kreuzberg 4.10.0.pre.rc.15 → 4.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 07df2bba324554ead6ac727a1d0c76ae7476b5081ee3c5a47d9d87d0d8f32805
-  data.tar.gz: 27027a158501e68a48af5bdbc2ae23d7c7725dd35b3e17ccc7188fadc9ed07d9
+  metadata.gz: bb319d70ecb6499c1e12ea466fc1aa015981245b2d50ad5d0c8955c96ee08db1
+  data.tar.gz: 4efade42bb03c57dca01ae5d4dd715a015a181201b6af84d942e60f09b4b4429
 SHA512:
-  metadata.gz: c07341b68985d5de1c7fec1a6e561bf0e83c51e4220f89a8507e87ddbcf89a4492cc3d897e672581645e375765df3eb2f4a8bbdca3686566fe04af206937db5d
-  data.tar.gz: a111f7a4e0c86b0dc85378be648aa8e053d1d12c9e8bf22336cdc21e1f0359c87b7e491170182507573ff127313a0f5a5b1116565780c9a341c2ea1cc7d71138
+  metadata.gz: ac7eb022d6a91fde12c92b2ce35f43019efbaa00e05c131b7674a3398ee9e2128685ec9eb38a964a1f2998a7a9b4f51911e71e71648e026233c85b7e778ae4ac
+  data.tar.gz: '09a7f3d76d19e3104c87a3d973e02defe87399f63bce223e87c3b2859f053cce0ad27bbeb9154492d589797ac3d713818d3bf243d268535b2e12707afa5a4c87'

data/README.md

@@ -0,0 +1,435 @@
+# 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-lts/releases">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg-lts?label=Go&color=007ec6&filter=v4.*" 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://kreuzberg-dev.r-universe.dev/kreuzberg">
+    <img src="https://img.shields.io/badge/R-kreuzberg-007ec6" alt="R">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/kreuzberg-lts/pkgs/container/kreuzberg">
+    <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
+  </a>
+  <a href="https://artifacthub.io/packages/search?repo=kreuzberg">
+    <img src="https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/kreuzberg" alt="Artifact Hub">
+  </a>
+
+  <!-- Project Info -->
+  <a href="https://github.com/kreuzberg-dev/kreuzberg-lts/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License">
+  </a>
+  <a href="https://docs.kreuzberg.dev">
+    <img src="https://img.shields.io/badge/docs-kreuzberg.dev-007ec6" alt="Documentation">
+  </a>
+  <a href="https://docs.kreuzberg.dev/demo.html">
+    <img src="https://img.shields.io/badge/%E2%96%B6%EF%B8%8F_Live_Demo-007ec6" alt="Live Demo">
+  </a>
+  <a href="https://huggingface.co/Kreuzberg">
+    <img src="https://img.shields.io/badge/%F0%9F%A4%97_Hugging_Face-007ec6" alt="Hugging Face">
+  </a>
+</div>
+
+> [!NOTE]
+> **Kreuzberg v4 LTS** — the long-term-support line for Kreuzberg **v4**. Active development has moved to
+> **[Xberg](https://github.com/xberg-io/xberg)** (v5+), which receives all new features. This line receives
+> critical bug and security fixes until the **end of 2026, on a best-effort basis**.
+> See the **[migration guide & LTS policy →](https://docs.kreuzberg.dev/lts/)**
+
+<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 91+ file formats and 248 programming languages 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 1.22.x 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://docs.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.quality_score}"
+puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
+```
+
+
+
+
+
+
+### Next Steps
+
+- **[Installation Guide](https://docs.kreuzberg.dev/getting-started/installation/)** - Platform-specific setup
+- **[API Documentation](https://docs.kreuzberg.dev/api/)** - Complete API reference
+- **[Examples & Guides](https://docs.kreuzberg.dev/guides/)** - Full code examples and usage guides
+- **[Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/)** - Advanced configuration options
+
+
+
+## Features
+
+### Supported File Formats (91+)
+
+91+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+
+#### Office Documents
+
+| Category | Formats | Capabilities |
+|----------|---------|--------------|
+| **Word Processing** | `.docx`, `.docm`, `.dotx`, `.dotm`, `.dot`, `.odt` | Full text, tables, images, metadata, styles |
+| **Spreadsheets** | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.xltx`, `.xlt`, `.ods` | Sheet data, formulas, cell metadata, charts |
+| **Presentations** | `.pptx`, `.pptm`, `.ppsx`, `.potx`, `.potm`, `.pot`, `.ppt` | Slides, speaker notes, images, metadata |
+| **PDF** | `.pdf` | Text, tables, images, metadata, OCR support |
+| **eBooks** | `.epub`, `.fb2` | Chapters, metadata, embedded resources |
+| **Database** | `.dbf` | Table data extraction, field type support |
+| **Hangul** | `.hwp`, `.hwpx` | Korean document format, text extraction |
+
+#### 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 |
+
+#### Code Intelligence (248 Languages)
+
+| Feature | Description |
+|---------|-------------|
+| **Structure Extraction** | Functions, classes, methods, structs, interfaces, enums |
+| **Import/Export Analysis** | Module dependencies, re-exports, wildcard imports |
+| **Symbol Extraction** | Variables, constants, type aliases, properties |
+| **Docstring Parsing** | Google, NumPy, Sphinx, JSDoc, RustDoc, and 10+ formats |
+| **Diagnostics** | Parse errors with line/column positions |
+| **Syntax-Aware Chunking** | Split code by semantic boundaries, not arbitrary byte offsets |
+
+Powered by [tree-sitter-language-pack](https://github.com/xberg-io/tree-sitter-language-pack) — [documentation](https://docs.tree-sitter-language-pack.xberg.io).
+
+**[Complete Format Reference](https://docs.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
+
+- **Code Intelligence** - Extract structure, imports, exports, symbols, and docstrings from [248 programming languages](https://docs.tree-sitter-language-pack.xberg.io) via tree-sitter
+
+- **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.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://docs.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://docs.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://docs.kreuzberg.dev/guides/configuration/)**
+
+## Documentation
+
+- **[Official Documentation](https://docs.kreuzberg.dev/)**
+- **[API Reference](https://docs.kreuzberg.dev/reference/api-ruby/)**
+- **[Examples & Guides](https://docs.kreuzberg.dev/guides/)**
+
+## Contributing
+
+Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg-dev/kreuzberg-lts/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-lts/issues)
+- **Discussions**: [Ask questions](https://github.com/kreuzberg-dev/kreuzberg-lts/discussions)

data/ext/kreuzberg_rb/extconf.rb

@@ -1,10 +1,58 @@
 # frozen_string_literal: true
 
-require 'mkmf'
-require 'rb_sys/mkmf'
+require "mkmf"
+require "rb_sys/mkmf"
+require "rbconfig"
+require "fileutils"
 
-default_profile = ENV.fetch('CARGO_PROFILE', 'release')
+if Gem.win_platform?
+  if ENV["CARGO_TARGET_DIR"]
+    puts("Windows detected: Using existing CARGO_TARGET_DIR=#{ENV["CARGO_TARGET_DIR"]}")
+  else
+    short_target_dir = Dir.exist?("C:/t") ? "C:/t" : "C:/kz-build"
+    begin
+      FileUtils.mkdir_p(short_target_dir)
+      ENV["CARGO_TARGET_DIR"] = short_target_dir
+      ENV["OUT_DIR"] = short_target_dir
+      puts("Windows detected: Using short build path #{short_target_dir}")
+    rescue StandardError => e
+      puts("Warning: Could not create short path #{short_target_dir}: #{e.message}")
+    end
+  end
+end
+
+if /mswin|mingw/.match?(RbConfig::CONFIG["host_os"])
+  devkit = ENV.fetch("RI_DEVKIT", nil)
+  prefix = ENV["MSYSTEM_PREFIX"] || "/ucrt64"
+
+  native_include = File.expand_path("native/include", __dir__).tr("\\", "/")
+  compat_include = File.expand_path("native/include/msvc_compat", __dir__).tr("\\", "/")
+
+  extra_args = []
+  extra_args << "-I#{native_include}"
+  extra_args << "-I#{compat_include}"
+
+  extra_args << "-fms-extensions"
+  extra_args << "-fno-omit-frame-pointer"
+
+  if devkit
+    sysroot = "#{devkit}#{prefix}".tr("\\", "/")
+    extra_args.push("--target=x86_64-pc-windows-gnu", "--sysroot=#{sysroot}")
+  end
+
+  unless extra_args.empty?
+    existing = ENV["BINDGEN_EXTRA_CLANG_ARGS"].to_s.split(/\s+/).reject(&:empty?)
+    ENV["BINDGEN_EXTRA_CLANG_ARGS"] = (existing + extra_args).uniq.join(" ")
+    puts("BINDGEN_EXTRA_CLANG_ARGS set to: #{ENV.fetch("BINDGEN_EXTRA_CLANG_ARGS", nil)}")
+  end
+
+  ENV["CARGO_BUILD_TARGET"] ||= "x86_64-pc-windows-gnu" if devkit || ENV["MSYSTEM"]
+end
+
+default_profile = ENV.fetch("CARGO_PROFILE", "release")
+native_dir = "native"
 
-create_rust_makefile('kreuzberg_rb') do |config|
+create_rust_makefile("kreuzberg_rb") do |config|
   config.profile = default_profile.to_sym
+  config.ext_dir = native_dir
 end

data/ext/kreuzberg_rb/native/.cargo/config.toml

@@ -0,0 +1,21 @@
+[build]
+rustflags = ["-A", "unpredictable-function-pointer-comparisons", "-A", "fn_ptr_eq"]
+
+[target.x86_64-pc-windows-gnu]
+rustflags = [
+    "-A",
+    "unpredictable-function-pointer-comparisons",
+    "-A",
+    "fn_ptr_eq",
+    "-C",
+    "link-arg=-lbcrypt",
+    "-C",
+    "link-arg=-lcrypt32",
+    "-C",
+    "link-arg=-lws2_32",
+    "-C",
+    "link-arg=-luserenv",
+]
+
+[target.x86_64-pc-windows-msvc]
+rustflags = ["-A", "unpredictable-function-pointer-comparisons", "-A", "fn_ptr_eq"]

data/ext/kreuzberg_rb/native/Cargo.toml

@@ -1,24 +1,74 @@
 [package]
 name = "kreuzberg-rb"
-version = "4.10.0-rc.2"
+version = "4.10.0"
 edition = "2024"
-license = "Elastic-2.0"
-description = "High-performance document intelligence library"
-readme = false
-keywords = ["document", "extraction", "pdf", "ocr", "text"]
-categories = ["text-processing"]
+rust-version = "1.91"
+authors = ["Na'aman Hirschfeld <naaman@kreuzberg.dev>"]
+license = "MIT"
+repository = "https://github.com/kreuzberg-dev/kreuzberg-lts"
+homepage = "https://kreuzberg.dev"
+documentation = "https://docs.rs/kreuzberg"
+readme = "README.md"
+description = "Ruby bindings (Magnus) for Kreuzberg - high-performance document intelligence framework"
+keywords = ["ruby", "magnus", "document", "extraction", "bindings"]
+categories = ["api-bindings", "text-processing"]
 
 [lib]
 name = "kreuzberg_rb"
-path = "../src/lib.rs"
-crate-type = ["cdylib"]
+crate-type = ["cdylib", "rlib"]
+
+[features]
+default = ["embeddings"]
+embeddings = ["kreuzberg/embeddings"]
 
 [dependencies]
-kreuzberg = { path = "../../../vendor/kreuzberg", features = ["full"] }
-magnus = "0.8"
-serde = { version = "1", features = ["derive"] }
-serde_json = "1"
-tokio = { version = "1", features = ["rt-multi-thread"] }
+async-trait = "0.1.89"
+kreuzberg = { path = "../../../vendor/kreuzberg", default-features = false, features = [
+    "pdf",
+    "excel",
+    "office",
+    "email",
+    "html",
+    "xml",
+    "archives",
+    "ocr",
+    "language-detection",
+    "chunking",
+    "chunking-tokenizers",
+    "embeddings",
+    "ort-bundled",
+    "quality",
+    "keywords",
+    "api",
+    "mcp",
+    "otel",
+    "bundled-pdfium",
+    "tokio-runtime",
+] }
+kreuzberg-ffi = { path = "../../../vendor/kreuzberg-ffi" }
+magnus = { git = "https://github.com/matsadler/magnus", rev = "f6db11769efb517427bf7f121f9c32e18b059b38", features = [
+    "rb-sys",
+] }
+rb-sys = { version = "0.9.128", default-features = false, features = [
+    "stable-api-compiled-fallback",
+] }
+serde_json = "1.0.150"
+toml = "1.1.2"
+serde_yaml_ng = "0.10"
+tokio = { version = "1.52.3", features = [
+    "rt",
+    "rt-multi-thread",
+    "macros",
+    "sync",
+    "process",
+    "fs",
+    "time",
+    "io-util",
+] }
+html-to-markdown-rs = { version = "3.5.7", default-features = false }
+
+[dev-dependencies]
+pretty_assertions = "1.4"
 
-[lints]
-workspace = true
+[package.metadata.cargo-machete]
+ignored = ["rb-sys"]