kreuzberg 4.4.5-aarch64-linux → 4.4.6-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b0b2ee3a1f346bf1409b2f773a83bb25e3f18eb097988e2c03450f0e9e5aa0f6
-  data.tar.gz: 906a83d73d97de0fbee6ac7bd278188513b1fee4f0a69adc523cb9ad8dc45ac9
+  metadata.gz: b52fd8ab029d63ee54f697c758806e2f32566d3b112cf48865f59f9ddb9b4d5f
+  data.tar.gz: 65c4f41bd2157f5d79e86fc9bda2b8389a991ffaed9568f602700e95adef55e9
 SHA512:
-  metadata.gz: 49f8597b418c1f8b593a0f1870727e467fbcf0852720c8470bef92aa8a53f8644f32083be305ddb383fb63254e738129de197c7d91c8bb7db1cf9c96f35369ed
-  data.tar.gz: a72287f790e915284d7dae4fd2b1e9e0122ed3ffebf290670066b6c3214a5462a481f814c0ade782e345f5c5eaeab868d7e5c81cd340d4023fd0185138301b89
+  metadata.gz: b2c65f9ea098867bda920c3732f6b81c4e52c35aa30d25f15f5755808c34b97a780d35e2f39fc05273658b629c3276577878b4cda1893aa901ccf801e7f39953
+  data.tar.gz: 5837f3f6e04712ad82d02bc121e3cb483d28a8b5b32a27f6b3af4f57e8ba875a339fc8e63d1fbc5a466e96d78968b63b5a303a9a58c812e4064e367094fbc511

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kreuzberg (4.4.5)
+    kreuzberg (4.4.6)
       rb_sys (~> 0.9.119)
       sorbet-runtime (~> 0.5)
 
@@ -134,7 +134,7 @@ GEM
       rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
     securerandom (0.4.1)
-    sorbet-runtime (0.6.13011)
+    sorbet-runtime (0.6.13023)
     steep (1.10.0)
       activesupport (>= 5.1)
       concurrent-ruby (>= 1.1.10)
@@ -222,7 +222,7 @@ CHECKSUMS
   io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
   json (2.19.1) sha256=dd94fdc59e48bff85913829a32350b3148156bc4fd2a95a2568a78b11344082d
   json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
-  kreuzberg (4.4.5)
+  kreuzberg (4.4.6)
   language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
   listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
@@ -259,7 +259,7 @@ CHECKSUMS
   rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
   ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
   securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
-  sorbet-runtime (0.6.13011) sha256=d451e380097747d64d39595fbbb6db2a198310f9eff0f810cd6e5696b402833f
+  sorbet-runtime (0.6.13023) sha256=c00d11cc54951efbc0aece994dd6b20b1d1cb2a2606100c24d4ae7f840383073
   steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
   strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
   terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2

data/README.md

@@ -22,7 +22,7 @@
     <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=v4.4.5" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.4.6" 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#">
@@ -33,12 +33,12 @@
   <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/pkgs/container/kreuzberg">
     <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
   </a>
-  <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/badge/C-FFI-007ec6" alt="C">
-  </a>
 
   <!-- Project Info -->
   <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
@@ -58,7 +58,7 @@
 </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.
+Extract text, tables, images, and metadata from 88+ file formats including PDF, Office documents, and images. Ruby bindings with idiomatic Ruby API and native performance.
 
 
 ## Installation
@@ -91,7 +91,7 @@ gem 'kreuzberg'
 
 - **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: [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.
@@ -188,7 +188,7 @@ config = Kreuzberg::Config::Extraction.new(
 result = Kreuzberg.extract_file_sync('contract.pdf', config: config)
 
 puts "Extracted #{result.content.length} characters"
-puts "Quality score: #{result.metadata&.dig('quality_score')}"
+puts "Quality score: #{result.quality_score}"
 puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 ```
 
@@ -208,19 +208,21 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 
 ## Features
 
-### Supported File Formats (75+)
+### Supported File Formats (88+)
 
-75+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+88+ 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 |
+| **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)
 
@@ -334,7 +336,7 @@ config = Kreuzberg::Config::Extraction.new(
 result = Kreuzberg.extract_file_sync('contract.pdf', config: config)
 
 puts "Extracted #{result.content.length} characters"
-puts "Quality score: #{result.metadata&.dig('quality_score')}"
+puts "Quality score: #{result.quality_score}"
 puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 ```
 

data/lib/kreuzberg/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Kreuzberg
-  VERSION = '4.4.5'
+  VERSION = '4.4.6'
 end

data/sig/kreuzberg.rbs

@@ -259,6 +259,9 @@ module Kreuzberg
       attr_reader preset: String?
       attr_reader embedding: Embedding?
       attr_reader enabled: bool?
+      attr_reader sizing_type: String?
+      attr_reader sizing_model: String?
+      attr_reader sizing_cache_dir: String?
 
       def initialize: (
         ?max_chars: Integer?,
@@ -267,7 +270,10 @@ module Kreuzberg
         ?embedding: (Embedding | Hash[Symbol, untyped])?,
         ?chunk_size: Integer?,
         ?chunk_overlap: Integer?,
-        ?enabled: bool
+        ?enabled: bool,
+        ?sizing_type: String?,
+        ?sizing_model: String?,
+        ?sizing_cache_dir: String?
       ) -> void
       def to_h: () -> Hash[Symbol, untyped]
     end
@@ -767,6 +773,21 @@ module Kreuzberg
       def to_h: () -> table_hash
     end
 
+    # Heading level in the document hierarchy
+    class HeadingLevel
+      attr_reader level: Integer
+      attr_reader text: String
+
+      def initialize: (level: Integer, text: String) -> void
+    end
+
+    # Heading context for a chunk's section
+    class HeadingContext
+      attr_reader headings: Array[HeadingLevel]
+
+      def initialize: (headings: Array[HeadingLevel]) -> void
+    end
+
     # Text chunk (Struct from result.rb)
     class Chunk
       attr_reader content: String
@@ -778,6 +799,7 @@ module Kreuzberg
       attr_reader first_page: Integer?
       attr_reader last_page: Integer?
       attr_reader embedding: Array[Float]?
+      attr_reader heading_context: HeadingContext?
 
       def initialize: (
         content: String,
@@ -788,7 +810,8 @@ module Kreuzberg
         total_chunks: Integer,
         first_page: Integer?,
         last_page: Integer?,
-        embedding: Array[Float]?
+        embedding: Array[Float]?,
+        heading_context: HeadingContext?
       ) -> void
       def to_h: () -> chunk_hash
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kreuzberg
 version: !ruby/object:Gem::Version
-  version: 4.4.5
+  version: 4.4.6
 platform: aarch64-linux
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-03-11 00:00:00.000000000 Z
+date: 2026-03-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler