xberg 1.0.0.pre.rc.40 → 1.0.0.pre.rc.42

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 91168584ce72ce570f483d3be288b4077ddc5c1a717662c03875d43852cab6f3
4
- data.tar.gz: 66e1a230de124ec726e39d123af7cabc49d98926309094d103ef66b30f42d6f5
3
+ metadata.gz: 843c35b446da636fad246d5b41d7e0e0b1e19ddb858bb91ab88709713a7426b7
4
+ data.tar.gz: 270431cbbb6679ff55d279751fc3b7d994022ce35bd5fe50d10508f1ce7eb581
5
5
  SHA512:
6
- metadata.gz: c804b88f7dfdccd557db3df2c55de892f30fa4acb33ab03ddcec14f078018dcf9c0c40e0ffc79bade325bb955358779c1cda7afd2561f6190faefec30abf3496
7
- data.tar.gz: 2643876f100d23a5c911e7518be2701743c3910377ef429920f00ddc5de24fa690a90e524626f0a40d45bffe7976bc610d8ce59c16a4054b07590d4ccfc267e1
6
+ metadata.gz: edb429989127405f6f241a900dac9f702cf568a465d78883eff72988c96ec514d5f4ef0f07f5da60b9ba1333c0ea7205c2c9e57f29312ef1064512754563d324
7
+ data.tar.gz: ab0000882144aa9c555f12ea83b1a68945ee93bd238c99c82440f3e2031bb7c781c505693500e1f937abc279cec19aeda79c663622addc9912a5e11632c02b4f
@@ -1346,9 +1346,9 @@ dependencies = [
1346
1346
 
1347
1347
  [[package]]
1348
1348
  name = "crawlberg"
1349
- version = "1.0.8"
1349
+ version = "1.0.9"
1350
1350
  source = "registry+https://github.com/rust-lang/crates.io-index"
1351
- checksum = "fc6e5f06202d56f7b1b16399841241b810db3e305401bb401599565b07c92e10"
1351
+ checksum = "b2841d7bdd19a54e025f61e852c54e0af8f5d492e6ed862dbb0b1363e4f9a29f"
1352
1352
  dependencies = [
1353
1353
  "ahash 0.8.12",
1354
1354
  "aho-corasick",
@@ -3765,14 +3765,14 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
3765
3765
 
3766
3766
  [[package]]
3767
3767
  name = "liter-llm"
3768
- version = "1.11.0"
3768
+ version = "1.11.2"
3769
3769
  source = "registry+https://github.com/rust-lang/crates.io-index"
3770
- checksum = "016fbd9e5fc66d4cb10eb5faa45242e54add93101816926fe9348bcfb0cb051a"
3770
+ checksum = "6b9cadc4e7d91a51d237279b777d58e2ca25223159963f0a66bf17f4157e0274"
3771
3771
  dependencies = [
3772
3772
  "ahash 0.8.12",
3773
3773
  "arc-swap",
3774
3774
  "async-trait",
3775
- "base64 0.22.1",
3775
+ "base64 0.23.0",
3776
3776
  "bytes",
3777
3777
  "dashmap",
3778
3778
  "futures-core",
@@ -7837,9 +7837,9 @@ checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
7837
7837
 
7838
7838
  [[package]]
7839
7839
  name = "tree-sitter-language-pack"
7840
- version = "1.13.3"
7840
+ version = "1.13.4"
7841
7841
  source = "registry+https://github.com/rust-lang/crates.io-index"
7842
- checksum = "345ee6dd864ca9f9e846120d5546082a27e946e1b129a55e7c6d4b1fc5cddec3"
7842
+ checksum = "57d7a66a4a143bc10fa060c2f28f81758ec20b4a335fdb8bdf95292709af409b"
7843
7843
  dependencies = [
7844
7844
  "ahash 0.8.12",
7845
7845
  "cc",
@@ -8875,9 +8875,9 @@ dependencies = [
8875
8875
 
8876
8876
  [[package]]
8877
8877
  name = "xberg"
8878
- version = "1.0.0-rc.40"
8878
+ version = "1.0.0-rc.42"
8879
8879
  source = "registry+https://github.com/rust-lang/crates.io-index"
8880
- checksum = "0e788f68e69b44a982ccbf1e2bbec3bbc27cc21c1c183cfa61e2f8856519e83d"
8880
+ checksum = "11a00254a4b2986b442724ac2bdba9fb5b436da7d9e8dfb265d13e8b1ce9b6e9"
8881
8881
  dependencies = [
8882
8882
  "aes-gcm",
8883
8883
  "ahash 0.8.12",
@@ -9000,9 +9000,9 @@ dependencies = [
9000
9000
 
9001
9001
  [[package]]
9002
9002
  name = "xberg-gliner"
9003
- version = "1.0.0-rc.40"
9003
+ version = "1.0.0-rc.42"
9004
9004
  source = "registry+https://github.com/rust-lang/crates.io-index"
9005
- checksum = "4bb85ca44b0a9fa9ee453e84e75c8a75c1a9ef3ffe292798e49931737b0a443a"
9005
+ checksum = "62e67c0be3f48b9a09681fee1873c5463abc5491aab44327359e24180c57d2cd"
9006
9006
  dependencies = [
9007
9007
  "getrandom 0.2.17",
9008
9008
  "getrandom 0.3.4",
@@ -9016,9 +9016,9 @@ dependencies = [
9016
9016
 
9017
9017
  [[package]]
9018
9018
  name = "xberg-libheif"
9019
- version = "1.0.0-rc.40"
9019
+ version = "1.0.0-rc.42"
9020
9020
  source = "registry+https://github.com/rust-lang/crates.io-index"
9021
- checksum = "8ca7c4b3019d30465eb912f52d554588cf7ce36b233298ef1edcd57dae2305fb"
9021
+ checksum = "4f1afdf970190b5a4c754fd037b2cb02c927633f12cdc44f2768058e68e8b5d8"
9022
9022
  dependencies = [
9023
9023
  "cfg-if 1.0.4",
9024
9024
  "enumn",
@@ -9029,9 +9029,9 @@ dependencies = [
9029
9029
 
9030
9030
  [[package]]
9031
9031
  name = "xberg-paddle-ocr"
9032
- version = "1.0.0-rc.40"
9032
+ version = "1.0.0-rc.42"
9033
9033
  source = "registry+https://github.com/rust-lang/crates.io-index"
9034
- checksum = "dd8dd1b3e5d70bd43d2408b1898995f56773c814e52d46c57316118d801eb820"
9034
+ checksum = "6878bc3247ec24ddcb8e57827b007f2ff42a6f35e6c1ea982275951fcdcde54f"
9035
9035
  dependencies = [
9036
9036
  "geo-clipper",
9037
9037
  "geo-types",
@@ -9046,7 +9046,7 @@ dependencies = [
9046
9046
 
9047
9047
  [[package]]
9048
9048
  name = "xberg-rb"
9049
- version = "1.0.0-rc.40"
9049
+ version = "1.0.0-rc.42"
9050
9050
  dependencies = [
9051
9051
  "async-trait",
9052
9052
  "crawlberg",
@@ -9061,9 +9061,9 @@ dependencies = [
9061
9061
 
9062
9062
  [[package]]
9063
9063
  name = "xberg-tesseract"
9064
- version = "1.0.0-rc.40"
9064
+ version = "1.0.0-rc.42"
9065
9065
  source = "registry+https://github.com/rust-lang/crates.io-index"
9066
- checksum = "be54788c7aab23f48ed3fb310800aeecc8daf89a6f3ffb1d0d88a291d3c44f1e"
9066
+ checksum = "019a1b0d14535c8a1eb7822249dd6dfcb83345ef8cd81dd0eff00e769dce1b5f"
9067
9067
  dependencies = [
9068
9068
  "cc",
9069
9069
  "cmake",
@@ -1,6 +1,6 @@
1
1
  [package]
2
2
  name = "xberg-rb"
3
- version = "1.0.0-rc.40"
3
+ version = "1.0.0-rc.42"
4
4
  edition = "2024"
5
5
  license = "MIT"
6
6
  description = "High-performance document intelligence library"
@@ -56,7 +56,7 @@ xml = ["xberg/xml"]
56
56
 
57
57
  [dependencies]
58
58
  async-trait = "0.1"
59
- crawlberg = { default-features = false, version = "1.0.8" }
59
+ crawlberg = { default-features = false, version = "1.0.9" }
60
60
  html-to-markdown-rs = { default-features = false, version = "3.9" }
61
61
  magnus = "0.8"
62
62
  rb-sys = ">=0.9, <0.9.128"
@@ -64,10 +64,10 @@ serde = { version = "1", features = ["derive"] }
64
64
  serde_json = "1"
65
65
  tokio = { version = "1", features = ["rt-multi-thread"] }
66
66
  [target.'cfg(not(any(target_os = "windows", all(target_os = "macos", target_arch = "x86_64"))))'.dependencies]
67
- xberg = { version = "1.0.0-rc.40", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-presets", "sparse-embeddings", "sparse-embedding-presets", "late-interaction", "late-interaction-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "api-types", "mcp", "liter-llm", "quality", "svg", "transcription", "transcription-types", "classification", "captioning", "ner-onnx", "ner-llm", "diff", "markdown-footnotes", "redaction", "enrichment", "heuristics", "presets", "structured", "url-ingestion"] }
67
+ xberg = { version = "1.0.0-rc.42", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-presets", "sparse-embeddings", "sparse-embedding-presets", "late-interaction", "late-interaction-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "api-types", "mcp", "liter-llm", "quality", "svg", "transcription", "transcription-types", "classification", "captioning", "ner-onnx", "ner-llm", "diff", "markdown-footnotes", "redaction", "enrichment", "heuristics", "presets", "structured", "url-ingestion"] }
68
68
 
69
69
  [target.'cfg(target_os = "windows")'.dependencies]
70
- xberg = { version = "1.0.0-rc.40", features = ["windows-target"] }
70
+ xberg = { version = "1.0.0-rc.42", features = ["windows-target"] }
71
71
 
72
72
  [target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
73
- xberg = { version = "1.0.0-rc.40", features = ["macos-intel-target"] }
73
+ xberg = { version = "1.0.0-rc.42", features = ["macos-intel-target"] }
@@ -1,5 +1,5 @@
1
1
  // This file is auto-generated by alef. DO NOT EDIT.
2
- // alef:hash:c42b3ed17053806bdcf42dea768a2aecba67c8ec1370751ea7323b02483cbce1
2
+ // alef:hash:27b14662489dbd72bffe76d749cce63acd51fb05b9d0eea856452c7d4c92c223
3
3
  // Re-generate with: alef generate
4
4
  #![allow(dead_code, unused_imports, unused_variables)]
5
5
  #![allow(
data/lib/xberg/native.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  # This file is auto-generated by alef — DO NOT EDIT.
2
- # alef:hash:c42b3ed17053806bdcf42dea768a2aecba67c8ec1370751ea7323b02483cbce1
2
+ # alef:hash:27b14662489dbd72bffe76d749cce63acd51fb05b9d0eea856452c7d4c92c223
3
3
  # To regenerate: alef generate
4
4
  # To verify freshness: alef verify --exit-code
5
5
  # frozen_string_literal: true
data/lib/xberg/version.rb CHANGED
@@ -1,10 +1,10 @@
1
1
  # This file is auto-generated by alef — DO NOT EDIT.
2
- # alef:hash:8c0392777d24d6d7f71a34cbb5e5e99b13a03c5d47c49c184923b96d1a71f109
2
+ # alef:hash:27b14662489dbd72bffe76d749cce63acd51fb05b9d0eea856452c7d4c92c223
3
3
  # To regenerate: alef generate
4
4
  # To verify freshness: alef verify --exit-code
5
5
  # frozen_string_literal: true
6
6
 
7
7
  module Xberg
8
8
  ## The version string for this package.
9
- VERSION = "1.0.0.pre.rc.40"
9
+ VERSION = "1.0.0.pre.rc.42"
10
10
  end
data/lib/xberg.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  # This file is auto-generated by alef — DO NOT EDIT.
2
- # alef:hash:c42b3ed17053806bdcf42dea768a2aecba67c8ec1370751ea7323b02483cbce1
2
+ # alef:hash:27b14662489dbd72bffe76d749cce63acd51fb05b9d0eea856452c7d4c92c223
3
3
  # To regenerate: alef generate
4
4
  # To verify freshness: alef verify --exit-code
5
5
  # frozen_string_literal: true
data/lib/xberg_rb.so CHANGED
Binary file
data/sig/types.rbs CHANGED
@@ -1,5 +1,5 @@
1
1
  # This file is auto-generated by alef — DO NOT EDIT.
2
- # alef:hash:c42b3ed17053806bdcf42dea768a2aecba67c8ec1370751ea7323b02483cbce1
2
+ # alef:hash:27b14662489dbd72bffe76d749cce63acd51fb05b9d0eea856452c7d4c92c223
3
3
  # To regenerate: alef generate
4
4
  # To verify freshness: alef verify --exit-code
5
5
 
@@ -2753,7 +2753,7 @@ def self.clear_embedding_backends: () -> void
2753
2753
 
2754
2754
  def self.list_embedding_backends: () -> Array[String]
2755
2755
 
2756
- def self.register_document_extractor: (DocumentExtractor extractor) -> void
2756
+ def self.register_document_extractor: (_DocumentExtractor extractor) -> void
2757
2757
 
2758
2758
  def self.unregister_document_extractor: (String name) -> void
2759
2759
 
@@ -2769,7 +2769,7 @@ def self.list_post_processors: () -> Array[String]
2769
2769
 
2770
2770
  def self.clear_post_processors: () -> void
2771
2771
 
2772
- def self.register_renderer: (Renderer renderer) -> void
2772
+ def self.register_renderer: (_Renderer renderer) -> void
2773
2773
 
2774
2774
  def self.unregister_renderer: (String name) -> void
2775
2775
 
@@ -2795,13 +2795,13 @@ def self.find_unmarked_claims: (String markdown) -> Array[String]
2795
2795
 
2796
2796
  def self.verify_excerpt: (String excerpt, String source_text) -> bool
2797
2797
 
2798
- def self.embed_sparse_async: (Array[String] texts, SparseEmbeddingConfig config) -> Array[SparseEmbedding]
2798
+ def self.embed_sparse_async: (Array[String] texts, SparseEmbeddingConfig config) -> Array[json_value]
2799
2799
 
2800
- def self.max_sim_score: (MultiVectorEmbedding query, MultiVectorEmbedding doc) -> Float
2800
+ def self.max_sim_score: (json_value query, json_value doc) -> Float
2801
2801
 
2802
- def self.max_sim_rank: (MultiVectorEmbedding query, Array[MultiVectorEmbedding] docs) -> Array[LateInteractionMatch]
2802
+ def self.max_sim_rank: (json_value query, Array[json_value] docs) -> Array[json_value]
2803
2803
 
2804
- def self.embed_multi_vector_async: (Array[String] texts, LateInteractionConfig config, bool is_query) -> Array[MultiVectorEmbedding]
2804
+ def self.embed_multi_vector_async: (Array[String] texts, LateInteractionConfig config, bool is_query) -> Array[json_value]
2805
2805
 
2806
2806
  interface _OcrBackend
2807
2807
  # Optional methods the bridge calls when the object defines them (the
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: xberg
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.0.pre.rc.40
4
+ version: 1.0.0.pre.rc.42
5
5
  platform: ruby
6
6
  authors:
7
7
  - Na'aman Hirschfeld <naaman@xberg.io>
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2026-07-26 00:00:00.000000000 Z
11
+ date: 2026-07-27 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: rb_sys