1.0)
+    rb_sys (0.9.128)
+      rake-compiler-dock (= 1.12.0)
+    rbs (3.10.4)
+      logger
+      tsort
+    regexp_parser (2.12.0)
+    rspec (3.13.2)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.6)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.8)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.7)
+    rubocop (1.86.2)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
+      parallel (>= 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.49.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.49.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.7)
+    rubocop-performance (1.26.1)
+      lint_roller (~> 1.1)
+      rubocop (>= 1.75.0, < 2.0)
+      rubocop-ast (>= 1.47.1, < 2.0)
+    rubocop-rspec (3.9.0)
+      lint_roller (~> 1.1)
+      rubocop (~> 1.81)
+    ruby-progressbar (1.13.0)
+    securerandom (0.4.1)
+    sorbet-runtime (0.6.13261)
+    steep (1.10.0)
+      activesupport (>= 5.1)
+      concurrent-ruby (>= 1.1.10)
+      csv (>= 3.0.9)
+      fileutils (>= 1.1.0)
+      json (>= 2.1.0)
+      language_server-protocol (>= 3.17.0.4, < 4.0)
+      listen (~> 3.0)
+      logger (>= 1.3.0)
+      mutex_m (>= 0.3.0)
+      parser (>= 3.1)
+      rainbow (>= 2.2.2, < 4.0)
+      rbs (~> 3.9)
+      securerandom (>= 0.1)
+      strscan (>= 1.0.0)
+      terminal-table (>= 2, < 5)
+      uri (>= 0.12.0)
+    strscan (3.1.8)
+    terminal-table (4.0.0)
+      unicode-display_width (>= 1.1.1, < 4)
+    tsort (0.2.0)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (3.2.0)
+      unicode-emoji (~> 4.1)
+    unicode-emoji (4.2.0)
+    uri (1.1.1)
+
+PLATFORMS
+  aarch64-linux-gnu
+  aarch64-linux-musl
+  arm-linux-gnu
+  arm-linux-musl
+  arm64-darwin
+  ruby
+  x86-linux-gnu
+  x86-linux-musl
+  x86_64-darwin
+  x86_64-linux-gnu
+  x86_64-linux-musl
+
+DEPENDENCIES
+  kreuzberg!
+  rake-compiler (~> 1.2)
+  rb_sys (~> 0.9)
+  rspec (~> 3.0)
+  rubocop (~> 1.0)
+  rubocop-performance (~> 1.0)
+  rubocop-rspec (~> 3.0)
+  steep (~> 1.0)
+
+CHECKSUMS
+  activesupport (8.1.3) sha256=21a5e0dfbd4c3ddd9e1317ec6a4d782fa226e7867dc70b0743acda81a1dca20e
+  ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
+  base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
+  bigdecimal (4.1.2) sha256=53d217666027eab4280346fba98e7d5b66baaae1b9c3c1c0ffe89d48188a3fbd
+  concurrent-ruby (1.3.6) sha256=6b56837e1e7e5292f9864f34b69c5a2cbc75c0cf5338f1ce9903d10fa762d5ab
+  connection_pool (3.0.2) sha256=33fff5ba71a12d2aa26cb72b1db8bba2a1a01823559fb01d29eb74c286e62e0a
+  csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
+  diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
+  drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
+  ffi (1.17.4) sha256=bcd1642e06f0d16fc9e09ac6d49c3a7298b9789bcb58127302f934e437d60acf
+  ffi (1.17.4-aarch64-linux-gnu) sha256=b208f06f91ffd8f5e1193da3cae3d2ccfc27fc36fba577baf698d26d91c080df
+  ffi (1.17.4-aarch64-linux-musl) sha256=9286b7a615f2676245283aef0a0a3b475ae3aae2bb5448baace630bb77b91f39
+  ffi (1.17.4-arm-linux-gnu) sha256=d6dbddf7cb77bf955411af5f187a65b8cd378cb003c15c05697f5feee1cb1564
+  ffi (1.17.4-arm-linux-musl) sha256=9d4838ded0465bef6e2426935f6bcc93134b6616785a84ffd2a3d82bc3cf6f95
+  ffi (1.17.4-arm64-darwin) sha256=19071aaf1419251b0a46852abf960e77330a3b334d13a4ab51d58b31a937001b
+  ffi (1.17.4-x86-linux-gnu) sha256=38e150df5f4ca555e25beca4090823ae09657bceded154e3c52f8631c1ed72cf
+  ffi (1.17.4-x86-linux-musl) sha256=fbeec0fc7c795bcf86f623bb18d31ea1820f7bd580e1703a3d3740d527437809
+  ffi (1.17.4-x86_64-darwin) sha256=aa70390523cf3235096cf64962b709b4cfbd5c082a2cb2ae714eb0fe2ccda496
+  ffi (1.17.4-x86_64-linux-gnu) sha256=9d3db14c2eae074b382fa9c083fe95aec6e0a1451da249eab096c34002bc752d
+  ffi (1.17.4-x86_64-linux-musl) sha256=3fdf9888483de005f8ef8d1cf2d3b20d86626af206cbf780f6a6a12439a9c49e
+  fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
+  i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
+  json (2.19.7) sha256=fe432c8639f6efff69f9d73b518a3705d9581ab93156f981ea72806e1e5bcc3e
+  kreuzberg (5.0.0.pre.rc.3)
+  language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
+  lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
+  listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
+  logger (1.7.0) sha256=196edec7cc44b66cfb40f9755ce11b392f21f7967696af15d274dde7edff0203
+  minitest (6.0.6) sha256=153ea36d1d987a62942382b61075745042a2b3123b1cd48f4c3675af9cc7d6f1
+  mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
+  parallel (2.1.0) sha256=b35258865c2e31134c5ecb708beaaf6772adf9d5efae28e93e99260877b09356
+  parser (3.3.11.1) sha256=d17ace7aabe3e72c3cc94043714be27cc6f852f104d81aa284c2281aecc65d54
+  prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
+  racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
+  rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
+  rake (13.4.2) sha256=cb825b2bd5f1f8e91ca37bddb4b9aaf345551b4731da62949be002fa89283701
+  rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
+  rake-compiler-dock (1.12.0) sha256=f13205c2738f3d2053afcd03491a9e4541b22a59a0bfc53fc8bc883bd8188023
+  rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
+  rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
+  rb_sys (0.9.128) sha256=9ab81f4d6d4e1895de18762232362d1264475aa7035756b50441e442130538fd
+  rbs (3.10.4) sha256=b17d7c4be4bb31a11a3b529830f0aa206a807ca42f2e7921a3027dfc6b7e5ce8
+  regexp_parser (2.12.0) sha256=35a916a1d63190ab5c9009457136ae5f3c0c7512d60291d0d1378ba18ce08ebb
+  rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
+  rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
+  rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
+  rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
+  rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
+  rubocop (1.86.2) sha256=bb2e97f635eda42c448f2588f4a6ff78f221b8bdfdf65b1e9b07fbd57521b45d
+  rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
+  rubocop-performance (1.26.1) sha256=cd19b936ff196df85829d264b522fd4f98b6c89ad271fa52744a8c11b8f71834
+  rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
+  ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
+  securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
+  sorbet-runtime (0.6.13261) sha256=880c1575676b9f3ddfd42328ea5dd13739e24186c35bac63adad41589ee3c763
+  steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
+  strscan (3.1.8) sha256=aae2db611a225559f21ffbb71765c9a4e60fd262534a9ea84f4f11c7f32f679e
+  terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2
+  tsort (0.2.0) sha256=9650a793f6859a43b6641671278f79cfead60ac714148aabe4e3f0060480089f
+  tzinfo (2.0.6) sha256=8daf828cc77bcf7d63b0e3bdb6caa47e2272dcfaf4fbfe46f8c3a9df087a829b
+  unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
+  unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
+  uri (1.1.1) sha256=379fa58d27ffb1387eaada68c749d1426738bd0f654d812fcc07e7568f5c57c6
+
+BUNDLED WITH
+  4.0.7
--- a/packages/ruby/LICENSE
+++ b/packages/ruby/LICENSE
@@ -0,0 +1,93 @@
+Elastic License 2.0 (ELv2)
+
+Copyright 2025-2026 Kreuzberg, Inc.
+
+Acceptance
+
+By using the software, you agree to all of the terms and conditions below.
+
+Copyright License
+
+The licensor grants you a non-exclusive, royalty-free, worldwide,
+non-sublicensable, non-transferable license to use, copy, distribute, make
+available, and prepare derivative works of the software, in each case subject to
+the limitations and conditions below.
+
+Limitations
+
+You may not provide the software to third parties as a hosted or managed
+service, where the service provides users with access to any substantial set of
+the features or functionality of the software.
+
+You may not move, change, disable, or circumvent the license key functionality
+in the software, and you may not remove or obscure any functionality in the
+software that is protected by the license key.
+
+You may not alter, remove, or obscure any licensing, copyright, or other notices
+of the licensor in the software. Any use of the licensor's trademarks is subject
+to applicable law.
+
+Patents
+
+The licensor grants you a license, under any patent claims the licensor can
+license, or becomes able to license, to make, have made, use, sell, offer for
+sale, import and have imported the software, in each case subject to the
+limitations and conditions in this license. This license does not cover any
+patent claims that you cause to be infringed by modifications or additions to the
+software. If you or your company make any written claim that the software
+infringes or contributes to infringement of any patent, your patent license for
+the software granted under these terms ends immediately. If your company makes
+such a claim, your patent license ends immediately for work on behalf of your
+company.
+
+Notices
+
+You must ensure that anyone who gets a copy of any part of the software from you
+also gets a copy of these terms.
+
+If you modify the software, you must include in any modified copies of the
+software prominent notices stating that you have modified the software.
+
+No Other Rights
+
+These terms do not imply any licenses other than those expressly granted in
+these terms.
+
+Termination
+
+If you use the software in violation of these terms, such use is not licensed,
+and your licenses will automatically terminate. If the licensor provides you with
+a notice of your violation, and you cease all violation of this license no later
+than 30 days after you receive that notice, your licenses will be reinstated
+retroactively. However, if you violate these terms after such reinstatement, any
+additional violation of these terms will cause your licenses to terminate
+automatically and permanently.
+
+No Liability
+
+As far as the law allows, the software comes as is, without any warranty or
+condition, and the licensor will not be liable to you for any damages arising out
+of these terms or the use or nature of the software, under any kind of legal
+claim.
+
+Definitions
+
+The licensor is the entity offering these terms, and the software is the
+software the licensor makes available under these terms, including any portion
+of it.
+
+you refers to the individual or entity agreeing to these terms.
+
+your company is any legal entity, sole proprietorship, or other kind of
+organization that you work for, plus all organizations that have control over,
+are under the control of, or are under common control with that organization.
+control means ownership of substantially all the assets of an entity, or the
+power to direct its management and policies by vote, contract, or otherwise.
+Control can be direct or indirect.
+
+your licenses are all the licenses granted to you for the software under these
+terms.
+
+use means anything you do with the software requiring one of your licenses.
+
+trademark means trademarks, service marks, and similar rights.
--- a/packages/ruby/README.md
+++ b/packages/ruby/README.md
@@ -0,0 +1,467 @@
+# Kreuzberg for Ruby
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
+  <a href="https://github.com/kreuzberg-dev/alef">
+    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+  </a>
+  <!-- Language Bindings -->
+  <a href="https://crates.io/crates/kreuzberg">
+    <img src="https://img.shields.io/crates/v/kreuzberg?label=Rust&color=007ec6" alt="Rust">
+  </a>
+  <a href="https://pypi.org/project/kreuzberg/">
+    <img src="https://img.shields.io/pypi/v/kreuzberg?label=Python&color=007ec6" alt="Python">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/node">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/node?label=Node.js&color=007ec6" alt="Node.js">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/wasm">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM&color=007ec6" alt="WASM">
+  </a>
+  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg">
+    <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/tree/main/packages/go/v5">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v5*" alt="Go">
+  </a>
+  <a href="https://www.nuget.org/packages/Kreuzberg/">
+    <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">
+  </a>
+  <a href="https://packagist.org/packages/kreuzberg/kreuzberg">
+    <img src="https://img.shields.io/packagist/v/kreuzberg/kreuzberg?label=PHP&color=007ec6" alt="PHP">
+  </a>
+  <a href="https://rubygems.org/gems/kreuzberg">
+    <img src="https://img.shields.io/gem/v/kreuzberg?label=Ruby&color=007ec6" alt="Ruby">
+  </a>
+  <a href="https://hex.pm/packages/kreuzberg">
+    <img src="https://img.shields.io/hexpm/v/kreuzberg?label=Elixir&color=007ec6" alt="Elixir">
+  </a>
+  <a href="https://kreuzberg-dev.r-universe.dev/kreuzberg">
+    <img src="https://img.shields.io/badge/R-kreuzberg-007ec6" alt="R">
+  </a>
+  <a href="https://pub.dev/packages/kreuzberg">
+    <img src="https://img.shields.io/pub/v/kreuzberg?label=Dart&color=007ec6" alt="Dart">
+  </a>
+  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg-android">
+    <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg-android?label=Kotlin&color=007ec6" alt="Kotlin">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/tree/main/packages/swift">
+    <img src="https://img.shields.io/badge/Swift-SPM-007ec6" alt="Swift">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/tree/main/packages/zig">
+    <img src="https://img.shields.io/badge/Zig-package-007ec6" alt="Zig">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
+    <img src="https://img.shields.io/badge/C-FFI-007ec6" alt="C FFI">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
+    <img src="https://img.shields.io/badge/Docker-ghcr.io-007ec6?logo=docker&logoColor=white" alt="Docker">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/charts%2Fkreuzberg">
+    <img src="https://img.shields.io/badge/Helm-ghcr.io-007ec6?logo=helm&logoColor=white" alt="Helm">
+  </a>
+
+  <!-- Project Info -->
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-Elastic--2.0-007ec6" alt="License">
+  </a>
+  <a href="https://docs.kreuzberg.dev">
+    <img src="https://img.shields.io/badge/Docs-kreuzberg-007ec6" alt="Documentation">
+  </a>
+  <a href="https://huggingface.co/Kreuzberg">
+    <img src="https://img.shields.io/badge/Hugging%20Face-Kreuzberg-007ec6" alt="Hugging Face">
+  </a>
+</div>
+
+<div align="center" style="margin: 24px 0 0;">
+  <a href="https://kreuzberg.dev">
+    <img alt="Kreuzberg" src="https://github.com/user-attachments/assets/419fc06c-8313-4324-b159-4b4d3cfce5c0" />
+  </a>
+</div>
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 12px; justify-content: center; margin: 28px 0 24px;">
+  <a href="https://discord.gg/xt9WY3GnKR">
+    <img height="22" src="https://img.shields.io/badge/Discord-Chat-007ec6?logo=discord&logoColor=white" alt="Join Discord">
+  </a>
+  <a href="https://docs.kreuzberg.dev/demo.html">
+    <img height="22" src="https://img.shields.io/badge/Live%20Demo-Open-007ec6?logo=webassembly&logoColor=white" alt="Live Demo">
+  </a>
+</div>
+
+Extract text, tables, images, and metadata from 90+ file formats and 300+ programming languages including PDF, Office documents, and images. Ruby bindings with idiomatic Ruby API and native performance.
+
+## What This Package Provides
+
+- **Ruby-native extraction** — idiomatic Ruby objects over the shared Rust document engine.
+- **Structured results** — text, tables, images, metadata, language detection, chunks, and warnings.
+- **OCR support** — Tesseract and PaddleOCR through the same configuration model as other bindings.
+- **Cross-binding parity** — output matches the Python, Node.js, Go, Java, .NET, PHP, Elixir, R, Dart, Swift, Zig, WASM, and C FFI packages.
+
+## Installation
+
+Add to your Gemfile:
+
+```ruby
+gem 'kreuzberg'
+```
+
+Then execute:
+
+```bash
+bundle install
+```
+
+Or install it directly:
+
+```bash
+gem install kreuzberg
+```
+
+## Quick Start
+
+### Basic Usage
+
+```ruby
+require 'kreuzberg'
+
+# Simple synchronous extraction
+result = Kreuzberg.extract_file("document.pdf")
+puts result.content
+```
+
+### Async Extraction
+
+```ruby
+require 'kreuzberg'
+
+# Using Fiber for concurrency (Ruby 3.0+)
+Fiber.new do
+  result = Kreuzberg.extract_file_async("document.pdf")
+  puts result.content
+end.resume
+```
+
+### Batch Processing
+
+```ruby
+require 'kreuzberg'
+
+files = ["doc1.pdf", "doc2.docx", "doc3.xlsx"]
+
+results = files.map { |file| Kreuzberg.extract_file(file) }
+
+results.each do |result|
+  puts "Content length: #{result.content.length}"
+end
+```
+
+## Configuration
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  use_cache: true,
+  enable_quality_processing: true,
+  ocr: Kreuzberg::OcrConfig.new(
+    backend: 'tesseract',
+    language: 'eng'
+  )
+)
+
+result = Kreuzberg.extract_file("document.pdf", config: config)
+puts result.content
+```
+
+## OCR Support
+
+### Tesseract Configuration
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  ocr: Kreuzberg::OcrConfig.new(
+    backend: 'tesseract',
+    language: 'eng',
+    tesseract_config: Kreuzberg::TesseractConfig.new(
+      psm: 6,
+      enable_table_detection: true
+    )
+  )
+)
+
+result = Kreuzberg.extract_file("scanned.pdf", config: config)
+puts result.content
+```
+
+## Table Extraction
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  ocr: Kreuzberg::OcrConfig.new(
+    backend: 'tesseract',
+    tesseract_config: Kreuzberg::TesseractConfig.new(
+      enable_table_detection: true
+    )
+  )
+)
+
+result = Kreuzberg.extract_file("invoice.pdf", config: config)
+
+result.tables.each_with_index do |table, index|
+  puts "Table #{index}:"
+  puts table.markdown
+end
+```
+
+## Metadata Extraction
+
+```ruby
+require 'kreuzberg'
+
+result = Kreuzberg.extract_file("document.pdf")
+
+# PDF metadata
+if result.metadata[:pdf]
+  pdf_meta = result.metadata[:pdf]
+  puts "Title: #{pdf_meta[:title]}"
+  puts "Author: #{pdf_meta[:author]}"
+  puts "Pages: #{pdf_meta[:page_count]}"
+end
+
+# Detected languages
+puts "Languages: #{result.detected_languages}"
+
+# Images
+if result.images
+  puts "Images found: #{result.images.count}"
+end
+```
+
+## Text Chunking
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  chunking: Kreuzberg::ChunkingConfig.new(
+    max_chars: 1000,
+    max_overlap: 200
+  )
+)
+
+result = Kreuzberg.extract_file("long_document.pdf", config: config)
+
+result.chunks.each_with_index do |chunk, index|
+  puts "Chunk #{index}: #{chunk.length} characters"
+end
+```
+
+## Password-Protected PDFs
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  pdf_options: Kreuzberg::PdfConfig.new(
+    passwords: ["password1", "password2"]
+  )
+)
+
+result = Kreuzberg.extract_file("protected.pdf", config: config)
+puts result.content
+```
+
+## Language Detection
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  language_detection: Kreuzberg::LanguageDetectionConfig.new(
+    enabled: true
+  )
+)
+
+result = Kreuzberg.extract_file("multilingual.pdf", config: config)
+puts "Detected languages: #{result.detected_languages}"
+```
+
+## API Reference
+
+### Main Methods
+
+- `Kreuzberg.extract_file(path, config: nil)` – Extract from file
+- `Kreuzberg.extract_file_async(path, config: nil)` – Async extraction
+- `Kreuzberg.extract_bytes(data, mime_type, config: nil)` – Extract from bytes
+- `Kreuzberg.batch_extract_files(paths, config: nil)` – Batch processing
+
+### Configuration Classes
+
+- `ExtractionConfig` – Main configuration
+- `OcrConfig` – OCR settings
+- `TesseractConfig` – Tesseract-specific options
+- `ChunkingConfig` – Text chunking settings
+- `PdfConfig` – PDF-specific options
+- `LanguageDetectionConfig` – Language detection settings
+
+### Result Object
+
+- `content` – Extracted text
+- `metadata` – File metadata as Hash
+- `tables` – Array of ExtractedTable objects
+- `detected_languages` – Array of language codes
+- `chunks` – Array of text chunks
+- `images` – Array of extracted images (if enabled)
+
+## System Requirements
+
+### Ruby Version
+
+- **Ruby 3.2.0 or higher** (including Ruby 4.x)
+- Ruby 4.0+ is fully supported with no code changes required
+- Magnus bindings compile successfully on all supported Ruby versions
+
+### Required
+
+- Rust toolchain (for native extension compilation)
+
+### Optional
+
+```bash
+# Tesseract OCR
+brew install tesseract          # macOS
+sudo apt-get install tesseract-ocr  # Ubuntu/Debian
+```
+
+### Ruby 4.0 Compatibility
+
+Kreuzberg is fully compatible with Ruby 4.0 (released December 25, 2025) and later. Key Ruby 4.0 features that work seamlessly:
+
+- **Ruby Box** - Improved memory efficiency and performance
+- **ZJIT Compiler** - Enhanced JIT compilation for faster execution
+- **Ractor Improvements** - Better multi-threaded document processing
+- **Set Promoted to Core** - No changes needed for Kreuzberg
+
+All tests pass with Ruby 4.0.1 with 100% compatibility. The gem compiles without any breaking changes.
+
+## Development
+
+Clone and setup:
+
+```bash
+git clone https://github.com/kreuzberg-dev/kreuzberg.git
+cd kreuzberg
+bundle install
+```
+
+Run tests:
+
+```bash
+rake test
+```
+
+## Troubleshooting
+
+### Native extension compilation error
+
+Ensure build tools are installed:
+
+```bash
+# macOS
+xcode-select --install
+
+# Ubuntu/Debian
+sudo apt-get install build-essential ruby-dev
+
+# Windows (via RubyInstaller)
+ridk install
+```
+
+### "Could not find Kreuzberg"
+
+Reinstall the gem:
+
+```bash
+gem uninstall kreuzberg
+gem install kreuzberg --no-document
+```
+
+### OCR not working
+
+Verify Tesseract is installed:
+
+```bash
+tesseract --version
+```
+
+## Examples
+
+### Process Directory of PDFs
+
+```ruby
+require 'kreuzberg'
+require 'pathname'
+
+Dir.glob("documents/*.pdf").each do |file|
+  puts "Processing: #{file}"
+  result = Kreuzberg.extract_file(file)
+  puts "  Content length: #{result.content.length}"
+  puts "  Language: #{result.detected_languages}"
+end
+```
+
+### Extract and Parse Structured Data
+
+```ruby
+require 'kreuzberg'
+require 'json'
+
+result = Kreuzberg.extract_file("data.pdf")
+
+# Parse content as JSON (if applicable)
+begin
+  data = JSON.parse(result.content)
+  puts "Parsed data: #{data}"
+rescue JSON::ParserError
+  puts "Content is not JSON"
+end
+```
+
+### Save Extracted Images
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::ExtractionConfig.new(
+  images: Kreuzberg::ImageExtractionConfig.new(
+    extract_images: true
+  )
+)
+
+result = Kreuzberg.extract_file("document.pdf", config: config)
+
+result.images&.each_with_index do |image, index|
+  File.write("image_#{index}.png", image.data)
+end
+```
+
+## Documentation
+
+For comprehensive documentation, visit [https://kreuzberg.dev](https://kreuzberg.dev)
+
+## Part of Kreuzberg.dev
+
+- [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
+- [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
+- [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
+- [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
+- [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces this README and all per-language bindings.
+- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
+
+## License
+
+Elastic-2.0 License - see [LICENSE](../../LICENSE) for details.
--- a/packages/ruby/Rakefile
+++ b/packages/ruby/Rakefile
@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require "bundler"
+Bundler::GemHelper.install_tasks name: "kreuzberg"
+require "rake/extensiontask"
+require "rspec/core/rake_task"
+
+GEM_ROOT = __dir__
+GEMSPEC = Gem::Specification.load(File.expand_path("kreuzberg.gemspec", GEM_ROOT))
+
+Rake::ExtensionTask.new("kreuzberg-rb", GEMSPEC) do |ext|
+  ext.lib_dir = "lib"
+  ext.ext_dir = "ext/kreuzberg_rb/native"
+  ext.source_pattern = "*.{}"
+  ext.platform = "ruby"
+end
+
+RSpec::Core::RakeTask.new(:spec)
+
+task spec: :compile
+task default: :spec
--- a/packages/ruby/Steepfile
+++ b/packages/ruby/Steepfile
@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+target :lib do
+  signature "sig"
+  check "lib"
+  # The generated `lib/kreuzberg/native.rb` carries inline Sorbet
+  # `sig { ... }` blocks on tagged-enum variant Data classes. Sorbet's runtime
+  # provides those via `extend T::Sig`, but Steep does not understand the
+  # extension (it relies on RBS, not Sorbet sigs) and reports
+  # `Type `self` does not have method `sig`` on every block. RBS coverage
+  # for the same surface lives in `sig/types.rbs`, so we steer Steep to the
+  # RBS file by ignoring the .rb.
+  ignore "lib/kreuzberg/native.rb"
+end
--- a/packages/ruby/ext/kreuzberg_rb/extconf.rb
+++ b/packages/ruby/ext/kreuzberg_rb/extconf.rb
@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require "mkmf"
+require "rb_sys/mkmf"
+
+default_profile = ENV.fetch("CARGO_PROFILE", "release")
+
+create_rust_makefile("kreuzberg_rb") do |config|
+  config.profile = default_profile.to_sym
+  config.ext_dir = "native"
+end
--- a/packages/ruby/ext/kreuzberg_rb/native/Cargo.lock
+++ b/packages/ruby/ext/kreuzberg_rb/native/Cargo.lock
--- a/packages/ruby/ext/kreuzberg_rb/native/Cargo.toml
+++ b/packages/ruby/ext/kreuzberg_rb/native/Cargo.toml
@@ -0,0 +1,25 @@
+[package]
+name = "kreuzberg-rb"
+version = "5.0.0-rc.3"
+edition = "2024"
+license = "Elastic-2.0"
+description = "High-performance document intelligence library"
+readme = false
+keywords = ["document", "extraction", "ocr", "pdf", "text"]
+categories = ["text-processing"]
+
+[package.metadata.cargo-machete]
+ignored = ["tokio", "async-trait"]
+
+[lib]
+name = "kreuzberg_rb"
+path = "../src/lib.rs"
+crate-type = ["cdylib"]
+
+[dependencies]
+async-trait = "0.1"
+kreuzberg = { version = "5.0.0-rc.3", path = "../../../../../crates/kreuzberg", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "mcp", "liter-llm", "quality"] }
+magnus = "0.8"
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+tokio = { version = "1", features = ["rt-multi-thread"] }
--- a/packages/ruby/ext/kreuzberg_rb/native/extconf.rb
+++ b/packages/ruby/ext/kreuzberg_rb/native/extconf.rb
@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require "mkmf"
+require "rb_sys/mkmf"
+
+default_profile = ENV.fetch("CARGO_PROFILE", "release")
+
+create_rust_makefile("kreuzberg_rb") do |config|
+  config.profile = default_profile.to_sym
+  config.ext_dir = "native"
+end
--- a/packages/ruby/ext/kreuzberg_rb/src/lib.rs
+++ b/packages/ruby/ext/kreuzberg_rb/src/lib.rs
--- a/packages/ruby/kreuzberg.gemspec
+++ b/packages/ruby/kreuzberg.gemspec
@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+Gem::Specification.new do |spec|
+  spec.name = "kreuzberg"
+  spec.version = "5.0.0.pre.rc.3"
+  spec.authors       = ["Na'aman Hirschfeld <naaman@kreuzberg.dev>"]
+  spec.summary       = "High-performance document intelligence library"
+  spec.description   = "High-performance document intelligence library"
+  spec.homepage      = "https://github.com/kreuzberg-dev/kreuzberg"
+  spec.license       = "Elastic-2.0"
+  spec.required_ruby_version = ">= 3.2.0"
+  spec.metadata["keywords"] = %w[document extraction ocr pdf text].join(",")
+  spec.metadata["rubygems_mfa_required"] = "true"
+
+  spec.files         = Dir.glob(%w[README* LICENSE* lib/**/* ext/**/* sig/**/* Steepfile]).select { |f| File.file?(f) }.reject { |f| f.include?("/native/target/") || f.include?("/native/tmp/") }
+  spec.require_paths = ["lib"]
+  spec.extensions    = ["ext/kreuzberg_rb/native/extconf.rb"]
+
+  spec.add_dependency "rb_sys", "~> 0.9"
+  spec.add_dependency "sorbet-runtime", "~> 0.5"
+end
--- a/packages/ruby/lib/kreuzberg.rb
+++ b/packages/ruby/lib/kreuzberg.rb
@@ -0,0 +1,13 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
+# frozen_string_literal: true
+
+require_relative "kreuzberg/version"
+require_relative "kreuzberg/native"
+
+module Kreuzberg
+  # Re-export all types and functions from native extension
+end
--- a/packages/ruby/lib/kreuzberg/native.rb
+++ b/packages/ruby/lib/kreuzberg/native.rb
--- a/packages/ruby/lib/kreuzberg/version.rb
+++ b/packages/ruby/lib/kreuzberg/version.rb
@@ -0,0 +1,10 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# Issues & docs: https://github.com/kreuzberg-dev/alef
+# frozen_string_literal: true
+
+module Kreuzberg
+  VERSION = "5.0.0.pre.rc.3"
+end
--- a/packages/ruby/sig/types.rbs
+++ b/packages/ruby/sig/types.rbs