kreuzberg 4.5.1-aarch64-linux → 4.5.4-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4f7421dd696f83a87681b1250e5a2271dd4dbad4cf31999b272921c87a6cbc3
-  data.tar.gz: a9fb76d70dedec40e317f36c432a715a5076ac9b2cb66a5e1030900003dfcb73
+  metadata.gz: dfd3586f04b1b2b6dcdf06af30712755fd3fd8d76c7bc03cee05a67133134998
+  data.tar.gz: c402149a2765063da19d639eb2aa2b75340db6292b680c9218bc826d5997346c
 SHA512:
-  metadata.gz: efaec6320e12b8f8d56016d26067a8ba5de8a92e2aee51ffc530e189fc5df6c0fc14125fae03cd6bfcd6b5e8386066741b089170257d20e047a28592652a1019
-  data.tar.gz: 3fd93ff62a4d0e63b782e4da4f93288a2705a5d84907910fc475062861e7c32a4dbe9cd1d3d8aaa194d7f977891b653cfc19ee38a35ded03ed94aace011dc419
+  metadata.gz: aa8f6ba036c180200182377b90b15f293cf008b440c49d732d5dfa84df203373b173b9928138d58917fd7dddfe41c3b4ea89cab582c69707253ed87163932349
+  data.tar.gz: 211e120a58693b5c385ff0c577391d542a4ee9ca3e1194ca96e2e975a2636d78cdf9526b25852dad70d543142576317c2b344260f83148143d4d9ab6ac6822bd

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kreuzberg (4.5.1)
+    kreuzberg (4.5.4)
       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 (0.6.13051)
+    sorbet-runtime (0.6.13055)
     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 (2.19.2) sha256=e7e1bd318b2c37c4ceee2444841c86539bc462e81f40d134cf97826cb14e83cf
   json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
-  kreuzberg (4.5.1)
+  kreuzberg (4.5.4)
   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 (0.6.13051) sha256=ae5495bf229c5e3e5e3a2e17ac4853798d993437f5b5f12b763d462183852452
+  sorbet-runtime (0.6.13055) sha256=c8ae8c81310e0a28d290b11f44ddca59659b7d7f13752c0ef5d16964bbb84d18
   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=v4.5.1" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.5.4" 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#">
@@ -61,7 +61,7 @@
 </div>
 
 
-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.
+Extract text, tables, images, and metadata from 91+ file formats including PDF, Office documents, and images. Ruby bindings with idiomatic Ruby API and native performance.
 
 
 ## Installation
@@ -211,9 +211,9 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 
 ## Features
 
-### Supported File Formats (88+)
+### Supported File Formats (91+)
 
-88+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+91+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
 
 #### Office Documents
 

data/lib/kreuzberg/config.rb

@@ -850,19 +850,21 @@ module Kreuzberg
     #   )
     #
     class LayoutDetection
-      attr_reader :preset, :confidence_threshold, :apply_heuristics
+      attr_reader :preset, :confidence_threshold, :apply_heuristics, :table_model
 
-      def initialize(preset: 'fast', confidence_threshold: nil, apply_heuristics: true)
+      def initialize(preset: 'fast', confidence_threshold: nil, apply_heuristics: true, table_model: nil)
         @preset = preset.to_s
         @confidence_threshold = confidence_threshold&.to_f
         @apply_heuristics = apply_heuristics ? true : false
+        @table_model = table_model&.to_s
       end
 
       def to_h
         {
           preset: @preset,
           confidence_threshold: @confidence_threshold,
-          apply_heuristics: @apply_heuristics
+          apply_heuristics: @apply_heuristics,
+          table_model: @table_model
         }.compact
       end
     end
@@ -930,7 +932,8 @@ module Kreuzberg
                   :images, :postprocessor,
                   :token_reduction, :keywords, :html_options, :pages,
                   :max_concurrent_extractions, :output_format, :result_format,
-                  :security_limits, :layout, :concurrency
+                  :security_limits, :layout, :concurrency,
+                  :cache_namespace, :cache_ttl_secs
 
       # Alias for backward compatibility - image_extraction is the canonical name
       alias image_extraction images
@@ -955,7 +958,7 @@ module Kreuzberg
         language_detection pdf_options image_extraction
         postprocessor token_reduction keywords html_options pages
         max_concurrent_extractions output_format result_format
-        security_limits layout concurrency
+        security_limits layout concurrency cache_namespace cache_ttl_secs
       ].freeze
 
       # Aliases for backward compatibility
@@ -1032,7 +1035,9 @@ module Kreuzberg
                      result_format: nil,
                      security_limits: nil,
                      layout: nil,
-                     concurrency: nil)
+                     concurrency: nil,
+                     cache_namespace: nil,
+                     cache_ttl_secs: nil)
         kwargs = {
           use_cache: use_cache, enable_quality_processing: enable_quality_processing,
           force_ocr: force_ocr, include_document_structure: include_document_structure,
@@ -1043,7 +1048,9 @@ module Kreuzberg
           pages: pages, max_concurrent_extractions: max_concurrent_extractions,
           output_format: output_format, result_format: result_format,
           security_limits: security_limits, layout: layout,
-          concurrency: concurrency
+          concurrency: concurrency,
+          cache_namespace: cache_namespace,
+          cache_ttl_secs: cache_ttl_secs
         }
         extracted = extract_from_hash(hash, kwargs)
 
@@ -1077,6 +1084,8 @@ module Kreuzberg
         @max_concurrent_extractions = params[:max_concurrent_extractions]&.to_i
         @output_format = validate_output_format(params[:output_format])
         @result_format = validate_result_format(params[:result_format])
+        @cache_namespace = params[:cache_namespace]
+        @cache_ttl_secs = params[:cache_ttl_secs]&.to_i
         @security_limits = params[:security_limits]
       end
 
@@ -1112,7 +1121,9 @@ module Kreuzberg
           include_document_structure: @include_document_structure,
           max_concurrent_extractions: @max_concurrent_extractions,
           output_format: @output_format,
-          result_format: @result_format
+          result_format: @result_format,
+          cache_namespace: @cache_namespace,
+          cache_ttl_secs: @cache_ttl_secs
         }
       end
 
@@ -1271,6 +1282,10 @@ module Kreuzberg
           @output_format = validate_output_format(value)
         when :result_format
           @result_format = validate_result_format(value)
+        when :cache_namespace
+          @cache_namespace = value
+        when :cache_ttl_secs
+          @cache_ttl_secs = value&.to_i
         else
           raise ArgumentError, "Unknown configuration key: #{key}"
         end
@@ -1352,6 +1367,8 @@ module Kreuzberg
         @max_concurrent_extractions = merged.max_concurrent_extractions
         @output_format = merged.output_format
         @result_format = merged.result_format
+        @cache_namespace = merged.cache_namespace
+        @cache_ttl_secs = merged.cache_ttl_secs
       end
     end
   end

data/lib/kreuzberg/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Kreuzberg
-  VERSION = '4.5.1'
+  VERSION = '4.5.4'
 end

data/sig/kreuzberg.rbs

@@ -463,8 +463,9 @@ module Kreuzberg
       attr_reader preset: String
       attr_reader confidence_threshold: Float?
       attr_reader apply_heuristics: bool
+      attr_reader table_model: String?
 
-      def initialize: (?preset: String, ?confidence_threshold: Float?, ?apply_heuristics: bool) -> void
+      def initialize: (?preset: String, ?confidence_threshold: Float?, ?apply_heuristics: bool, ?table_model: String?) -> void
       def to_h: () -> Hash[Symbol, untyped]
     end
 
@@ -478,6 +479,8 @@ module Kreuzberg
     class Extraction
       attr_reader use_cache: bool
       attr_reader enable_quality_processing: bool
+      attr_reader cache_namespace: String?
+      attr_reader cache_ttl_secs: Integer?
       attr_reader force_ocr: bool
       attr_reader include_document_structure: bool
       attr_reader ocr: OCR?
@@ -520,7 +523,9 @@ module Kreuzberg
         ?concurrency: (Concurrency | Hash[Symbol, untyped])?,
         ?max_concurrent_extractions: Integer?,
         ?output_format: String?,
-        ?result_format: String?
+        ?result_format: String?,
+        ?cache_namespace: String?,
+        ?cache_ttl_secs: Integer?
       ) -> void
       def to_h: () -> Hash[Symbol, untyped]
       def to_json: (*untyped) -> String

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kreuzberg
 version: !ruby/object:Gem::Version
-  version: 4.5.1
+  version: 4.5.4
 platform: aarch64-linux
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-03-21 00:00:00.000000000 Z
+date: 2026-03-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler