kreuzberg 5.0.0.pre.rc.30 → 5.0.0.pre.rc.32

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 329bbeb566e9d1e7e8e89d90e96560fb107476f3b52471bf61e9120f84bbaad3
-  data.tar.gz: 014d2b64d5ceb9e75c6f783de42c48d149c95398935d5acf77b69e78db130d10
+  metadata.gz: 12aacf589df9ea6e0e80ada2ef3c41194a5e74aa4185a438abce37554bea8e5d
+  data.tar.gz: 9f3cb43f31d255d734ae628e54905dca73d127c01a5c26ed7330d2eaf7a6e50f
 SHA512:
-  metadata.gz: d03759c1705908e4073c2432b115f19ec5febf82de052ed63520d84a5d2d6d1c9e122f113c7f536dcf720f9c18605bc9234b38fd2e277af3c7b3ec32c72d889c
-  data.tar.gz: 65d513133b42735259d32eede4935155d5e81e29112b1d3aa55596091c616231e44ba66da43e8ca11bc0aebf3e048a22aca452f391df407b51dd8a9950bfe841
+  metadata.gz: d071bcbbbeccd55799a47aaad69a74b72fa5ac1289c5cf61a8dedf287759e738a6c6e5876def7a95f1308db62c65c9a8978c731292ebb3333efe06162154cc13
+  data.tar.gz: 0d4770ba862de8637a724916efc1d4cd76057b313e8fa5314413169c115cfe198e26ee018f7576796f0fbf57a2d9118c78e0aac939f0068c5aea1381c1e23c73

data/ext/kreuzberg_rb/native/Cargo.lock

@@ -206,9 +206,9 @@ checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
 
 [[package]]
 name = "arrayvec"
-version = "0.7.6"
+version = "0.7.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
+checksum = "f02882884d3e1bc524fb12c79f107f6ad0e1cfd498c536ffb494301740995dfe"
 
 [[package]]
 name = "as-slice"
@@ -824,9 +824,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.2.64"
+version = "1.2.65"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dad887fd958be91b5098c0248def011f4523ab786cd411be668777e55063501f"
+checksum = "e228eec9be7c17ccb640b59b36a5cd805ea2a564a4c5e162c2f659fea30d3b96"
 dependencies = [
  "find-msvc-tools",
  "jobserver",
@@ -1465,6 +1465,38 @@ version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac6b926516df9c60bfa16e107b21086399f8285a44ca9711344b9e553c5146e2"
 
+[[package]]
+name = "defmt"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a6e524506490a1953d237cb87b1cfc1e46f88c18f10a22dfe0f507dc6bfc7f7f"
+dependencies = [
+ "bitflags 1.3.2",
+ "defmt-macros",
+]
+
+[[package]]
+name = "defmt-macros"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0a27770e9c8f719a79d8b638281f4d828f77d8fd61e0bd94451b9b85e576a0b"
+dependencies = [
+ "defmt-parser",
+ "proc-macro-error2",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.118",
+]
+
+[[package]]
+name = "defmt-parser"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10d60334b3b2e7c9d91ef8150abfb6fa4c1c39ebbcf4a81c2e346aad939fee3e"
+dependencies = [
+ "thiserror 2.0.18",
+]
+
 [[package]]
 name = "der"
 version = "0.8.0"
@@ -2111,9 +2143,9 @@ checksum = "312d2295c7302019c395cfb90dacd00a82a2eabd700429bba9c7a3f38dbbe11b"
 
 [[package]]
 name = "gcp_auth"
-version = "0.12.6"
+version = "0.12.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c2b3d0b409a042a380111af38136310839af8ac1a0917fb6e84515ed1e4bf3ee"
+checksum = "26d27dbcc645b60b8e7f6e2868a9d7102ece97d1bb49c1288b5321fcc67f7260"
 dependencies = [
  "async-trait",
  "base64 0.22.1",
@@ -2125,6 +2157,7 @@ dependencies = [
  "hyper-rustls",
  "hyper-util",
  "ring",
+ "rustls",
  "rustls-pki-types",
  "serde",
  "serde_json",
@@ -2482,9 +2515,9 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "3.6.15"
+version = "3.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de0dd81706c600309dda21949e23a30344d0153d2325faeeaf1122839b93651d"
+checksum = "965c9e8ff7244c3946c9508d9c4aa0ae355a5cccdea366689c20ec1303fef56c"
 dependencies = [
  "ahash 0.8.12",
  "astral-tl",
@@ -3063,10 +3096,11 @@ checksum = "47f142fe24a9c9944451e8349de0a56af5f3e7226dc46f3ed4d4ecc0b85af75e"
 
 [[package]]
 name = "jiff"
-version = "0.2.28"
+version = "0.2.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4603d3033e49e2b0e31229fcab20a5d40089c607d975cd9c80551dc69eed9102"
+checksum = "34f877a98676d2fb664698d74cc6a51ce6c484ce8c770f05d0108ec9090aeb46"
 dependencies = [
+ "defmt",
  "jiff-static",
  "jiff-tzdb-platform",
  "log",
@@ -3078,9 +3112,9 @@ dependencies = [
 
 [[package]]
 name = "jiff-static"
-version = "0.2.28"
+version = "0.2.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "782d32378dddf207193ac91cefb848ad41abb58195c95168e1291227a0832b47"
+checksum = "0666b5ab5ecaca213fc2a85b8c0083d9004e84ee2d5f9a7e0017aaf50986f25f"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -3233,8 +3267,6 @@ dependencies = [
  "referencing",
  "regex",
  "regex-syntax",
- "reqwest 0.13.4",
- "rustls",
  "serde",
  "serde_json",
  "unicode-general-category",
@@ -3243,9 +3275,9 @@ dependencies = [
 
 [[package]]
 name = "kreuzberg"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a5fc97a9058d41eeed6589717b843cbe1b452a40967ac805330e0d2e999c6a43"
+checksum = "fd3f7f001f2ea8d359463333c3f24389b56d58f0bb0802c1dc7d8163925bfd9f"
 dependencies = [
  "ahash 0.8.12",
  "async-trait",
@@ -3378,9 +3410,9 @@ dependencies = [
 
 [[package]]
 name = "kreuzberg-libheif"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f08a60d0135deceb0a3852e6627644a2f4a7069d7455fffc87e02e6ba59880e"
+checksum = "52762c0f3d21e23b592b5e598824f58dbcd69917a7a95209e4f85c2e294c5162"
 dependencies = [
  "cfg-if",
  "enumn",
@@ -3402,9 +3434,9 @@ dependencies = [
 
 [[package]]
 name = "kreuzberg-paddle-ocr"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b6f4516c42aad6d30227faabbb06e0896b8fb17bfcec2cdef5f9f73471df5d3"
+checksum = "f45f032fca2841d98d42cf393b1b94fa87de2c4be395923f5167ac720d8e1feb"
 dependencies = [
  "geo-clipper",
  "geo-types",
@@ -3418,7 +3450,7 @@ dependencies = [
 
 [[package]]
 name = "kreuzberg-rb"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 dependencies = [
  "async-trait",
  "kreuzberg",
@@ -3431,9 +3463,9 @@ dependencies = [
 
 [[package]]
 name = "kreuzberg-tesseract"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2c9a29237793847b570680837898082c2b0dc958db0bb68f390fac4570246e3"
+checksum = "ca1bae2b7d1c6d3b2a25c8ee622c0a024f80221c5179d214f72f09eeae6afda1"
 dependencies = [
  "cc",
  "cmake",
@@ -3550,9 +3582,9 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "liter-llm"
-version = "1.7.1"
+version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0552ad2a855bd57c422933227a1d664ad66b1e773dd2244a14194500880ef544"
+checksum = "9fa5f699609fb9153fb48d5857b302b25e0088f7ebbb0de5e8847fa442a3315a"
 dependencies = [
  "ahash 0.8.12",
  "async-trait",
@@ -3623,9 +3655,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.32"
+version = "0.4.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "953f07c43838f8e6f9758cab68bf5bed85465e7587ebe0b823f1bcd81978ad3a"
+checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
 
 [[package]]
 name = "loop9"
@@ -3765,9 +3797,9 @@ dependencies = [
 
 [[package]]
 name = "mail-parser"
-version = "0.11.3"
+version = "0.11.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d8a2420e9ce11c2b0583ca97ddff7ab2398c8a613154e9b72e3bafdbf767f1d7"
+checksum = "f2c0e7e0704500930be5b6c629f30d23fd1dde4d1800e138e04b3fa302e64d51"
 dependencies = [
  "hashify",
 ]
@@ -3851,9 +3883,9 @@ checksum = "88904434abc2901f197fe8cc55f0445e7ded921dba5911dad2e2b39b48e663c4"
 
 [[package]]
 name = "memmap2"
-version = "0.9.10"
+version = "0.9.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "714098028fe011992e1c3962653c96b2d578c4b4bce9036e15ff220319b1e0e3"
+checksum = "d1219ed1b7f229ee7104d281dd01d6802fe28bb6e95d292942c4daacdeb798c0"
 dependencies = [
  "libc",
 ]
@@ -4479,9 +4511,9 @@ dependencies = [
 
 [[package]]
 name = "pdf_oxide"
-version = "0.3.66"
+version = "0.3.67"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b30ba994e5ce01c9d584ead6dc5d28d69a6f24c180873ee262e4bb9e2f5dadff"
+checksum = "ebe40b26fba42c41c162dbfd33a6d4a6f90a57b6f114dddaa1806d973f909c66"
 dependencies = [
  "aes 0.9.1",
  "base64 0.22.1",
@@ -4783,6 +4815,28 @@ dependencies = [
  "toml_edit",
 ]
 
+[[package]]
+name = "proc-macro-error-attr2"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96de42df36bb9bba5542fe9f1a054b8cc87e172759a1868aa05c1f3acc89dfc5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "proc-macro-error2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11ec05c52be0a07b08061f7dd003e7d7092e0472bc731b4af7bb1ef876109802"
+dependencies = [
+ "proc-macro-error-attr2",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.118",
+]
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.106"
@@ -4935,9 +4989,9 @@ dependencies = [
 
 [[package]]
 name = "quinn"
-version = "0.11.9"
+version = "0.11.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9e20a958963c291dc322d98411f541009df2ced7b5a4f2bd52337638cfccf20"
+checksum = "0c1a41e437b6bbd489372cd4971de128e85c855f56c57f283d20ff016cf7c0a8"
 dependencies = [
  "bytes",
  "cfg_aliases",
@@ -4955,9 +5009,9 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.14"
+version = "0.11.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
+checksum = "4fcb935c5bec503c2f0e306bdd3e58bb9029dcb14fa8d9ac76e3a5256ac0763e"
 dependencies = [
  "aws-lc-rs",
  "bytes",
@@ -4991,9 +5045,9 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.45"
+version = "1.0.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+checksum = "dfbc457d0c7a0759a614551b11a6409e5951f6c7537be1f1b7682b9ae9230368"
 dependencies = [
  "proc-macro2",
 ]
@@ -5659,9 +5713,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.40"
+version = "0.23.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef86cd5876211988985292b91c96a8f2d298df24e75989a43a3c73f2d4d8168b"
+checksum = "6b92b125634d9b795e7beca796cc790df15a7fb38323bf3196fda83292d06b1f"
 dependencies = [
  "aws-lc-rs",
  "log",
@@ -6760,9 +6814,9 @@ dependencies = [
 
 [[package]]
 name = "time"
-version = "0.3.49"
+version = "0.3.51"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "711a53c2d47bbd818258c498c8dbfe186a2526c631495cfe7e078567f86b8469"
+checksum = "85c17d80feb7334b40c484e45ed1a5273dfd8bfda537c3be2e74a06a6686f327"
 dependencies = [
  "deranged",
  "num-conv",
@@ -6780,9 +6834,9 @@ checksum = "9e1c906769ad99c88eaa54e728060edef082f8e358ff32030cb7c7d315e81109"
 
 [[package]]
 name = "time-macros"
-version = "0.2.29"
+version = "0.2.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "71c652a3727a9cbb9a02f707f530b618ce00d0ccd762009c8c23bd191df3c17d"
+checksum = "dcef1a61bdb119096e153208ec5cbec23944ce8bca13be5c7f60c634f7403935"
 dependencies = [
  "num-conv",
  "time-core",
@@ -7193,9 +7247,9 @@ checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
 
 [[package]]
 name = "tree-sitter-language-pack"
-version = "1.9.1"
+version = "1.10.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09a9d3b46347363ce7dc86d1df53ebe6af125cb9b30c24461d190aa942da6b50"
+checksum = "4a19cf15df25708c7c837024c7fda7ca92e218ebc87652abd0ff07b057ff7105"
 dependencies = [
  "ahash 0.8.12",
  "cc",
@@ -8404,9 +8458,9 @@ dependencies = [
 
 [[package]]
 name = "zlib-rs"
-version = "0.6.3"
+version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3be3d40e40a133f9c916ee3f9f4fa2d9d63435b5fbe1bfc6d9dae0aa0ada1513"
+checksum = "977347db8caa080403f6b6b7c1cda9479a8e869316f7e13a59b19076a40f94e3"
 
 [[package]]
 name = "zmij"

data/ext/kreuzberg_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kreuzberg-rb"
-version = "5.0.0-rc.30"
+version = "5.0.0-rc.32"
 edition = "2024"
 license = "Elastic-2.0"
 description = "High-performance document intelligence library"
@@ -58,7 +58,7 @@ xml = ["kreuzberg/xml"]
 
 [dependencies]
 async-trait = "0.1"
-kreuzberg = { version = "5.0.0-rc.30", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-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"] }
+kreuzberg = { version = "5.0.0-rc.32", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-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"] }
 magnus = "0.8"
 rb-sys = ">=0.9, <0.9.128"
 serde = { version = "1", features = ["derive"] }

data/ext/kreuzberg_rb/src/lib.rs

@@ -1,5 +1,5 @@
 // This file is auto-generated by alef. DO NOT EDIT.
-// alef:hash:1865aced39145e92bc65e9f4ca999b62f1f2b003e5fe0ed4bd2b1050a8f64a0f
+// alef:hash:6a863205e7a486a4e1b97dac288554ebbf65a8b3ad1aaa6799965109e6543cd4
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(
@@ -20448,9 +20448,11 @@ impl magnus::TryConvert for ImageOutputFormat {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -20509,6 +20511,7 @@ impl magnus::TryConvert for OutputFormat {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
@@ -20803,9 +20806,11 @@ impl magnus::TryConvert for VlmFallbackPolicy {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "mode": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -20950,9 +20955,11 @@ impl magnus::TryConvert for ChunkSizing {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -21011,9 +21018,11 @@ impl magnus::TryConvert for EmbeddingModelType {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -21083,9 +21092,11 @@ impl magnus::TryConvert for RerankerModelType {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -21822,9 +21833,11 @@ impl magnus::TryConvert for NodeContent {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "node_type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -21889,9 +21902,11 @@ impl magnus::TryConvert for AnnotationKind {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "annotation_type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -21954,6 +21969,7 @@ impl magnus::TryConvert for EntityCategory {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
@@ -22389,9 +22405,11 @@ impl magnus::TryConvert for FormatMetadata {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "format_type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -22778,9 +22796,11 @@ impl magnus::TryConvert for OcrBoundingGeometry {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -22986,6 +23006,7 @@ impl magnus::TryConvert for PiiCategory {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
@@ -23043,9 +23064,11 @@ impl magnus::TryConvert for DiffLine {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "kind": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -23172,9 +23195,11 @@ impl magnus::TryConvert for RevisionAnchor {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -23415,9 +23440,11 @@ impl magnus::TryConvert for EnrichStatus {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "status": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -23519,9 +23546,11 @@ impl magnus::TryConvert for ChunkingDecision {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -23597,9 +23626,11 @@ impl magnus::TryConvert for NoChunkingReason {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -23658,9 +23689,11 @@ impl magnus::TryConvert for ChunkingReason {
             })?
         };
         // Try deserializing as JSON first (handles JSON strings like "\"markdown\"" or "{\"click\":{\"selector\":\"...\"}}\"")
+        // For internally-tagged enums, a bare variant string is wrapped as {"<tag>": value}.
         // If that fails, try treating it as a plain string value and wrap in quotes
         // If both fail, try as Custom variant (for untagged enum support)
         serde_json::from_str(&json_str)
+            .or_else(|_| serde_json::from_value(serde_json::json!({ "type": json_str })))
             .or_else(|_| serde_json::from_str(&format!("\"{json_str}\"")))
             .or_else(|_| {
                 // Try as a JSON string for Custom variant (untagged enums accept any remaining value)
@@ -25743,6 +25776,30 @@ fn render_pdf_page_to_png(args: &[magnus::Value]) -> Result<Vec<u8>, Error> {
     Ok(result.to_vec())
 }
 
+#[cfg(feature = "pdf")]
+fn pdf_page_count(args: &[magnus::Value]) -> Result<usize, Error> {
+    let args = magnus::scan_args::scan_args::<(Vec<u8>,), (Option<magnus::Value>,), (), (), (), ()>(args)?;
+    let (pdf_bytes,) = args.required;
+
+    let (password,) = args.optional;
+
+    let password: Option<String> = password.and_then(|v| {
+        if v.is_nil() {
+            None
+        } else {
+            Some(String::try_convert(v).unwrap_or_default())
+        }
+    });
+
+    let result = kreuzberg::pdf_page_count(&pdf_bytes, password.as_deref()).map_err(|e| {
+        magnus::Error::new(
+            unsafe { Ruby::get_unchecked() }.exception_runtime_error(),
+            e.to_string(),
+        )
+    })?;
+    Ok(result)
+}
+
 #[cfg(all(feature = "captioning", feature = "tokio-runtime"))]
 fn caption_image(args: &[magnus::Value]) -> Result<String, Error> {
     let args =
@@ -37819,6 +37876,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
 
     module.define_module_function("render_pdf_page_to_png", function!(render_pdf_page_to_png, -1))?;
 
+    module.define_module_function("pdf_page_count", function!(pdf_page_count, -1))?;
+
     module.define_module_function("caption_image", function!(caption_image, -1))?;
 
     module.define_module_function("caption_image_async", function!(caption_image_async, -1))?;

data/lib/kreuzberg/native.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:1865aced39145e92bc65e9f4ca999b62f1f2b003e5fe0ed4bd2b1050a8f64a0f
+# alef:hash:6a863205e7a486a4e1b97dac288554ebbf65a8b3ad1aaa6799965109e6543cd4
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/lib/kreuzberg/version.rb

@@ -1,10 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:1865aced39145e92bc65e9f4ca999b62f1f2b003e5fe0ed4bd2b1050a8f64a0f
+# alef:hash:6a863205e7a486a4e1b97dac288554ebbf65a8b3ad1aaa6799965109e6543cd4
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
 module Kreuzberg
   ## The version string for this package.
-  VERSION = "5.0.0.pre.rc.30"
+  VERSION = "5.0.0.pre.rc.32"
 end

data/lib/kreuzberg.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:1865aced39145e92bc65e9f4ca999b62f1f2b003e5fe0ed4bd2b1050a8f64a0f
+# alef:hash:6a863205e7a486a4e1b97dac288554ebbf65a8b3ad1aaa6799965109e6543cd4
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:1865aced39145e92bc65e9f4ca999b62f1f2b003e5fe0ed4bd2b1050a8f64a0f
+# alef:hash:6a863205e7a486a4e1b97dac288554ebbf65a8b3ad1aaa6799965109e6543cd4
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 
@@ -2504,6 +2504,8 @@ module Kreuzberg
 
   def self.render_pdf_page_to_png: (String pdf_bytes, Integer page_index, ?Integer dpi, ?String password) -> String
 
+  def self.pdf_page_count: (String pdf_bytes, ?String password) -> Integer
+
   def self.caption_image: (String image_bytes, LlmConfig llm_config, ?String custom_prompt) -> String
 
   def self.caption_image_file: (String path, LlmConfig llm_config, ?String custom_prompt) -> String

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kreuzberg
 version: !ruby/object:Gem::Version
-  version: 5.0.0.pre.rc.30
+  version: 5.0.0.pre.rc.32
 platform: ruby
 authors:
 - Na'aman Hirschfeld <naaman@kreuzberg.dev>
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-06-22 00:00:00.000000000 Z
+date: 2026-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys