diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index 0e77850..3f1a5c9 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -29,6 +29,14 @@ jobs:
       - name: Build project
         run: cargo build --verbose
 
+      # Check the formatting
+      - name: Formatting check
+        run: cargo fmt --check
+
+      # Check for code mistakes an possible improvements
+      - name: Clippy check
+        run: cargo clippy -- -D warnings
+
       # Run the tests
       # This command executes all tests in the project
       - name: Run tests
diff --git a/Cargo.lock b/Cargo.lock
index bd848a3..8a2b214 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -472,7 +472,7 @@ checksum = "3109e49b1e4909e9db6515a30c633684d68cdeaa252f215214cb4fa1a5bfee2c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "synstructure",
 ]
 
@@ -484,7 +484,7 @@ checksum = "7b18050c2cd6fe86c3a76584ef5e0baf286d038cda203eb6223df2cc413565f7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -623,7 +623,7 @@ checksum = "e539d3fca749fcee5236ab05e93a52867dd549cc157c8cb7f99595f3cedffdb5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -643,9 +643,9 @@ checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
 
 [[package]]
 name = "autocfg"
-version = "1.4.0"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
 
 [[package]]
 name = "axum"
@@ -806,7 +806,7 @@ dependencies = [
  "hyperlocal",
  "log",
  "pin-project-lite",
- "rustls 0.23.27",
+ "rustls 0.23.28",
  "rustls-native-certs 0.8.1",
  "rustls-pemfile 2.2.0",
  "rustls-pki-types",
@@ -900,9 +900,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.2.26"
+version = "1.2.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "956a5e21988b87f372569b66183b78babf23ebc2e744b733e4350a752c4dafac"
+checksum = "d487aa071b5f64da6f19a3e848e3578944b726ee5a4854b82172f02aa876bfdc"
 dependencies = [
  "jobserver",
  "libc",
@@ -959,7 +959,7 @@ dependencies = [
  "anstream",
  "anstyle",
  "clap_lex",
- "strsim 0.11.1",
+ "strsim",
 ]
 
 [[package]]
@@ -971,7 +971,7 @@ dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -1176,38 +1176,14 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "darling"
-version = "0.14.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b750cb3417fd1b327431a470f388520309479ab0bf5e323505daf0290cd3850"
-dependencies = [
- "darling_core 0.14.4",
- "darling_macro 0.14.4",
-]
-
 [[package]]
 name = "darling"
 version = "0.20.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc7f46116c46ff9ab3eb1597a45688b6715c6e628b5c133e288e709a29bcb4ee"
 dependencies = [
- "darling_core 0.20.11",
- "darling_macro 0.20.11",
-]
-
-[[package]]
-name = "darling_core"
-version = "0.14.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "109c1ca6e6b7f82cc233a97004ea8ed7ca123a9af07a8230878fcfda9b158bf0"
-dependencies = [
- "fnv",
- "ident_case",
- "proc-macro2",
- "quote",
- "strsim 0.10.0",
- "syn 1.0.109",
+ "darling_core",
+ "darling_macro",
 ]
 
 [[package]]
@@ -1220,19 +1196,8 @@ dependencies = [
  "ident_case",
  "proc-macro2",
  "quote",
- "strsim 0.11.1",
- "syn 2.0.102",
-]
-
-[[package]]
-name = "darling_macro"
-version = "0.14.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4aab4dbc9f7611d8b55048a3a16d2d010c2c8334e46304b40ac1cc14bf3b48e"
-dependencies = [
- "darling_core 0.14.4",
- "quote",
- "syn 1.0.109",
+ "strsim",
+ "syn",
 ]
 
 [[package]]
@@ -1241,9 +1206,9 @@ version = "0.20.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc34b93ccb385b40dc71c6fceac4b2ad23662c7eeb248cf10d529b7e055b6ead"
 dependencies = [
- "darling_core 0.20.11",
+ "darling_core",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -1287,7 +1252,7 @@ checksum = "8034092389675178f570469e6c3b0465d3d30b4505c294a6550db47f3c17ad18"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -1302,33 +1267,33 @@ dependencies = [
 
 [[package]]
 name = "derive_builder"
-version = "0.12.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d67778784b508018359cbc8696edb3db78160bab2c2a28ba7f56ef6932997f8"
+checksum = "507dfb09ea8b7fa618fcf76e953f4f5e192547945816d5358edffe39f6f94947"
 dependencies = [
  "derive_builder_macro",
 ]
 
 [[package]]
 name = "derive_builder_core"
-version = "0.12.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c11bdc11a0c47bc7d37d582b5285da6849c96681023680b906673c5707af7b0f"
+checksum = "2d5bcf7b024d6835cfb3d473887cd966994907effbe9227e8c8219824d06c4e8"
 dependencies = [
- "darling 0.14.4",
+ "darling",
  "proc-macro2",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "derive_builder_macro"
-version = "0.12.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebcda35c7a396850a55ffeac740804b40ffec779b98fffbb1738f4033f0ee79e"
+checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c"
 dependencies = [
  "derive_builder_core",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
@@ -1353,23 +1318,23 @@ dependencies = [
 
 [[package]]
 name = "dirs"
-version = "5.0.1"
+version = "6.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
+checksum = "c3e8aa94d75141228480295a7d0e7feb620b1a5ad9f12bc40be62411e38cce4e"
 dependencies = [
  "dirs-sys",
 ]
 
 [[package]]
 name = "dirs-sys"
-version = "0.4.1"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
+checksum = "e01a3366d27ee9890022452ee61b2b63a67e6f13f58900b651ff5665f0bb1fab"
 dependencies = [
  "libc",
  "option-ext",
  "redox_users",
- "windows-sys 0.48.0",
+ "windows-sys 0.60.2",
 ]
 
 [[package]]
@@ -1380,7 +1345,7 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -1400,6 +1365,12 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "dyn-clone"
+version = "1.0.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1c7a8fb8a9fbf66c1f703fe16184d10ca0ee9d23be5b4436400408ba54a95005"
+
 [[package]]
 name = "either"
 version = "1.15.0"
@@ -1682,7 +1653,7 @@ checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -1832,19 +1803,21 @@ checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "hf-hub"
-version = "0.3.2"
+version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b780635574b3d92f036890d8373433d6f9fc7abb320ee42a5c25897fc8ed732"
+checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
 dependencies = [
  "dirs",
+ "http 1.3.1",
  "indicatif",
+ "libc",
  "log",
- "native-tls",
- "rand 0.8.5",
+ "rand 0.9.1",
  "serde",
  "serde_json",
- "thiserror 1.0.69",
+ "thiserror 2.0.12",
  "ureq",
+ "windows-sys 0.60.2",
 ]
 
 [[package]]
@@ -2015,7 +1988,7 @@ dependencies = [
  "http 1.3.1",
  "hyper 1.6.0",
  "hyper-util",
- "rustls 0.23.27",
+ "rustls 0.23.28",
  "rustls-pki-types",
  "tokio",
  "tokio-rustls 0.26.2",
@@ -2515,7 +2488,7 @@ checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -2683,9 +2656,9 @@ dependencies = [
 
 [[package]]
 name = "itertools"
-version = "0.12.1"
+version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
 dependencies = [
  "either",
 ]
@@ -2819,9 +2792,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.172"
+version = "0.2.174"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
+checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
 
 [[package]]
 name = "libm"
@@ -2837,7 +2810,7 @@ checksum = "c0ff37bd590ca25063e35af745c343cb7a0271906fb7b37e4813e8f79f00268d"
 dependencies = [
  "bitflags 2.9.1",
  "libc",
- "redox_syscall 0.5.12",
+ "redox_syscall 0.5.13",
 ]
 
 [[package]]
@@ -2888,11 +2861,11 @@ checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
 
 [[package]]
 name = "lz4_flex"
-version = "0.11.3"
+version = "0.11.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75761162ae2b0e580d7e7c390558127e5f01b4194debd6221fd8c207fc80e3f5"
+checksum = "2c592ad9fbc1b7838633b3ae55ce69b17d01150c72fcef229fbb819d39ee51ee"
 dependencies = [
- "twox-hash",
+ "twox-hash 2.1.1",
 ]
 
 [[package]]
@@ -2992,7 +2965,7 @@ checksum = "c402a4092d5e204f32c9e155431046831fa712637043c58cb73bc6bc6c9663b5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -3019,7 +2992,7 @@ checksum = "254a5372af8fc138e36684761d3c0cdb758a4410e938babcff1c860ce14ddbfc"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -3220,7 +3193,7 @@ checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -3308,7 +3281,7 @@ checksum = "bc838d2a56b5b1a6c25f55575dfc605fabb63bb2365f6c2353ef9159aa69e4a5"
 dependencies = [
  "cfg-if",
  "libc",
- "redox_syscall 0.5.12",
+ "redox_syscall 0.5.13",
  "smallvec",
  "windows-targets 0.52.6",
 ]
@@ -3342,7 +3315,7 @@ dependencies = [
  "simdutf8",
  "snap",
  "thrift",
- "twox-hash",
+ "twox-hash 1.6.3",
  "zstd",
 ]
 
@@ -3368,7 +3341,7 @@ dependencies = [
  "regex",
  "regex-syntax 0.8.5",
  "structmeta",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -3545,22 +3518,21 @@ dependencies = [
 
 [[package]]
 name = "procfs"
-version = "0.16.0"
+version = "0.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "731e0d9356b0c25f16f33b5be79b1c57b562f141ebfcdb0ad8ac2c13a24293b4"
+checksum = "cc5b72d8145275d844d4b5f6d4e1eef00c8cd889edb6035c21675d1bb1f45c9f"
 dependencies = [
  "bitflags 2.9.1",
  "hex",
- "lazy_static",
  "procfs-core",
  "rustix 0.38.44",
 ]
 
 [[package]]
 name = "procfs-core"
-version = "0.16.0"
+version = "0.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2d3554923a69f4ce04c4a754260c338f505ce22642d3830e049a399fc2059a29"
+checksum = "239df02d8349b06fc07398a3a1697b06418223b1c7725085e801e7c0fc6a12ec"
 dependencies = [
  "bitflags 2.9.1",
  "hex",
@@ -3568,9 +3540,9 @@ dependencies = [
 
 [[package]]
 name = "prometheus"
-version = "0.13.4"
+version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d33c28a30771f7f96db69893f78b857f7450d7e0237e9c8fc6427a81bae7ed1"
+checksum = "3ca5326d8d0b950a9acd87e6a3f94745394f62e4dae1b1ee22b2bc0c394af43a"
 dependencies = [
  "cfg-if",
  "fnv",
@@ -3580,14 +3552,28 @@ dependencies = [
  "parking_lot",
  "procfs",
  "protobuf",
- "thiserror 1.0.69",
+ "thiserror 2.0.12",
 ]
 
 [[package]]
 name = "protobuf"
-version = "2.28.0"
+version = "3.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "106dd99e98437432fed6519dedecfade6a06a73bb7b2a1e019fdd2bee5778d94"
+checksum = "d65a1d4ddae7d8b5de68153b48f6aa3bba8cb002b243dbdbc55a5afbc98f99f4"
+dependencies = [
+ "once_cell",
+ "protobuf-support",
+ "thiserror 1.0.69",
+]
+
+[[package]]
+name = "protobuf-support"
+version = "3.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3e36c2f31e0a47f9280fb347ef5e461ffcd2c52dd520d8e216b52f93b0b0d7d6"
+dependencies = [
+ "thiserror 1.0.69",
+]
 
 [[package]]
 name = "quote"
@@ -3600,9 +3586,9 @@ dependencies = [
 
 [[package]]
 name = "r-efi"
-version = "5.2.0"
+version = "5.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
 
 [[package]]
 name = "rand"
@@ -3731,22 +3717,42 @@ dependencies = [
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.12"
+version = "0.5.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "928fca9cf2aa042393a8325b9ead81d2f0df4cb12e1e24cef072922ccd99c5af"
+checksum = "0d04b7d0ee6b4a0207a0a7adb104d23ecb0b47d6beae7152d0fa34b692b29fd6"
 dependencies = [
  "bitflags 2.9.1",
 ]
 
 [[package]]
 name = "redox_users"
-version = "0.4.6"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
+checksum = "dd6f9d3d47bdd2ad6945c5015a226ec6155d0bcdfd8f7cd29f86b71f8de99d2b"
 dependencies = [
  "getrandom 0.2.16",
  "libredox",
- "thiserror 1.0.69",
+ "thiserror 2.0.12",
+]
+
+[[package]]
+name = "ref-cast"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a0ae411dbe946a674d89546582cea4ba2bb8defac896622d6496f14c23ba5cf"
+dependencies = [
+ "ref-cast-impl",
+]
+
+[[package]]
+name = "ref-cast-impl"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1165225c21bff1f3bbce98f5a1f889949bc902d3575308cc7b0de30b4f6d27c7"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -3949,9 +3955,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.27"
+version = "0.23.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
+checksum = "7160e3e10bf4535308537f3c4e1641468cd0e485175d6163087c0393c7d46643"
 dependencies = [
  "log",
  "once_cell",
@@ -3969,7 +3975,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "70cc376c6ba1823ae229bacf8ad93c136d93524eab0e4e5e0e4f96b9c4e5b212"
 dependencies = [
  "log",
- "rustls 0.23.27",
+ "rustls 0.23.28",
  "rustls-native-certs 0.7.3",
  "rustls-pki-types",
  "rustls-webpki 0.103.3",
@@ -4087,6 +4093,18 @@ dependencies = [
  "windows-sys 0.59.0",
 ]
 
+[[package]]
+name = "schemars"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4cd191f9397d57d581cddd31014772520aa448f65ef991055d7f61582c65165f"
+dependencies = [
+ "dyn-clone",
+ "ref-cast",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "scopeguard"
 version = "1.2.0"
@@ -4179,7 +4197,7 @@ checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4212,7 +4230,7 @@ checksum = "175ee3e80ae9982737ca543e96133087cbd9a485eecc3bc4de9c1a37b47ea59c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4229,15 +4247,16 @@ dependencies = [
 
 [[package]]
 name = "serde_with"
-version = "3.12.0"
+version = "3.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d6b6f7f2fcb69f747921f79f3926bd1e203fce4fef62c268dd3abfb6d86029aa"
+checksum = "bf65a400f8f66fb7b0552869ad70157166676db75ed8181f8104ea91cf9d0b42"
 dependencies = [
  "base64 0.22.1",
  "chrono",
  "hex",
  "indexmap 1.9.3",
  "indexmap 2.9.0",
+ "schemars",
  "serde",
  "serde_derive",
  "serde_json",
@@ -4247,14 +4266,14 @@ dependencies = [
 
 [[package]]
 name = "serde_with_macros"
-version = "3.12.0"
+version = "3.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d00caa5193a3c8362ac2b73be6b9e768aa5a4b2f721d8f4b339600c3cb51f8e"
+checksum = "81679d9ed988d5e9a5e6531dc3f2c28efbd639cbd1dfb628df08edea6004da77"
 dependencies = [
- "darling 0.20.11",
+ "darling",
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4337,12 +4356,9 @@ checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e"
 
 [[package]]
 name = "slab"
-version = "0.4.9"
+version = "0.4.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f92a496fb766b417c996b9c5e57daf2f7ad3b0bebe1ccfca4856390e3d3bb67"
-dependencies = [
- "autocfg",
-]
+checksum = "04dc19736151f35336d325007ac991178d504a119863a2fcb3758cdb5e52c50d"
 
 [[package]]
 name = "smallvec"
@@ -4376,6 +4392,17 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "socks"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0c3dbbd9ae980613c6dd8e28a9407b50509d3803b57624d5dfe8315218cd58b"
+dependencies = [
+ "byteorder",
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "spin"
 version = "0.9.8"
@@ -4419,12 +4446,6 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
-[[package]]
-name = "strsim"
-version = "0.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
-
 [[package]]
 name = "strsim"
 version = "0.11.1"
@@ -4440,7 +4461,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "structmeta-derive",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4451,7 +4472,7 @@ checksum = "152a0b65a590ff6c3da95cabe2353ee04e6167c896b28e3b14478c2636c922fc"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4462,20 +4483,9 @@ checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
 
 [[package]]
 name = "syn"
-version = "1.0.109"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
-dependencies = [
- "proc-macro2",
- "quote",
- "unicode-ident",
-]
-
-[[package]]
-name = "syn"
-version = "2.0.102"
+version = "2.0.103"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f6397daf94fa90f058bd0fd88429dd9e5738999cca8d701813c80723add80462"
+checksum = "e4307e30089d6fd6aff212f2da3a1f9e32f3223b1f010fb09b7c95f90f3ca1e8"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -4502,7 +4512,7 @@ checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4607,7 +4617,7 @@ checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4618,17 +4628,16 @@ checksum = "7f7cf42b4507d8ea322120659672cf1b9dbb93f8f2d4ecfd6e51350ff5b17a1d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
 name = "thread_local"
-version = "1.1.8"
+version = "1.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b9ef9bad013ada3808854ceac7b46812a6465ba368859a37e2100283d2d719c"
+checksum = "f60246a4944f24f6e018aa17cdeffb7818b76356965d03b07d6a9886e8962185"
 dependencies = [
  "cfg-if",
- "once_cell",
 ]
 
 [[package]]
@@ -4704,18 +4713,17 @@ dependencies = [
 
 [[package]]
 name = "tokenizers"
-version = "0.15.2"
+version = "0.21.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3dd47962b0ba36e7fd33518fbf1754d136fd1474000162bbf2a8b5fcb2d3654d"
+checksum = "3169b3195f925496c895caee7978a335d49218488ef22375267fba5a46a40bd7"
 dependencies = [
  "aho-corasick",
- "clap",
  "derive_builder",
  "esaxx-rs",
  "getrandom 0.2.16",
  "hf-hub",
  "indicatif",
- "itertools 0.12.1",
+ "itertools 0.13.0",
  "lazy_static",
  "log",
  "macro_rules_attribute",
@@ -4730,7 +4738,7 @@ dependencies = [
  "serde",
  "serde_json",
  "spm_precompiled",
- "thiserror 1.0.69",
+ "thiserror 2.0.12",
  "unicode-normalization-alignments",
  "unicode-segmentation",
  "unicode_categories",
@@ -4773,7 +4781,7 @@ checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4806,7 +4814,7 @@ version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
 dependencies = [
- "rustls 0.23.27",
+ "rustls 0.23.28",
  "tokio",
 ]
 
@@ -4903,13 +4911,13 @@ dependencies = [
 
 [[package]]
 name = "tracing-attributes"
-version = "0.1.29"
+version = "0.1.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b1ffbcf9c6f6b99d386e7444eb608ba646ae452a36b39737deb9663b610f662"
+checksum = "81383ab64e72a7a8b8e13130c49e3dab29def6d0c7d76a03087b3cf71c5c6903"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -4967,6 +4975,12 @@ dependencies = [
  "static_assertions",
 ]
 
+[[package]]
+name = "twox-hash"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b907da542cbced5261bd3256de1b3a1bf340a3d37f93425a07362a1d687de56"
+
 [[package]]
 name = "typenum"
 version = "1.18.0"
@@ -5027,12 +5041,12 @@ dependencies = [
  "base64 0.22.1",
  "flate2",
  "log",
- "native-tls",
  "once_cell",
- "rustls 0.23.27",
+ "rustls 0.23.28",
  "rustls-pki-types",
  "serde",
  "serde_json",
+ "socks",
  "url",
  "webpki-roots 0.26.11",
 ]
@@ -5137,7 +5151,7 @@ dependencies = [
  "log",
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "wasm-bindgen-shared",
 ]
 
@@ -5172,7 +5186,7 @@ checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -5293,7 +5307,7 @@ checksum = "a47fddd13af08290e67f4acabf4b459f647552718f683a7b415d290ac744a836"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -5304,14 +5318,14 @@ checksum = "bd9211b69f8dcdfa817bfd14bf1c97c9188afa36f4750130fcdf3f400eca9fa8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
 name = "windows-link"
-version = "0.1.2"
+version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d3bfe459f85da17560875b8bf1423d6f113b7a87a5d942e7da0ac71be7c61f8b"
+checksum = "5e6ad25900d524eaabdbbb96d20b4311e1e7ae1699af4fb28c17ae66c80d798a"
 
 [[package]]
 name = "windows-result"
@@ -5358,6 +5372,15 @@ dependencies = [
  "windows-targets 0.52.6",
 ]
 
+[[package]]
+name = "windows-sys"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2f500e4d28234f72040990ec9d39e3a6b950f9f22d3dba18416c35882612bcb"
+dependencies = [
+ "windows-targets 0.53.2",
+]
+
 [[package]]
 name = "windows-targets"
 version = "0.48.5"
@@ -5382,13 +5405,29 @@ dependencies = [
  "windows_aarch64_gnullvm 0.52.6",
  "windows_aarch64_msvc 0.52.6",
  "windows_i686_gnu 0.52.6",
- "windows_i686_gnullvm",
+ "windows_i686_gnullvm 0.52.6",
  "windows_i686_msvc 0.52.6",
  "windows_x86_64_gnu 0.52.6",
  "windows_x86_64_gnullvm 0.52.6",
  "windows_x86_64_msvc 0.52.6",
 ]
 
+[[package]]
+name = "windows-targets"
+version = "0.53.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c66f69fcc9ce11da9966ddb31a40968cad001c5bedeb5c2b82ede4253ab48aef"
+dependencies = [
+ "windows_aarch64_gnullvm 0.53.0",
+ "windows_aarch64_msvc 0.53.0",
+ "windows_i686_gnu 0.53.0",
+ "windows_i686_gnullvm 0.53.0",
+ "windows_i686_msvc 0.53.0",
+ "windows_x86_64_gnu 0.53.0",
+ "windows_x86_64_gnullvm 0.53.0",
+ "windows_x86_64_msvc 0.53.0",
+]
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.48.5"
@@ -5401,6 +5440,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86b8d5f90ddd19cb4a147a5fa63ca848db3df085e25fee3cc10b39b6eebae764"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.48.5"
@@ -5413,6 +5458,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7651a1f62a11b8cbd5e0d42526e55f2c99886c77e007179efff86c2b137e66c"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.48.5"
@@ -5425,12 +5476,24 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1dc67659d35f387f5f6c479dc4e28f1d4bb90ddd1a5d3da2e5d97b42d6272c3"
+
 [[package]]
 name = "windows_i686_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
 
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ce6ccbdedbf6d6354471319e781c0dfef054c81fbc7cf83f338a4296c0cae11"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.48.5"
@@ -5443,6 +5506,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "581fee95406bb13382d2f65cd4a908ca7b1e4c2f1917f143ba16efe98a589b5d"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.48.5"
@@ -5455,6 +5524,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2e55b5ac9ea33f2fc1716d1742db15574fd6fc8dadc51caab1c16a3d3b4190ba"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.48.5"
@@ -5467,6 +5542,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0a6e035dd0599267ce1ee132e51c27dd29437f63325753051e71dd9e42406c57"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.48.5"
@@ -5479,6 +5560,12 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
+
 [[package]]
 name = "winreg"
 version = "0.50.0"
@@ -5589,7 +5676,7 @@ checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "synstructure",
 ]
 
@@ -5601,28 +5688,28 @@ checksum = "38da3c9736e16c5d3c8c597a9aaa5d1fa565d0532ae05e27c24aa62fb32c0ab6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "synstructure",
 ]
 
 [[package]]
 name = "zerocopy"
-version = "0.8.25"
+version = "0.8.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1702d9583232ddb9174e01bb7c15a2ab8fb1bc6f227aa1233858c351a3ba0cb"
+checksum = "1039dd0d3c310cf05de012d8a39ff557cb0d23087fd44cad61df08fc31907a2f"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.25"
+version = "0.8.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28a6e20d751156648aa063f3800b706ee209a32c0b4d9f24be3d980b01be55ef"
+checksum = "9ecf5b4cc5364572d7f4c329661bcc82724222973f2cab6f050a4e5c22f75181"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -5642,7 +5729,7 @@ checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
  "synstructure",
 ]
 
@@ -5704,7 +5791,7 @@ checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
@@ -5715,7 +5802,7 @@ checksum = "5b96237efa0c878c64bd89c436f661be4e46b2f3eff1ebb976f7ef2321d2f58f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.102",
+ "syn",
 ]
 
 [[package]]
diff --git a/Cargo.toml b/Cargo.toml
index 6a610d5..bd431e8 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -23,7 +23,7 @@ clap = { version = "4.5.37", features = ["derive"] }
 lapin = { version = "2.5.3", features = ["native-tls"] }
 indicatif = { version = "0.17", features = ["tokio"] }
 axum = "0.7"
-prometheus = { version = "0.13", features = ["process"] }
+prometheus = { version = "0.14", features = ["process"] }
 lazy_static = "1.4" # Or use once_cell which is already present
 tracing = "0.1"
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
@@ -39,7 +39,7 @@ chrono = "0.4.41"
 serde_yaml = "0.9.34"
 whatlang = "0.16.4"
 anyhow = "1.0.98"
-tokenizers = { version = "0.15.2", features = ["http"] } # Specify version and add http feature
+tokenizers = { version = "0.21", features = ["http"] } # Specify version and add http feature
 
 # {{ Define the library (implicitly done by having src/lib.rs) }}
 # [lib]
diff --git a/config/pipeline_config.yaml b/config/pipeline_config.yaml
index afe3e69..8fe9cc1 100644
--- a/config/pipeline_config.yaml
+++ b/config/pipeline_config.yaml
@@ -78,7 +78,7 @@ pipeline:
     short_line_length: 30
     char_duplicates_ratio: 0.01
     new_line_ratio: 0.3
-    language: "da"
+    # language: "da"
 
   - type: TokenCounter
     tokenizer_name: "gpt2"
\ No newline at end of file
diff --git a/src/bin/producer.rs b/src/bin/producer.rs
index 6e115ca..4fc0f45 100644
--- a/src/bin/producer.rs
+++ b/src/bin/producer.rs
@@ -16,8 +16,9 @@ use TextBlaster::data_model::{ProcessingOutcome, TextDocument}; // Import both T
 use TextBlaster::error::{PipelineError, Result}; // Use the library's Result type
 use TextBlaster::pipeline::readers::ParquetReader;
 use TextBlaster::pipeline::writers::parquet_writer::ParquetWriter; // For retry delay
-use TextBlaster::utils::utils::{connect_rabbitmq, setup_prometheus_metrics}; // Updated for shared functions
-                                                                             // axum and TcpListener imports removed as they are now in utils::utils
+use TextBlaster::utils::common::connect_rabbitmq; // Updated for shared functions
+use TextBlaster::utils::prometheus_metrics::setup_prometheus_metrics;
+
 use chrono::Utc; // For consumer tag in aggregate_results
 use TextBlaster::utils::prometheus_metrics::*; // Import shared metrics
 
diff --git a/src/bin/worker.rs b/src/bin/worker.rs
index 4303a5e..b4e7bfe 100644
--- a/src/bin/worker.rs
+++ b/src/bin/worker.rs
@@ -32,14 +32,14 @@ use TextBlaster::pipeline::filters::{
     LanguageDetectionFilter,
 };
 use TextBlaster::pipeline::token::TokenCounter;
+use TextBlaster::utils::common::connect_rabbitmq; // Updated for shared functions
 use TextBlaster::utils::prometheus_metrics::*;
-use TextBlaster::utils::utils::{connect_rabbitmq, setup_prometheus_metrics}; // Using shared setup_prometheus_metrics // Import shared metrics
 
 use std::path::PathBuf;
 use std::sync::Arc; // To share the executor across potential concurrent tasks
                     // {{ Add serde_json for result serialization }}
 use tracing::{debug, error, info, info_span, instrument, warn}; // Added tracing
-use tracing_appender;
+use tracing_appender::{non_blocking, rolling};
 use tracing_subscriber::{fmt, layer::SubscriberExt, util::SubscriberInitExt, EnvFilter, Layer}; // Added tracing_subscriber // Added for file logging
 
 // Define command-line arguments
@@ -152,7 +152,7 @@ fn build_pipeline_from_config(config: &PipelineConfig) -> Result<Vec<Box<dyn Pro
                     params.short_line_length,
                     params.char_duplicates_ratio,
                     params.new_line_ratio,
-                    params.language.clone(),
+                    // params.language.clone(),
                     params.stop_chars.clone(),
                 ))
             }
@@ -286,7 +286,7 @@ async fn process_tasks(
                                                 info!(filtered_doc_id = %document.id, %step_name, %reason, "Document was filtered");
                                                 TASKS_FILTERED_TOTAL.inc(); // Increment filtered counter
                                                 Some(ProcessingOutcome::Filtered {
-                                                    document,
+                                                    document: *document,
                                                     reason,
                                                 })
                                             }
@@ -381,9 +381,9 @@ async fn main() -> Result<()> {
     let env_filter = EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new("info")); // Default to info if RUST_LOG is not set
 
     // Setup file logging
-    let file_appender = tracing_appender::rolling::daily("./log", "worker.log");
+    let file_appender = rolling::daily("./log", "worker.log");
 
-    let (non_blocking_file_writer, _guard) = tracing_appender::non_blocking(file_appender);
+    let (non_blocking_file_writer, _guard) = non_blocking(file_appender);
 
     // Configure the console layer
     let console_layer = fmt::layer()
diff --git a/src/config.rs b/src/config.rs
index 5ea5448..f3fc89f 100644
--- a/src/config.rs
+++ b/src/config.rs
@@ -127,7 +127,7 @@ pub struct FineWebQualityFilterParams {
     pub short_line_length: usize, // serde will handle u64 -> usize if value fits
     pub char_duplicates_ratio: f64,
     pub new_line_ratio: f64,
-    pub language: String,
+    // pub language: String,
 }
 
 // Parameters for the TokenCounter
diff --git a/src/error.rs b/src/error.rs
index 2004fd8..07ee3ff 100644
--- a/src/error.rs
+++ b/src/error.rs
@@ -32,7 +32,7 @@ pub enum PipelineError {
     // {{MODIFIED: Changed 'doc_id: String' to 'document: TextDocument' and updated message}}
     #[error("Document '{document_id}' filtered out: {reason}", document_id = document.id)]
     DocumentFiltered {
-        document: TextDocument,
+        document: Box<TextDocument>,
         reason: String,
     },
 
diff --git a/src/lib.rs b/src/lib.rs
index 2b27d88..4a54396 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1,3 +1,6 @@
+#![allow(non_snake_case)]
+#![allow(clippy::too_many_arguments)]
+
 // Declare the modules that form the library's public API (or internal structure)
 // Using `pub mod` makes them accessible from the binaries using `use rust_data::module_name;`
 pub mod config;
diff --git a/src/pipeline/filters/c4_filters.rs b/src/pipeline/filters/c4_filters.rs
index a1955f0..e1ee629 100644
--- a/src/pipeline/filters/c4_filters.rs
+++ b/src/pipeline/filters/c4_filters.rs
@@ -176,7 +176,7 @@ impl ProcessingStep for C4QualityFilter {
                 .metadata
                 .insert("c4_filter_reasons".to_string(), reasons_string.clone());
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: reasons_string,
             });
         }
@@ -262,7 +262,7 @@ impl ProcessingStep for C4QualityFilter {
                 .metadata
                 .insert("c4_filter_reasons".to_string(), reasons_string.clone());
             Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: reasons_string,
             })
         } else {
@@ -469,7 +469,10 @@ impl ProcessingStep for C4BadWordsFilter {
                 document
                     .metadata
                     .insert("c4_badwords_filter_reason".to_string(), reason.clone());
-                return Err(PipelineError::DocumentFiltered { document, reason });
+                return Err(PipelineError::DocumentFiltered {
+                    document: Box::new(document),
+                    reason,
+                });
             }
         };
 
@@ -511,7 +514,10 @@ impl ProcessingStep for C4BadWordsFilter {
                 document
                     .metadata
                     .insert("c4_badwords_filter_reason".to_string(), reason.clone());
-                Err(PipelineError::DocumentFiltered { document, reason })
+                Err(PipelineError::DocumentFiltered {
+                    document: Box::new(document),
+                    reason,
+                })
             }
         } else {
             // No bad words found
diff --git a/src/pipeline/filters/fineweb_quality.rs b/src/pipeline/filters/fineweb_quality.rs
index acf3958..65edaf6 100644
--- a/src/pipeline/filters/fineweb_quality.rs
+++ b/src/pipeline/filters/fineweb_quality.rs
@@ -36,7 +36,7 @@ pub struct FineWebQualityFilter {
     short_line_length: usize,
     char_duplicates_ratio: f64,
     new_line_ratio: f64,
-    language: String, // Stored, but might not be actively used by utils::text::split_into_words
+    // language: String, // Stored, but might not be actively used by utils::text::split_into_words
 }
 
 impl FineWebQualityFilter {
@@ -47,10 +47,10 @@ impl FineWebQualityFilter {
         short_line_length: usize,
         char_duplicates_ratio: f64,
         new_line_ratio: f64,
-        language: String,
+        // language: String,
         stop_chars: Option<HashSet<char>>,
     ) -> Self {
-        let sc = stop_chars.unwrap_or_else(|| default_stop_chars().iter().map(|&s| s).collect());
+        let sc = stop_chars.unwrap_or_else(|| default_stop_chars().iter().copied().collect());
         FineWebQualityFilter {
             line_punct_thr,
             line_punct_exclude_zero,
@@ -59,7 +59,7 @@ impl FineWebQualityFilter {
             short_line_length,
             char_duplicates_ratio,
             new_line_ratio,
-            language,
+            // language,
         }
     }
 }
@@ -79,7 +79,7 @@ impl ProcessingStep for FineWebQualityFilter {
 
         if lines.is_empty() {
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: "empty".to_string(),
             });
         }
@@ -102,7 +102,7 @@ impl ProcessingStep for FineWebQualityFilter {
             && !(line_punct_actual_ratio == 0.0 && self.line_punct_exclude_zero)
         {
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: format!(
                     "line_punct_ratio: {:.4} < threshold {:.4} (exclude_zero: {})",
                     line_punct_actual_ratio, self.line_punct_thr, self.line_punct_exclude_zero
@@ -118,7 +118,7 @@ impl ProcessingStep for FineWebQualityFilter {
         let short_line_actual_ratio = short_lines_count as f64 / lines.len() as f64;
         if short_line_actual_ratio > self.short_line_thr {
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: format!(
                     "short_line_ratio: {:.4} > threshold {:.4}",
                     short_line_actual_ratio, self.short_line_thr
@@ -136,7 +136,7 @@ impl ProcessingStep for FineWebQualityFilter {
         };
         if char_dup_actual_ratio > self.char_duplicates_ratio {
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: format!(
                     "char_dup_ratio: {:.4} > threshold {:.4}",
                     char_dup_actual_ratio, self.char_duplicates_ratio
@@ -151,7 +151,7 @@ impl ProcessingStep for FineWebQualityFilter {
         if words.is_empty() {
             if new_line_count > 0 {
                 return Err(PipelineError::DocumentFiltered {
-                    document,
+                    document: Box::new(document),
                     reason: "list_ratio_no_words (newlines present but no words)".to_string(),
                 });
             }
@@ -159,7 +159,7 @@ impl ProcessingStep for FineWebQualityFilter {
             let list_actual_ratio = new_line_count as f64 / words.len() as f64;
             if list_actual_ratio > self.new_line_ratio {
                 return Err(PipelineError::DocumentFiltered {
-                    document,
+                    document: Box::new(document),
                     reason: format!(
                         "list_ratio: {:.4} > threshold {:.4}",
                         list_actual_ratio, self.new_line_ratio
@@ -183,7 +183,7 @@ mod tests {
     const DEFAULT_SHORT_LINE_THR: f64 = 0.67;
     const DEFAULT_SHORT_LINE_LENGTH: usize = 30;
     const DEFAULT_NEW_LINE_RATIO: f64 = 0.3;
-    const DEFAULT_LANGUAGE: &str = "english"; // Currently not used by split_into_words if it's new_auto()
+    // const DEFAULT_LANGUAGE: &str = "english"; // Currently not used by split_into_words if it's new_auto()
 
     // Helper to create a default filter instance for tests
     fn default_filter() -> FineWebQualityFilter {
@@ -195,7 +195,7 @@ mod tests {
             short_line_length: DEFAULT_SHORT_LINE_LENGTH,
             char_duplicates_ratio: 0.95, // Temporarily very high to isolate other test failures
             new_line_ratio: DEFAULT_NEW_LINE_RATIO,
-            language: DEFAULT_LANGUAGE.to_string(),
+            // language: DEFAULT_LANGUAGE.to_string(),
         }
     }
 
diff --git a/src/pipeline/filters/gopher_quality.rs b/src/pipeline/filters/gopher_quality.rs
index b7d095d..ad5c27d 100644
--- a/src/pipeline/filters/gopher_quality.rs
+++ b/src/pipeline/filters/gopher_quality.rs
@@ -306,7 +306,7 @@ impl ProcessingStep for GopherQualityFilter {
                 reasons_string.clone(),
             );
             Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: reasons_string,
             })
         } else {
diff --git a/src/pipeline/filters/gopher_rep.rs b/src/pipeline/filters/gopher_rep.rs
index 2f42940..a8a6589 100644
--- a/src/pipeline/filters/gopher_rep.rs
+++ b/src/pipeline/filters/gopher_rep.rs
@@ -238,7 +238,7 @@ impl ProcessingStep for GopherRepetitionFilter {
             );
 
             return Err(PipelineError::DocumentFiltered {
-                document,
+                document: Box::new(document),
                 reason: reasons_string,
             });
         }
diff --git a/src/pipeline/filters/language_filter.rs b/src/pipeline/filters/language_filter.rs
index 620a0c2..f69d366 100644
--- a/src/pipeline/filters/language_filter.rs
+++ b/src/pipeline/filters/language_filter.rs
@@ -46,13 +46,19 @@ impl ProcessingStep for LanguageDetectionFilter {
                 "Document is not any of the following languages: {}",
                 self.allowed_languages.join("; ")
             );
-            Err(PipelineError::DocumentFiltered { document, reason })
+            Err(PipelineError::DocumentFiltered {
+                document: Box::new(document),
+                reason,
+            })
         } else if confidence < self.min_confidence {
             let reason = format!(
                 "Language detection confidence is not satified: {} < {}",
                 confidence, self.min_confidence
             );
-            Err(PipelineError::DocumentFiltered { document, reason })
+            Err(PipelineError::DocumentFiltered {
+                document: Box::new(document),
+                reason,
+            })
         } else {
             Ok(document)
         }
diff --git a/src/pipeline/mod.rs b/src/pipeline/mod.rs
index e8f5fe2..b364380 100644
--- a/src/pipeline/mod.rs
+++ b/src/pipeline/mod.rs
@@ -2,8 +2,8 @@
 
 pub mod filters;
 pub mod readers;
-pub mod writers;
-pub mod token; // Added new module
+pub mod token;
+pub mod writers; // Added new module
 
 // Potentially other pipeline related items, traits, etc.
 // e.g., pub trait PipelineStep {}
diff --git a/src/pipeline/writers/parquet_writer.rs b/src/pipeline/writers/parquet_writer.rs
index 5e4ab42..0b8487d 100644
--- a/src/pipeline/writers/parquet_writer.rs
+++ b/src/pipeline/writers/parquet_writer.rs
@@ -10,7 +10,7 @@ use std::sync::Arc; // For serializing metadata
 // Assuming your error module and Result type are defined like this
 // Adjust the import path if necessary
 use crate::data_model::TextDocument;
-use crate::error::Result;
+use crate::error::{PipelineError, Result};
 
 // Define the schema for TextDocument
 fn create_schema() -> SchemaRef {
@@ -59,7 +59,9 @@ impl ParquetWriter {
         if self.writer.is_none() {
             // Handle error: writer was already closed or failed to initialize
             // You might want a more specific error type here
-            return Err(std::io::Error::new(std::io::ErrorKind::Other, "Writer is closed").into());
+            return Err(PipelineError::Unexpected(
+                "The parquet writer was already closed".to_string(),
+            ));
         }
 
         // 1. Convert TextDocuments to Arrow Arrays
diff --git a/src/utils/common.rs b/src/utils/common.rs
new file mode 100644
index 0000000..dd910d4
--- /dev/null
+++ b/src/utils/common.rs
@@ -0,0 +1,35 @@
+// src/utils/utils.rs
+
+use lapin::{Connection, ConnectionProperties, Result as LapinResult};
+use std::time::Duration;
+use tokio::time::sleep;
+use tracing::{error, info};
+
+// Helper function to connect to RabbitMQ with retry (already here)
+pub async fn connect_rabbitmq(addr: &str) -> LapinResult<Connection> {
+    let options = ConnectionProperties::default()
+        .with_executor(tokio_executor_trait::Tokio::current())
+        .with_reactor(tokio_reactor_trait::Tokio);
+
+    let mut attempts = 0;
+    loop {
+        match Connection::connect(addr, options.clone()).await {
+            Ok(conn) => {
+                info!("Successfully connected to RabbitMQ at {}", addr);
+                return Ok(conn);
+            }
+            Err(e) => {
+                attempts += 1;
+                error!(
+                    attempt = attempts,
+                    error = %e,
+                    "Failed to connect to RabbitMQ. Retrying in 5 seconds..."
+                );
+                if attempts >= 5 {
+                    return Err(e);
+                }
+                sleep(Duration::from_secs(5)).await;
+            }
+        }
+    }
+}
diff --git a/src/utils/mod.rs b/src/utils/mod.rs
index 89723d9..c227a9e 100644
--- a/src/utils/mod.rs
+++ b/src/utils/mod.rs
@@ -1,8 +1,8 @@
 // Utils
 
+pub mod common;
 pub mod prometheus_metrics;
-pub mod text;
-pub mod utils; // Added to declare the utils.rs module // Added to declare the prometheus_metrics.rs module
+pub mod text; // Added to declare the common.rs module
 
 pub use text::{
     find_all_duplicate, find_duplicates, find_top_duplicate, get_n_grams, split_into_sentences,
diff --git a/src/utils/prometheus_metrics.rs b/src/utils/prometheus_metrics.rs
index ee0c2b9..f5a4bb9 100644
--- a/src/utils/prometheus_metrics.rs
+++ b/src/utils/prometheus_metrics.rs
@@ -1,7 +1,16 @@
 // src/utils/prometheus_metrics.rs
 
+use tracing::{error, info};
+
+use crate::error::Result;
+use axum::{http::StatusCode, routing::get, serve, Router};
+use tokio::net::TcpListener; // Assuming Result is crate::error::Result for PipelineError
+
 use once_cell::sync::Lazy;
-use prometheus::{register_counter, register_gauge, register_histogram, Counter, Gauge, Histogram};
+use prometheus::{
+    gather, register_counter, register_gauge, register_histogram, Counter, Encoder, Gauge,
+    Histogram, TextEncoder,
+};
 
 // Metrics from Producer
 pub static TASKS_PUBLISHED_TOTAL: Lazy<Counter> = Lazy::new(|| {
@@ -132,3 +141,61 @@ pub static ACTIVE_PROCESSING_TASKS: Lazy<Gauge> = Lazy::new(|| {
     )
     .expect("Failed to register worker_active_processing_tasks gauge")
 });
+
+// Axum handler for /metrics
+// This function needs to be async as it's used as an Axum handler.
+// It's kept non-public as it's an internal detail of setup_prometheus_metrics.
+async fn metrics_handler() -> (StatusCode, String) {
+    let encoder = TextEncoder::new();
+    let mut buffer = vec![];
+    if let Err(e) = encoder.encode(&gather(), &mut buffer) {
+        error!("Could not encode prometheus metrics: {}", e);
+        return (
+            StatusCode::INTERNAL_SERVER_ERROR,
+            format!("Could not encode prometheus metrics: {}", e),
+        );
+    }
+    match String::from_utf8(buffer) {
+        Ok(s) => (StatusCode::OK, s),
+        Err(e) => {
+            error!("Prometheus metrics UTF-8 error: {}", e);
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Prometheus metrics UTF-8 error: {}", e),
+            )
+        }
+    }
+}
+
+// Function to setup Prometheus metrics endpoint
+// This function is now public to be used by binaries.
+pub async fn setup_prometheus_metrics(metrics_port: Option<u16>) -> Result<()> {
+    if let Some(port) = metrics_port {
+        let app = Router::new().route("/metrics", get(metrics_handler));
+        let listener_addr = format!("0.0.0.0:{}", port);
+        info!(
+            "Metrics endpoint will be available at http://{}/metrics",
+            listener_addr
+        );
+
+        tokio::spawn(async move {
+            match TcpListener::bind(&listener_addr).await {
+                Ok(listener) => {
+                    if let Err(e) = serve(listener, app).await {
+                        error!("Metrics server error: {}", e);
+                    }
+                }
+                Err(e) => {
+                    error!("Failed to bind metrics server to {}: {}", listener_addr, e);
+                    // This error is within a spawned task, so we can't directly bubble it up
+                    // with `?` from setup_prometheus_metrics. Logging is appropriate.
+                    // Consider if this should return an error that prevents server startup.
+                }
+            }
+        });
+        Ok(())
+    } else {
+        info!("Prometheus metrics endpoint not configured (no port specified).");
+        Ok(())
+    }
+}
diff --git a/src/utils/text.rs b/src/utils/text.rs
index 6307e23..802ded4 100644
--- a/src/utils/text.rs
+++ b/src/utils/text.rs
@@ -110,9 +110,10 @@ pub fn split_into_words(text: &str) -> Vec<&str> {
 
     // segment_str() returns an iterator over break points (usize byte offsets).
     // A segment is the text between two consecutive break points.
-    let mut breaks_iter = segmenter.segment_str(text).peekable();
+    let breaks_iter = segmenter.segment_str(text).peekable();
 
-    while let Some(current_break) = breaks_iter.next() {
+    for current_break in breaks_iter {
+        // while let Some(current_break) = breaks_iter.next() {
         if current_break > prev_break {
             let segment_candidate = &text[prev_break..current_break];
 
diff --git a/src/utils/utils.rs b/src/utils/utils.rs
deleted file mode 100644
index ef2e74d..0000000
--- a/src/utils/utils.rs
+++ /dev/null
@@ -1,98 +0,0 @@
-// src/utils/utils.rs
-
-use lapin::{Connection, ConnectionProperties, Result as LapinResult};
-use std::time::Duration;
-use tokio::time::sleep;
-use tracing::{error, info};
-
-use crate::error::Result;
-use axum::{http::StatusCode, routing::get, serve, Router};
-use prometheus::{gather, Encoder, TextEncoder};
-use tokio::net::TcpListener; // Assuming Result is crate::error::Result for PipelineError
-
-// Helper function to connect to RabbitMQ with retry (already here)
-pub async fn connect_rabbitmq(addr: &str) -> LapinResult<Connection> {
-    let options = ConnectionProperties::default()
-        .with_executor(tokio_executor_trait::Tokio::current())
-        .with_reactor(tokio_reactor_trait::Tokio);
-
-    let mut attempts = 0;
-    loop {
-        match Connection::connect(addr, options.clone()).await {
-            Ok(conn) => {
-                info!("Successfully connected to RabbitMQ at {}", addr);
-                return Ok(conn);
-            }
-            Err(e) => {
-                attempts += 1;
-                error!(
-                    attempt = attempts,
-                    error = %e,
-                    "Failed to connect to RabbitMQ. Retrying in 5 seconds..."
-                );
-                if attempts >= 5 {
-                    return Err(e);
-                }
-                sleep(Duration::from_secs(5)).await;
-            }
-        }
-    }
-}
-
-// Axum handler for /metrics
-// This function needs to be async as it's used as an Axum handler.
-// It's kept non-public as it's an internal detail of setup_prometheus_metrics.
-async fn metrics_handler() -> (StatusCode, String) {
-    let encoder = TextEncoder::new();
-    let mut buffer = vec![];
-    if let Err(e) = encoder.encode(&gather(), &mut buffer) {
-        error!("Could not encode prometheus metrics: {}", e);
-        return (
-            StatusCode::INTERNAL_SERVER_ERROR,
-            format!("Could not encode prometheus metrics: {}", e),
-        );
-    }
-    match String::from_utf8(buffer) {
-        Ok(s) => (StatusCode::OK, s),
-        Err(e) => {
-            error!("Prometheus metrics UTF-8 error: {}", e);
-            (
-                StatusCode::INTERNAL_SERVER_ERROR,
-                format!("Prometheus metrics UTF-8 error: {}", e),
-            )
-        }
-    }
-}
-
-// Function to setup Prometheus metrics endpoint
-// This function is now public to be used by binaries.
-pub async fn setup_prometheus_metrics(metrics_port: Option<u16>) -> Result<()> {
-    if let Some(port) = metrics_port {
-        let app = Router::new().route("/metrics", get(metrics_handler));
-        let listener_addr = format!("0.0.0.0:{}", port);
-        info!(
-            "Metrics endpoint will be available at http://{}/metrics",
-            listener_addr
-        );
-
-        tokio::spawn(async move {
-            match TcpListener::bind(&listener_addr).await {
-                Ok(listener) => {
-                    if let Err(e) = serve(listener, app).await {
-                        error!("Metrics server error: {}", e);
-                    }
-                }
-                Err(e) => {
-                    error!("Failed to bind metrics server to {}: {}", listener_addr, e);
-                    // This error is within a spawned task, so we can't directly bubble it up
-                    // with `?` from setup_prometheus_metrics. Logging is appropriate.
-                    // Consider if this should return an error that prevents server startup.
-                }
-            }
-        });
-        Ok(())
-    } else {
-        info!("Prometheus metrics endpoint not configured (no port specified).");
-        Ok(())
-    }
-}