kreuzberg 4.3.5-aarch64-linux

data/Gemfile.lock

@@ -0,0 +1,260 @@
+PATH
+  remote: .
+  specs:
+    kreuzberg (4.3.5)
+      rb_sys (~> 0.9.119)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (8.1.2)
+      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 (4.0.1)
+    byebug (13.0.0)
+      reline (>= 0.6.0)
+    coderay (1.1.3)
+    concurrent-ruby (1.3.6)
+    connection_pool (3.0.2)
+    csv (3.3.5)
+    diff-lcs (1.6.2)
+    drb (2.2.3)
+    ffi (1.17.3)
+    ffi (1.17.3-aarch64-linux-gnu)
+    ffi (1.17.3-aarch64-linux-musl)
+    ffi (1.17.3-arm-linux-gnu)
+    ffi (1.17.3-arm-linux-musl)
+    ffi (1.17.3-arm64-darwin)
+    ffi (1.17.3-x86-linux-gnu)
+    ffi (1.17.3-x86-linux-musl)
+    ffi (1.17.3-x86_64-darwin)
+    ffi (1.17.3-x86_64-linux-gnu)
+    ffi (1.17.3-x86_64-linux-musl)
+    fileutils (1.8.0)
+    i18n (1.14.8)
+      concurrent-ruby (~> 1.0)
+    io-console (0.8.2)
+    json (2.18.1)
+    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)
+    method_source (1.1.0)
+    minitest (6.0.1)
+      prism (~> 1.5)
+    mutex_m (0.3.0)
+    parallel (1.27.0)
+    parser (3.3.10.2)
+      ast (~> 2.4.1)
+      racc
+    prism (1.9.0)
+    pry (0.16.0)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+      reline (>= 0.6.0)
+    pry-byebug (3.12.0)
+      byebug (~> 13.0)
+      pry (>= 0.13, < 0.17)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    rake (13.3.1)
+    rake-compiler (1.3.1)
+      rake
+    rake-compiler-dock (1.11.0)
+    rb-fsevent (0.11.2)
+    rb-inotify (0.11.1)
+      ffi (~> 1.0)
+    rb_sys (0.9.124)
+      rake-compiler-dock (= 1.11.0)
+    rbs (3.10.3)
+      logger
+      tsort
+    regexp_parser (2.11.3)
+    reline (0.6.3)
+      io-console (~> 0.5)
+    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 (3.13.7)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.7)
+    rubocop (1.84.2)
+      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 (1.49.0)
+      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 (0.6.12942)
+    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 (3.1.7)
+    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)
+    yard (0.9.38)
+
+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
+  x86_64-linux-gnu
+  x86_64-linux-musl
+
+DEPENDENCIES
+  bundler (~> 4.0)
+  kreuzberg!
+  pry (~> 0.14)
+  pry-byebug (~> 3.10)
+  rake (~> 13.0)
+  rake-compiler (~> 1.2)
+  rbs (~> 3.0)
+  rspec (~> 3.12)
+  rubocop (~> 1.66)
+  rubocop-performance (~> 1.21)
+  rubocop-rspec (~> 3.0)
+  sorbet-runtime (~> 0.5)
+  steep (~> 1.8)
+  yard (~> 0.9)
+
+CHECKSUMS
+  activesupport (8.1.2) sha256=88842578ccd0d40f658289b0e8c842acfe9af751afee2e0744a7873f50b6fdae
+  ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
+  base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
+  bigdecimal (4.0.1) sha256=8b07d3d065a9f921c80ceaea7c9d4ae596697295b584c296fe599dd0ad01c4a7
+  byebug (13.0.0) sha256=d2263efe751941ca520fa29744b71972d39cbc41839496706f5d9b22e92ae05d
+  coderay (1.1.3) sha256=dc530018a4684512f8f38143cd2a096c9f02a1fc2459edcfe534787a7fc77d4b
+  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 (1.17.3) sha256=0e9f39f7bb3934f77ad6feab49662be77e87eedcdeb2a3f5c0234c2938563d4c
+  ffi (1.17.3-aarch64-linux-gnu) sha256=28ad573df26560f0aedd8a90c3371279a0b2bd0b4e834b16a2baa10bd7a97068
+  ffi (1.17.3-aarch64-linux-musl) sha256=020b33b76775b1abacc3b7d86b287cef3251f66d747092deec592c7f5df764b2
+  ffi (1.17.3-arm-linux-gnu) sha256=5bd4cea83b68b5ec0037f99c57d5ce2dd5aa438f35decc5ef68a7d085c785668
+  ffi (1.17.3-arm-linux-musl) sha256=0d7626bb96265f9af78afa33e267d71cfef9d9a8eb8f5525344f8da6c7d76053
+  ffi (1.17.3-arm64-darwin) sha256=0c690555d4cee17a7f07c04d59df39b2fba74ec440b19da1f685c6579bb0717f
+  ffi (1.17.3-x86-linux-gnu) sha256=868a88fcaf5186c3a46b7c7c2b2c34550e1e61a405670ab23f5b6c9971529089
+  ffi (1.17.3-x86-linux-musl) sha256=f0286aa6ef40605cf586e61406c446de34397b85dbb08cc99fdaddaef8343945
+  ffi (1.17.3-x86_64-darwin) sha256=1f211811eb5cfaa25998322cdd92ab104bfbd26d1c4c08471599c511f2c00bb5
+  ffi (1.17.3-x86_64-linux-gnu) sha256=3746b01f677aae7b16dc1acb7cb3cc17b3e35bdae7676a3f568153fb0e2c887f
+  ffi (1.17.3-x86_64-linux-musl) sha256=086b221c3a68320b7564066f46fed23449a44f7a1935f1fe5a245bd89d9aea56
+  fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
+  i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
+  io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
+  json (2.18.1) sha256=fe112755501b8d0466b5ada6cf50c8c3f41e897fa128ac5d263ec09eedc9f986
+  kreuzberg (4.3.5)
+  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
+  method_source (1.1.0) sha256=181301c9c45b731b4769bc81e8860e72f9161ad7d66dd99103c9ab84f560f5c5
+  minitest (6.0.1) sha256=7854c74f48e2e975969062833adc4013f249a4b212f5e7b9d5c040bf838d54bb
+  mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
+  parallel (1.27.0) sha256=4ac151e1806b755fb4e2dc2332cbf0e54f2e24ba821ff2d3dcf86bf6dc4ae130
+  parser (3.3.10.2) sha256=6f60c84aa4bdcedb6d1a2434b738fe8a8136807b6adc8f7f53b97da9bc4e9357
+  prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
+  pry (0.16.0) sha256=d76c69065698ed1f85e717bd33d7942c38a50868f6b0673c636192b3d1b6054e
+  pry-byebug (3.12.0) sha256=594e094ae8a8390a7ad4c7b36ae36e13304ed02664c67417d108dc5f7213d1b7
+  racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
+  rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
+  rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
+  rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
+  rake-compiler-dock (1.11.0) sha256=eab51f2cd533eb35cea6b624a75281f047123e70a64c58b607471bb49428f8c2
+  rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
+  rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
+  rb_sys (0.9.124) sha256=513476557b12eaf73764b3da9f8746024558fe8699bda785fb548c9aa3877ae7
+  rbs (3.10.3) sha256=70627f3919016134d554e6c99195552ae3ef6020fe034c8e983facc9c192daa6
+  regexp_parser (2.11.3) sha256=ca13f381a173b7a93450e53459075c9b76a10433caadcb2f1180f2c741fc55a4
+  reline (0.6.3) sha256=1198b04973565b36ec0f11542ab3f5cfeeec34823f4e54cebde90968092b1835
+  rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
+  rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
+  rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
+  rspec-mocks (3.13.7) sha256=0979034e64b1d7a838aaaddf12bf065ea4dc40ef3d4c39f01f93ae2c66c62b1c
+  rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
+  rubocop (1.84.2) sha256=5692cea54168f3dc8cb79a6fe95c5424b7ea893c707ad7a4307b0585e88dbf5f
+  rubocop-ast (1.49.0) sha256=49c3676d3123a0923d333e20c6c2dbaaae2d2287b475273fddee0c61da9f71fd
+  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 (0.6.12942) sha256=967bda04814d234e4239c4f883c1d0ee6de3e47bf8bafd2c0cc30d18df2ddd3a
+  steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
+  strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
+  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
+  yard (0.9.38) sha256=721fb82afb10532aa49860655f6cc2eaa7130889df291b052e1e6b268283010f
+
+BUNDLED WITH
+  4.0.5

data/README.md

@@ -0,0 +1,399 @@
+# Ruby
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
+  <!-- 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://hex.pm/packages/kreuzberg">
+    <img src="https://img.shields.io/hexpm/v/kreuzberg?label=Elixir&color=007ec6" alt="Elixir">
+  </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/releases">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.3.5" 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://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
+    <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
+  </a>
+
+  <!-- Project Info -->
+  <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License">
+  </a>
+  <a href="https://docs.kreuzberg.dev">
+    <img src="https://img.shields.io/badge/docs-kreuzberg.dev-blue" alt="Documentation">
+  </a>
+</div>
+
+<img width="1128" height="191" alt="Banner2" src="https://github.com/user-attachments/assets/419fc06c-8313-4324-b159-4b4d3cfce5c0" />
+
+<div align="center" style="margin-top: 20px;">
+  <a href="https://discord.gg/xt9WY3GnKR">
+      <img height="22" src="https://img.shields.io/badge/Discord-Join%20our%20community-7289da?logo=discord&logoColor=white" alt="Discord">
+  </a>
+</div>
+
+
+Extract text, tables, images, and metadata from 75+ file formats including PDF, Office documents, and images. Ruby bindings with idiomatic Ruby API and native performance.
+
+
+## Installation
+
+### Package Installation
+
+
+Install via one of the supported package managers:
+
+
+
+**gem:**
+```bash
+gem install kreuzberg
+```
+
+
+
+
+**Bundler:**
+```ruby
+gem 'kreuzberg'
+```
+
+
+
+
+
+### System Requirements
+
+- **Ruby 3.2.0 or higher** required (including Ruby 4.x)
+- Ruby 4.0+ is fully supported with no code changes required
+- Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.24+ for embeddings support
+- Optional: [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) for OCR functionality
+
+**Ruby 4.0 Compatibility:** Kreuzberg is fully compatible with Ruby 4.0 (released December 25, 2025) and all Ruby 4.x versions. All tests pass with 100% compatibility. The gem compiles without any breaking changes. Key Ruby 4.0 features like Ruby Box, ZJIT compiler, and Ractor improvements work seamlessly with Kreuzberg.
+
+
+
+## Quick Start
+
+### Basic Extraction
+
+Extract text, metadata, and structure from any supported document format:
+
+```ruby
+require 'kreuzberg'
+
+result = Kreuzberg.extract_file_sync('document.pdf')
+
+puts "Content:"
+puts result.content
+
+puts "\nMetadata:"
+puts "Title: #{result.metadata&.dig('title')}"
+puts "Author: #{result.metadata&.dig('author')}"
+
+puts "\nTables found: #{result.tables.length}"
+puts "Images found: #{result.images.length}"
+```
+
+
+### Common Use Cases
+
+#### Extract with Custom Configuration
+
+Most use cases benefit from configuration to control extraction behavior:
+
+
+**With OCR (for scanned documents):**
+
+```ruby
+require 'kreuzberg'
+
+ocr_config = Kreuzberg::Config::OCR.new(
+  backend: 'tesseract',
+  language: 'eng'
+)
+
+config = Kreuzberg::Config::Extraction.new(ocr: ocr_config)
+result = Kreuzberg.extract_file_sync('scanned.pdf', config: config)
+
+puts "Extracted text from scanned document:"
+puts result.content
+puts "Used OCR backend: tesseract"
+```
+
+
+
+
+#### Table Extraction
+
+
+See [Table Extraction Guide](https://kreuzberg.dev/features/table-extraction/) for detailed examples.
+
+
+
+#### Processing Multiple Files
+
+
+```ruby
+require 'kreuzberg'
+
+puts "Kreuzberg version: #{Kreuzberg::VERSION}"
+puts "FFI bindings loaded successfully"
+
+result = Kreuzberg.extract_file_sync('sample.pdf')
+puts "Installation verified! Extracted #{result.content.length} characters"
+```
+
+
+
+
+
+#### Async Processing
+
+For non-blocking document processing:
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::Config::Extraction.new(
+  use_cache: true,
+  enable_quality_processing: true
+)
+
+result = Kreuzberg.extract_file_sync('contract.pdf', config: config)
+
+puts "Extracted #{result.content.length} characters"
+puts "Quality score: #{result.metadata&.dig('quality_score')}"
+puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
+```
+
+
+
+
+
+
+### Next Steps
+
+- **[Installation Guide](https://kreuzberg.dev/getting-started/installation/)** - Platform-specific setup
+- **[API Documentation](https://kreuzberg.dev/api/)** - Complete API reference
+- **[Examples & Guides](https://kreuzberg.dev/guides/)** - Full code examples and usage guides
+- **[Configuration Guide](https://kreuzberg.dev/guides/configuration/)** - Advanced configuration options
+
+
+
+## Features
+
+### Supported File Formats (75+)
+
+75+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+
+#### Office Documents
+
+| Category | Formats | Capabilities |
+|----------|---------|--------------|
+| **Word Processing** | `.docx`, `.odt` | Full text, tables, images, metadata, styles |
+| **Spreadsheets** | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.ods` | Sheet data, formulas, cell metadata, charts |
+| **Presentations** | `.pptx`, `.ppt`, `.ppsx` | Slides, speaker notes, images, metadata |
+| **PDF** | `.pdf` | Text, tables, images, metadata, OCR support |
+| **eBooks** | `.epub`, `.fb2` | Chapters, metadata, embedded resources |
+
+#### Images (OCR-Enabled)
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Raster** | `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`, `.tiff`, `.tif` | OCR, table detection, EXIF metadata, dimensions, color space |
+| **Advanced** | `.jp2`, `.jpx`, `.jpm`, `.mj2`, `.jbig2`, `.jb2`, `.pnm`, `.pbm`, `.pgm`, `.ppm` | OCR via hayro-jpeg2000 (pure Rust decoder), JBIG2 support, table detection, format-specific metadata |
+| **Vector** | `.svg` | DOM parsing, embedded text, graphics metadata |
+
+#### Web & Data
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Markup** | `.html`, `.htm`, `.xhtml`, `.xml`, `.svg` | DOM parsing, metadata (Open Graph, Twitter Card), link extraction |
+| **Structured Data** | `.json`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv` | Schema detection, nested structures, validation |
+| **Text & Markdown** | `.txt`, `.md`, `.markdown`, `.djot`, `.rst`, `.org`, `.rtf` | CommonMark, GFM, Djot, reStructuredText, Org Mode |
+
+#### Email & Archives
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Email** | `.eml`, `.msg` | Headers, body (HTML/plain), attachments, threading |
+| **Archives** | `.zip`, `.tar`, `.tgz`, `.gz`, `.7z` | File listing, nested archives, metadata |
+
+#### Academic & Scientific
+
+| Category | Formats | Features |
+|----------|---------|----------|
+| **Citations** | `.bib`, `.biblatex`, `.ris`, `.nbib`, `.enw`, `.csl` | Structured parsing: RIS (structured), PubMed/MEDLINE, EndNote XML (structured), BibTeX, CSL JSON |
+| **Scientific** | `.tex`, `.latex`, `.typst`, `.jats`, `.ipynb`, `.docbook` | LaTeX, Jupyter notebooks, PubMed JATS |
+| **Documentation** | `.opml`, `.pod`, `.mdoc`, `.troff` | Technical documentation formats |
+
+**[Complete Format Reference](https://kreuzberg.dev/reference/formats/)**
+
+### Key Capabilities
+
+- **Text Extraction** - Extract all text content with position and formatting information
+- **Metadata Extraction** - Retrieve document properties, creation date, author, etc.
+- **Table Extraction** - Parse tables with structure and cell content preservation
+- **Image Extraction** - Extract embedded images and render page previews
+- **OCR Support** - Integrate multiple OCR backends for scanned documents
+
+- **Async/Await** - Non-blocking document processing with concurrent operations
+
+
+- **Plugin System** - Extensible post-processing for custom text transformation
+
+
+- **Embeddings** - Generate vector embeddings using ONNX Runtime models
+
+- **Batch Processing** - Efficiently process multiple documents in parallel
+- **Memory Efficient** - Stream large files without loading entirely into memory
+- **Language Detection** - Detect and support multiple languages in documents
+- **Configuration** - Fine-grained control over extraction behavior
+
+### Performance Characteristics
+
+| Format | Speed | Memory | Notes |
+|--------|-------|--------|-------|
+| **PDF (text)** | 10-100 MB/s | ~50MB per doc | Fastest extraction |
+| **Office docs** | 20-200 MB/s | ~100MB per doc | DOCX, XLSX, PPTX |
+| **Images (OCR)** | 1-5 MB/s | Variable | Depends on OCR backend |
+| **Archives** | 5-50 MB/s | ~200MB per doc | ZIP, TAR, etc. |
+| **Web formats** | 50-200 MB/s | Streaming | HTML, XML, JSON |
+
+
+
+## OCR Support
+
+Kreuzberg supports multiple OCR backends for extracting text from scanned documents and images:
+
+
+- **Tesseract**
+
+- **Paddleocr**
+
+
+### OCR Configuration Example
+
+```ruby
+require 'kreuzberg'
+
+ocr_config = Kreuzberg::Config::OCR.new(
+  backend: 'tesseract',
+  language: 'eng'
+)
+
+config = Kreuzberg::Config::Extraction.new(ocr: ocr_config)
+result = Kreuzberg.extract_file_sync('scanned.pdf', config: config)
+
+puts "Extracted text from scanned document:"
+puts result.content
+puts "Used OCR backend: tesseract"
+```
+
+
+
+
+## Async Support
+
+This binding provides full async/await support for non-blocking document processing:
+
+```ruby
+require 'kreuzberg'
+
+config = Kreuzberg::Config::Extraction.new(
+  use_cache: true,
+  enable_quality_processing: true
+)
+
+result = Kreuzberg.extract_file_sync('contract.pdf', config: config)
+
+puts "Extracted #{result.content.length} characters"
+puts "Quality score: #{result.metadata&.dig('quality_score')}"
+puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
+```
+
+
+
+
+## Plugin System
+
+Kreuzberg supports extensible post-processing plugins for custom text transformation and filtering.
+
+For detailed plugin documentation, visit [Plugin System Guide](https://kreuzberg.dev/guides/plugins/).
+
+
+
+
+## Embeddings Support
+
+Generate vector embeddings for extracted text using the built-in ONNX Runtime support. Requires ONNX Runtime installation.
+
+**[Embeddings Guide](https://kreuzberg.dev/features/#embeddings)**
+
+
+
+## Batch Processing
+
+Process multiple documents efficiently:
+
+```ruby
+require 'kreuzberg'
+
+puts "Kreuzberg version: #{Kreuzberg::VERSION}"
+puts "FFI bindings loaded successfully"
+
+result = Kreuzberg.extract_file_sync('sample.pdf')
+puts "Installation verified! Extracted #{result.content.length} characters"
+```
+
+
+
+
+## Configuration
+
+For advanced configuration options including language detection, table extraction, OCR settings, and more:
+
+**[Configuration Guide](https://kreuzberg.dev/guides/configuration/)**
+
+## Documentation
+
+- **[Official Documentation](https://kreuzberg.dev/)**
+- **[API Reference](https://kreuzberg.dev/reference/api-ruby/)**
+- **[Examples & Guides](https://kreuzberg.dev/guides/)**
+
+## Contributing
+
+Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg-dev/kreuzberg/blob/main/CONTRIBUTING.md).
+
+## License
+
+MIT License - see LICENSE file for details.
+
+## Support
+
+- **Discord Community**: [Join our Discord](https://discord.gg/xt9WY3GnKR)
+- **GitHub Issues**: [Report bugs](https://github.com/kreuzberg-dev/kreuzberg/issues)
+- **Discussions**: [Ask questions](https://github.com/kreuzberg-dev/kreuzberg/discussions)

data/Rakefile

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rake/extensiontask'
+require 'rspec/core/rake_task'
+
+GEMSPEC = Gem::Specification.load(File.expand_path('kreuzberg.gemspec', __dir__))
+
+# Vendor kreuzberg core crates before compilation
+task :vendor do
+  vendor_script = File.expand_path('../../scripts/ci/ruby/vendor-kreuzberg-core.py', __dir__)
+  puts 'Vendoring kreuzberg core crates...'
+  sh "python3 #{vendor_script}"
+end
+
+Rake::ExtensionTask.new('kreuzberg_rb', GEMSPEC) do |ext|
+  ext.lib_dir = 'lib'
+  ext.ext_dir = 'ext/kreuzberg_rb'
+  ext.cross_compile = true
+  ext.cross_platform = %w[
+    x86_64-linux
+    aarch64-linux
+    x86_64-darwin
+    arm64-darwin
+    x64-mingw32
+    x64-mingw-ucrt
+  ]
+end
+
+RSpec::Core::RakeTask.new(:spec)
+
+task compile: :vendor
+task spec: :compile
+task default: :spec