diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 0f609e86116..e0732d6ef2b 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -136,6 +136,18 @@ jobs:
         if: always() && steps.tests.outputs.has-rust == 'true'
         run: sudo apt install protobuf-compiler
 
+      - name: Install PDFium
+        if: matrix.package == '@rust/chonky'
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          temp_dir=$(mktemp -d)
+          gh release download chromium/6721 --repo bblanchon/pdfium-binaries --pattern 'pdfium-linux-x64.tgz' --dir $temp_dir
+          tar -xzf $temp_dir/pdfium-linux-x64.tgz -C $temp_dir
+          mv $temp_dir/lib/* "${{ matrix.directory }}/libs/"
+          rm -rf $temp_dir
+          echo "PDFIUM_DYNAMIC_LIB_PATH=$(pwd)/${{ matrix.directory }}/libs/" >> $GITHUB_ENV
+
       - name: Install Rust toolchain
         if: always() && steps.tests.outputs.has-rust == 'true'
         uses: ./.github/actions/install-rust-toolchain
@@ -269,6 +281,18 @@ jobs:
       - name: Install Protobuf
         run: sudo apt install protobuf-compiler
 
+      - name: Install PDFium
+        if: matrix.package == '@rust/chonky'
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          temp_dir=$(mktemp -d)
+          gh release download chromium/6721 --repo bblanchon/pdfium-binaries --pattern 'pdfium-linux-x64.tgz' --dir $temp_dir
+          tar -xzf $temp_dir/pdfium-linux-x64.tgz -C $temp_dir
+          mv $temp_dir/lib/* "${{ matrix.directory }}/libs/"
+          rm -rf $temp_dir
+          echo "PDFIUM_DYNAMIC_LIB_PATH=$(pwd)/${{ matrix.directory }}/libs/" >> $GITHUB_ENV
+
       - name: Install playwright
         if: matrix.package == '@tests/hash-playwright'
         uses: nick-fields/retry@7152eba30c6575329ac0576536151aca5a72780e # v3.0.0
diff --git a/Cargo.lock b/Cargo.lock
index 3d82f7082be..fbcaa499fdb 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -75,6 +75,12 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "aligned-vec"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4aa90d7ce82d4be67b64039a3d588d38dbcc6736577de4a847025ce5b0c468d1"
+
 [[package]]
 name = "allocator-api2"
 version = "0.2.18"
@@ -193,6 +199,23 @@ dependencies = [
  "num-traits",
 ]
 
+[[package]]
+name = "arbitrary"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dde20b3d026af13f561bdd0f15edf01fc734f0dafcedbaf42bba506a9517f223"
+
+[[package]]
+name = "arg_enum_proc_macro"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ae92a5119aa49cdbcf6b9f893fe4e1d98b04ccbf82ee0584ad948a44a734dea"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.87",
+]
+
 [[package]]
 name = "ariadne"
 version = "0.5.0"
@@ -374,6 +397,29 @@ version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
 
+[[package]]
+name = "av1-grain"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6678909d8c5d46a42abcf571271e15fdbc0a225e3646cf23762cd415046c78bf"
+dependencies = [
+ "anyhow",
+ "arrayvec",
+ "log",
+ "nom",
+ "num-rational",
+ "v_frame",
+]
+
+[[package]]
+name = "avif-serialize"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e335041290c43101ca215eed6f43ec437eb5a42125573f600fc3fa42b9bddd62"
+dependencies = [
+ "arrayvec",
+]
+
 [[package]]
 name = "aws-config"
 version = "1.5.10"
@@ -936,6 +982,12 @@ version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5e764a1d40d510daf35e07be9eb06e75770908c27d411ee6c92109c9840eaaf7"
 
+[[package]]
+name = "bit_field"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc827186963e592360843fb5ba4b973e145841266c1357f7180c43526f2e5b61"
+
 [[package]]
 name = "bitflags"
 version = "1.3.2"
@@ -948,6 +1000,12 @@ version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
 
+[[package]]
+name = "bitstream-io"
+version = "2.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c12d1856e42f0d817a835fe55853957c85c8c8a470114029143d3f12671446e"
+
 [[package]]
 name = "bitvec"
 version = "1.0.1"
@@ -993,6 +1051,12 @@ dependencies = [
  "tinyvec",
 ]
 
+[[package]]
+name = "built"
+version = "0.7.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c360505aed52b7ec96a3636c3f039d99103c37d1d9b4f7a8c743d3ea9ffcd03b"
+
 [[package]]
 name = "bumpalo"
 version = "3.16.0"
@@ -1017,6 +1081,12 @@ version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
 
+[[package]]
+name = "byteorder-lite"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
+
 [[package]]
 name = "bytes"
 version = "1.8.0"
@@ -1080,9 +1150,21 @@ version = "1.1.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2e80e3b6a3ab07840e1cae9b0666a63970dc28e8ed5ffbcdacbfc760c281bfc1"
 dependencies = [
+ "jobserver",
+ "libc",
  "shlex",
 ]
 
+[[package]]
+name = "cfg-expr"
+version = "0.15.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d067ad48b8650848b989a59a86c6c36a995d02d2bf778d45c3c5d57bc2718f02"
+dependencies = [
+ "smallvec",
+ "target-lexicon",
+]
+
 [[package]]
 name = "cfg-if"
 version = "1.0.0"
@@ -1118,19 +1200,25 @@ name = "chonky"
 version = "0.0.0"
 dependencies = [
  "error-stack",
+ "image 0.24.9",
+ "insta",
+ "pdfium-render",
+ "thiserror 2.0.3",
 ]
 
 [[package]]
 name = "chrono"
-version = "0.4.38"
+version = "0.4.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a21f936df1771bf62b77f047b726c4625ff2e8aa607c01ec06e5a05bd8463401"
+checksum = "7f2c685bad3eb3d45a01354cedb7d5faa66194d1d58ba6e267a8de788f79db38"
 dependencies = [
  "android-tzdata",
  "iana-time-zone",
+ "js-sys",
  "num-traits",
  "serde",
- "windows-targets 0.52.6",
+ "wasm-bindgen",
+ "windows-targets 0.48.5",
 ]
 
 [[package]]
@@ -1221,6 +1309,12 @@ version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1462739cb27611015575c0c11df5df7601141071f07518d56fcc1be504cbec97"
 
+[[package]]
+name = "color_quant"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b"
+
 [[package]]
 name = "colorchoice"
 version = "1.0.2"
@@ -1258,6 +1352,16 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "console_log"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be8aed40e4edbf4d3b4431ab260b63fdc40f5780a4766824329ea0f1eefe3c0f"
+dependencies = [
+ "log",
+ "web-sys",
+]
+
 [[package]]
 name = "const-oid"
 version = "0.9.6"
@@ -2020,6 +2124,21 @@ dependencies = [
  "once_cell",
 ]
 
+[[package]]
+name = "exr"
+version = "1.73.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f83197f59927b46c04a183a619b7c29df34e63e63c7869320862268c0ef687e0"
+dependencies = [
+ "bit_field",
+ "half",
+ "lebe",
+ "miniz_oxide",
+ "rayon-core",
+ "smallvec",
+ "zune-inflate",
+]
+
 [[package]]
 name = "eyre"
 version = "0.6.12"
@@ -2053,6 +2172,15 @@ version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e8c02a5121d4ea3eb16a80748c74f5549a5665e4c21333c6098f283870fbdea6"
 
+[[package]]
+name = "fdeflate"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8090f921a24b04994d9929e204f50b498a33ea6ba559ffaa05e04f7ee7fb5ab"
+dependencies = [
+ "simd-adler32",
+]
+
 [[package]]
 name = "fiat-crypto"
 version = "0.2.9"
@@ -2077,6 +2205,16 @@ version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80"
 
+[[package]]
+name = "flate2"
+version = "1.0.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1b589b4dc103969ad3cf85c950899926ec64300a1a46d76c03a6072957036f0"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "fluent-uri"
 version = "0.3.2"
@@ -2365,6 +2503,16 @@ dependencies = [
  "polyval",
 ]
 
+[[package]]
+name = "gif"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3fb2d69b19215e18bb912fa30f7ce15846e301408695e44e0ef719f1da9e19f2"
+dependencies = [
+ "color_quant",
+ "weezl",
+]
+
 [[package]]
 name = "gimli"
 version = "0.31.1"
@@ -3556,6 +3704,58 @@ dependencies = [
  "xmltree",
 ]
 
+[[package]]
+name = "image"
+version = "0.24.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5690139d2f55868e080017335e4b94cb7414274c74f1669c84fb5feba2c9f69d"
+dependencies = [
+ "bytemuck",
+ "byteorder",
+ "color_quant",
+ "num-traits",
+ "png",
+]
+
+[[package]]
+name = "image"
+version = "0.25.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd6f44aed642f18953a158afeb30206f4d50da59fbc66ecb53c66488de73563b"
+dependencies = [
+ "bytemuck",
+ "byteorder-lite",
+ "color_quant",
+ "exr",
+ "gif",
+ "image-webp",
+ "num-traits",
+ "png",
+ "qoi",
+ "ravif",
+ "rayon",
+ "rgb",
+ "tiff",
+ "zune-core",
+ "zune-jpeg",
+]
+
+[[package]]
+name = "image-webp"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e031e8e3d94711a9ccb5d6ea357439ef3dcbed361798bd4071dc4d9793fbe22f"
+dependencies = [
+ "byteorder-lite",
+ "quick-error 2.0.1",
+]
+
+[[package]]
+name = "imgref"
+version = "1.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0263a3d970d5c054ed9312c0057b4f3bde9c0b33836d3637361d4a9e6e7a408"
+
 [[package]]
 name = "include_dir"
 version = "0.7.4"
@@ -3653,6 +3853,17 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "interpolate_name"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c34819042dc3d3971c46c2190835914dfbe0c3c13f61449b2997f4e9722dfa60"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.87",
+]
+
 [[package]]
 name = "inventory"
 version = "0.3.15"
@@ -3718,6 +3929,15 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itertools"
 version = "0.13.0"
@@ -3733,6 +3953,21 @@ version = "1.0.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
 
+[[package]]
+name = "jobserver"
+version = "0.1.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48d1dbcbbeb6a7fec7e059840aa538bd62aaccf972c7346c4d9d2059312853d0"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "jpeg-decoder"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f5d4a7da358eff58addd2877a45865158f0d78c911d43a5784ceb7bbf52833b0"
+
 [[package]]
 name = "js-sys"
 version = "0.3.72"
@@ -3797,6 +4032,12 @@ version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
 
+[[package]]
+name = "lebe"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "03087c2bad5e1034e8cace5926dec053fb3790248370865f5117a7d0213354c8"
+
 [[package]]
 name = "lexical"
 version = "7.0.2"
@@ -3876,6 +4117,26 @@ version = "0.2.159"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "561d97a539a36e26a9a5fad1ea11a3039a67714694aaa379433e580854bc3dc5"
 
+[[package]]
+name = "libfuzzer-sys"
+version = "0.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b9569d2f74e257076d8c6bfa73fb505b46b851e51ddaecc825944aa3bed17fa"
+dependencies = [
+ "arbitrary",
+ "cc",
+]
+
+[[package]]
+name = "libloading"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
+dependencies = [
+ "cfg-if",
+ "windows-targets 0.52.6",
+]
+
 [[package]]
 name = "libm"
 version = "0.2.8"
@@ -4331,6 +4592,15 @@ dependencies = [
  "tracing-subscriber",
 ]
 
+[[package]]
+name = "loop9"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fae87c125b03c1d2c0150c90365d7d6bcc53fb73a9acaef207d2d065860f062"
+dependencies = [
+ "imgref",
+]
+
 [[package]]
 name = "lru"
 version = "0.12.5"
@@ -4370,6 +4640,22 @@ version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0e7465ac9959cc2b1404e8e2367b43684a6d13790fe23056cc8c6c5a6b7bcb94"
 
+[[package]]
+name = "maybe-owned"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4facc753ae494aeb6e3c22f839b158aebd4f9270f55cd3c79906c45476c47ab4"
+
+[[package]]
+name = "maybe-rayon"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ea1f30cedd69f0a2954655f7188c6a834246d2bcf1e315e2ac40c4b24dc9519"
+dependencies = [
+ "cfg-if",
+ "rayon",
+]
+
 [[package]]
 name = "md-5"
 version = "0.10.6"
@@ -4424,6 +4710,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
 dependencies = [
  "adler2",
+ "simd-adler32",
 ]
 
 [[package]]
@@ -4564,6 +4851,12 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "new_debug_unreachable"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
+
 [[package]]
 name = "nix"
 version = "0.24.3"
@@ -4591,6 +4884,12 @@ dependencies = [
  "minimal-lexical",
 ]
 
+[[package]]
+name = "noop_proc_macro"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0676bb32a98c1a483ce53e500a81ad9c3d5b3f7c920c28c24e9cb0980d0b5bc8"
+
 [[package]]
 name = "nu-ansi-term"
 version = "0.46.0"
@@ -4646,6 +4945,17 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9"
 
+[[package]]
+name = "num-derive"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed3955f1a9c7c0c15e092f9c887db08b1fc683305fdf6eb6684f22555355e202"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.87",
+]
+
 [[package]]
 name = "num-format"
 version = "0.4.4"
@@ -5005,6 +5315,32 @@ version = "1.0.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a"
 
+[[package]]
+name = "pdfium-render"
+version = "0.8.26"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc9b3c6a3e32b3745bee220a4d3e77e284db1cf57b0361f94509a8821cfd920f"
+dependencies = [
+ "bitflags 2.6.0",
+ "bytemuck",
+ "bytes",
+ "chrono",
+ "console_error_panic_hook",
+ "console_log",
+ "image 0.25.5",
+ "itertools 0.13.0",
+ "js-sys",
+ "libloading",
+ "log",
+ "maybe-owned",
+ "once_cell",
+ "utf16string",
+ "vecmath",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
 [[package]]
 name = "pem"
 version = "3.0.4"
@@ -5081,6 +5417,12 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
+[[package]]
+name = "piston-float"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad78bf43dcf80e8f950c92b84f938a0fc7590b7f6866fbcbeca781609c115590"
+
 [[package]]
 name = "pkcs8"
 version = "0.10.2"
@@ -5091,6 +5433,12 @@ dependencies = [
  "spki",
 ]
 
+[[package]]
+name = "pkg-config"
+version = "0.3.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2"
+
 [[package]]
 name = "plotters"
 version = "0.3.7"
@@ -5119,6 +5467,19 @@ dependencies = [
  "plotters-backend",
 ]
 
+[[package]]
+name = "png"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52f9d46a34a05a6a57566bc2bfae066ef07585a6e3fa30fbbdff5936380623f0"
+dependencies = [
+ "bitflags 1.3.2",
+ "crc32fast",
+ "fdeflate",
+ "flate2",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "polling"
 version = "3.7.3"
@@ -5281,6 +5642,25 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "profiling"
+version = "1.0.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "afbdc74edc00b6f6a218ca6a5364d6226a259d4b8ea1af4a0ea063f27e179f4d"
+dependencies = [
+ "profiling-procmacros",
+]
+
+[[package]]
+name = "profiling-procmacros"
+version = "1.0.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a65f2e60fbf1063868558d69c6beacf412dc755f9fc020f514b7955fc914fe30"
+dependencies = [
+ "quote",
+ "syn 2.0.87",
+]
+
 [[package]]
 name = "prometheus-client"
 version = "0.22.3"
@@ -5443,12 +5823,27 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "qoi"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f6d64c71eb498fe9eae14ce4ec935c555749aef511cca85b5568910d6e48001"
+dependencies = [
+ "bytemuck",
+]
+
 [[package]]
 name = "quick-error"
 version = "1.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
 
+[[package]]
+name = "quick-error"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
+
 [[package]]
 name = "quick-protobuf"
 version = "0.8.1"
@@ -5583,6 +5978,56 @@ dependencies = [
  "rand_core",
 ]
 
+[[package]]
+name = "rav1e"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd87ce80a7665b1cce111f8a16c1f3929f6547ce91ade6addf4ec86a8dda5ce9"
+dependencies = [
+ "arbitrary",
+ "arg_enum_proc_macro",
+ "arrayvec",
+ "av1-grain",
+ "bitstream-io",
+ "built",
+ "cfg-if",
+ "interpolate_name",
+ "itertools 0.12.1",
+ "libc",
+ "libfuzzer-sys",
+ "log",
+ "maybe-rayon",
+ "new_debug_unreachable",
+ "noop_proc_macro",
+ "num-derive",
+ "num-traits",
+ "once_cell",
+ "paste",
+ "profiling",
+ "rand",
+ "rand_chacha",
+ "simd_helpers",
+ "system-deps",
+ "thiserror 1.0.69",
+ "v_frame",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "ravif"
+version = "0.11.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2413fd96bd0ea5cdeeb37eaf446a22e6ed7b981d792828721e74ded1980a45c6"
+dependencies = [
+ "avif-serialize",
+ "imgref",
+ "loop9",
+ "quick-error 2.0.1",
+ "rav1e",
+ "rayon",
+ "rgb",
+]
+
 [[package]]
 name = "rayon"
 version = "1.10.0"
@@ -5802,7 +6247,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "52e44394d2086d010551b14b53b1f24e31647570cd1deb0379e2c21b329aba00"
 dependencies = [
  "hostname 0.3.1",
- "quick-error",
+ "quick-error 1.2.3",
 ]
 
 [[package]]
@@ -6448,6 +6893,21 @@ dependencies = [
  "rand_core",
 ]
 
+[[package]]
+name = "simd-adler32"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d66dc143e6b11c1eddc06d5c423cfc97062865baf299914ab64caa38182078fe"
+
+[[package]]
+name = "simd_helpers"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95890f873bec569a0362c235787f3aca6e1e887302ba4840839bcc6459c42da6"
+dependencies = [
+ "quote",
+]
+
 [[package]]
 name = "similar"
 version = "2.6.0"
@@ -6698,6 +7158,19 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "system-deps"
+version = "6.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3e535eb8dded36d55ec13eddacd30dec501792ff23a0b1682c38601b8cf2349"
+dependencies = [
+ "cfg-expr",
+ "heck 0.5.0",
+ "pkg-config",
+ "toml",
+ "version-compare",
+]
+
 [[package]]
 name = "tachyonix"
 version = "0.3.1"
@@ -6717,6 +7190,12 @@ version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "55937e1799185b12863d447f42597ed69d9928686b8d88a1df17376a097d8369"
 
+[[package]]
+name = "target-lexicon"
+version = "0.12.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
+
 [[package]]
 name = "target-triple"
 version = "0.1.3"
@@ -7002,6 +7481,17 @@ dependencies = [
  "once_cell",
 ]
 
+[[package]]
+name = "tiff"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba1310fcea54c6a9a4fd1aad794ecc02c31682f6bfbecdf460bf19533eed1e3e"
+dependencies = [
+ "flate2",
+ "jpeg-decoder",
+ "weezl",
+]
+
 [[package]]
 name = "time"
 version = "0.3.36"
@@ -7777,6 +8267,15 @@ version = "2.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "daf8dba3b7eb870caf1ddeed7bc9d2a049f3cfdfae7cb521b087cc33ae4c49da"
 
+[[package]]
+name = "utf16string"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b62a1e85e12d5d712bf47a85f426b73d303e2d00a90de5f3004df3596e9d216"
+dependencies = [
+ "byteorder",
+]
+
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -7837,12 +8336,38 @@ dependencies = [
  "vsimd",
 ]
 
+[[package]]
+name = "v_frame"
+version = "0.3.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6f32aaa24bacd11e488aa9ba66369c7cd514885742c9fe08cfe85884db3e92b"
+dependencies = [
+ "aligned-vec",
+ "num-traits",
+ "wasm-bindgen",
+]
+
 [[package]]
 name = "valuable"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "830b7e5d4d90034032940e4ace0d9a9a057e7a45cd94e6c007832e39edb82f6d"
 
+[[package]]
+name = "vecmath"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "956ae1e0d85bca567dee1dcf87fb1ca2e792792f66f87dced8381f99cd91156a"
+dependencies = [
+ "piston-float",
+]
+
+[[package]]
+name = "version-compare"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "852e951cb7832cb45cb1169900d19760cfa39b82bc0ea9c0e5a14ae88411c98b"
+
 [[package]]
 name = "version_check"
 version = "0.9.5"
@@ -8035,6 +8560,12 @@ dependencies = [
  "rustls-pki-types",
 ]
 
+[[package]]
+name = "weezl"
+version = "0.1.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53a85b86a771b1c87058196170769dd264f66c0782acf1ae6cc51bfd64b39082"
+
 [[package]]
 name = "which"
 version = "4.4.2"
@@ -8484,3 +9015,27 @@ dependencies = [
  "quote",
  "syn 2.0.87",
 ]
+
+[[package]]
+name = "zune-core"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f423a2c17029964870cfaabb1f13dfab7d092a62a29a89264f4d36990ca414a"
+
+[[package]]
+name = "zune-inflate"
+version = "0.2.54"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73ab332fe2f6680068f3582b16a24f90ad7096d5d39b974d1c0aff0125116f02"
+dependencies = [
+ "simd-adler32",
+]
+
+[[package]]
+name = "zune-jpeg"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16099418600b4d8f028622f73ff6e3deaabdff330fb9a2a131dea781ee8b0768"
+dependencies = [
+ "zune-core",
+]
diff --git a/Cargo.toml b/Cargo.toml
index bff09f7c976..05478f2c399 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -111,6 +111,7 @@ futures-sink       = { version = "=0.3.31", default-features = false }
 futures-util       = { version = "=0.3.31", default-features = false }
 hashbrown          = { version = "=0.15.1", default-features = false, features = ["inline-more", "nightly"] }
 http               = { version = "=1.1.0", default-features = false }
+image              = { version = "0.24.9", default-features = false }
 inferno            = { version = "=0.11.21", default-features = false }
 iso8601-duration   = { version = "=0.2.0", default-features = false }
 json-number        = { version = "=0.4.9", default-features = false }
@@ -122,6 +123,7 @@ libp2p-swarm       = { version = "=0.45.1", default-features = false }
 libp2p-yamux       = { version = "=0.46.0", default-features = false }
 multiaddr          = { version = "=0.18.2", default-features = false }
 multistream-select = { version = "=0.13.0", default-features = false }
+pdfium-render      = { version = "0.8.26" }
 postgres-types     = { version = "=0.2.8", default-features = false }
 prometheus-client  = { version = "=0.22.3", default-features = false }
 regex              = { version = "=1.11.1", default-features = false, features = ["perf", "unicode"] }
diff --git a/libs/chonky/.gitattributes b/libs/chonky/.gitattributes
new file mode 100644
index 00000000000..5a1ce7f276c
--- /dev/null
+++ b/libs/chonky/.gitattributes
@@ -0,0 +1,2 @@
+src/snapshots/*.snap linguist-generated=true
+src/snapshots/*.snap.bmp linguist-generated=true
diff --git a/libs/chonky/Cargo.toml b/libs/chonky/Cargo.toml
index c9080fe04a1..c17dda0554f 100644
--- a/libs/chonky/Cargo.toml
+++ b/libs/chonky/Cargo.toml
@@ -17,14 +17,19 @@ edition.workspace = true
 error-stack = { workspace = true, public = true }
 
 # Public third-party dependencies
+image         = { workspace = true, public = true, features = ["png", "bmp"] }
+pdfium-render = { workspace = true, public = true }
 
 # Private workspace dependencies
 
 # Private third-party dependencies
+thiserror = { workspace = true }
 
 [dev-dependencies]
+insta = { workspace = true }
 
 [features]
+static = ["pdfium-render/static"]
 
 [lints]
 workspace = true
diff --git a/libs/chonky/README.md b/libs/chonky/README.md
index 04db5666ca1..2d4ec027f9f 100644
--- a/libs/chonky/README.md
+++ b/libs/chonky/README.md
@@ -23,6 +23,48 @@ The library relies on common Rust tools as configured in the repository root. Th
 - For linting, [`clippy`](https://github.com/rust-lang/rust-clippy) is used: `cargo clippy --package chonky`
 - [`rustfmt`](https://github.com/rust-lang/rustfmt) serves as the formatter: `cargo fmt`
 
+## Usage
+
+To run this package, a compiled library of `pdfium` must be provided. The library can either be statically or dynamically linked. The `libs/` folder is reserved to store the libraries.
+
+### Dynamic linking
+
+A dynamic library can be downloaded from [`bblanchon/pdfium-binaries`](https://github.com/bblanchon/pdfium-binaries/releases). It's possible to download the library from the command line. For example, to download the library for `mac-arm64` from the release `6721` and store it in `./libs/`:L
+
+```sh
+temp_dir=$(mktemp -d)
+gh release download chromium/6721 --repo bblanchon/pdfium-binaries --pattern 'pdfium-mac-arm64.tgz' --dir $temp_dir
+tar -xzf $temp_dir/pdfium-mac-arm64.tgz -C $temp_dir
+mv $temp_dir/lib/* libs/
+rm -rf $temp_dir
+```
+
+To link the library dynamically, don't enable the `static`. The binary will read `PDFIUM_DYNAMIC_LIB_PATH` to search for the library. If the variable is not set it will use `libs/`:
+
+```sh
+export PDFIUM_DYNAMIC_LIB_PATH="${pwd}/libs/"
+cargo build
+```
+
+### Static linking
+
+A static library can be downloaded from [`paulocoutinhox/pdfium-lib`](https://github.com/paulocoutinhox/pdfium-lib/releases). It's possible to download the library from the command line. For example, to download the library for `macos` from the release `6694` and store it in `./libs/`:
+
+```sh
+temp_dir=$(mktemp -d)
+gh release download 6694 --repo paulocoutinhox/pdfium-lib --pattern 'macos.tgz' --dir $temp_dir
+tar -xzf $temp_dir/macos.tgz -C $temp_dir
+mv $temp_dir/release/lib/* libs/
+rm -rf $temp_dir
+```
+
+To link the library statically, enable the `static` feature by passing `--features static` to any `cargo` invocation. When building the library it will search for `PDFIUM_STATIC_LIB_PATH`. For example if the library is located at `libs/libpdfium.a` you can build the library with:
+
+```sh
+export PDFIUM_STATIC_LIB_PATH="${pwd}/libs/"
+cargo build --features static
+```
+
 ### Testing
 
 The tests for the package can either be run by using the default test harness:
diff --git a/libs/chonky/build.rs b/libs/chonky/build.rs
new file mode 100644
index 00000000000..06b6a52a363
--- /dev/null
+++ b/libs/chonky/build.rs
@@ -0,0 +1,23 @@
+fn main() {
+    #[cfg(all(feature = "static", target_os = "macos"))]
+    link_macos();
+
+    #[cfg(all(feature = "static", target_os = "linux"))]
+    link_linux();
+}
+
+#[cfg(all(feature = "static", target_os = "macos"))]
+fn link_macos() {
+    // `pdfium` requires linking to the `CoreGraphics` and `libc++` frameworks on macOS
+    println!("cargo:rustc-link-lib=framework=CoreGraphics");
+    // `pdfium` also has the `libc++` feature, which can be used instead, but this makes it more
+    // explicit that we need both.
+    println!("cargo:rustc-link-lib=c++");
+}
+
+#[cfg(all(feature = "static", target_os = "linux"))]
+fn link_linux() {
+    // `pdfium` also has a `libstdc++` feature, which can be used instead, but this makes it more
+    // explicit that we need a different one depending on architecture.
+    println!("cargo:rustc-link-lib=stdc++");
+}
diff --git a/libs/chonky/libs/.gitignore b/libs/chonky/libs/.gitignore
new file mode 100644
index 00000000000..593bcf0e80e
--- /dev/null
+++ b/libs/chonky/libs/.gitignore
@@ -0,0 +1,2 @@
+!.gitignore
+*
diff --git a/libs/chonky/package.json b/libs/chonky/package.json
index 3b31199fbe4..da851bdce47 100644
--- a/libs/chonky/package.json
+++ b/libs/chonky/package.json
@@ -5,7 +5,7 @@
   "scripts": {
     "fix:clippy": "just clippy --fix",
     "lint:clippy": "just clippy",
-    "test:unit": "cargo hack nextest run --feature-powerset --all-targets && cargo test --all-features --doc"
+    "test:unit": "cargo hack nextest run --feature-powerset --exclude-features static --all-targets && cargo test --all-features --doc"
   },
   "dependencies": {
     "@rust/error-stack": "0.5.0"
diff --git a/libs/chonky/src/lib.rs b/libs/chonky/src/lib.rs
index ed157c258bd..a5638709480 100644
--- a/libs/chonky/src/lib.rs
+++ b/libs/chonky/src/lib.rs
@@ -1,26 +1,304 @@
 #![doc = include_str!("../README.md")]
 
-/// Adds two numbers together
+extern crate alloc;
+
+#[cfg(not(feature = "static"))]
+use alloc::borrow::Cow;
+#[cfg(not(feature = "static"))]
+use std::{env, path::Path};
+
+use error_stack::{Report, ResultExt as _};
+use pdfium_render::prelude::Pdfium;
+use thiserror::Error;
+
+#[derive(Error, Debug)]
+pub enum ChonkyError {
+    #[error("parsing error in pdf")]
+    ReadPdf,
+    #[error("pdfium error")]
+    Pdfium,
+    #[error("write error to system")]
+    Write,
+    #[error("Issues with CLI input")]
+    Arguments,
+}
+
+/// Attempts to link to the `PDFium` library.
+///
+/// ## Loading strategy
 ///
-/// # Example
+/// - if the `static` feature is enabled, it will attempt to statically link to the `PDFium`
+///   library.
+/// - Otherwise, it will use the `PDFIUM_DYNAMIC_LIB_PATH` environment variable to load the dynamic
+///   library from the specific path. If the environment variable is not set, it will attempt to
+///   load the dynamic library from the default path `./libs/`.
 ///
-/// ```rust
-/// use chonky::add;
+/// # Errors
 ///
-/// assert_eq!(add(1, 3), 4);
-/// ```
-#[must_use]
-pub const fn add(left: u64, right: u64) -> u64 {
-    left + right
+/// Will return a [`ChonkyError::Pdfium`] if the `PDFium` library could not be loaded.
+pub fn link_pdfium() -> Result<Pdfium, Report<ChonkyError>> {
+    #[cfg(feature = "static")]
+    return Ok(Pdfium::new(
+        Pdfium::bind_to_statically_linked_library().change_context(ChonkyError::Pdfium)?,
+    ));
+
+    #[cfg(not(feature = "static"))]
+    {
+        let lib_path = env::var("PDFIUM_DYNAMIC_LIB_PATH")
+            .map_or_else(|_| Cow::Borrowed("./libs/"), Cow::Owned);
+
+        let lib_path = Path::new(lib_path.as_ref())
+            .canonicalize()
+            .change_context(ChonkyError::Pdfium)
+            .attach_printable_lazy(|| format!("could not canonicalize path `{lib_path}`"))?;
+        Ok(Pdfium::new(
+            Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path(&lib_path))
+                .change_context(ChonkyError::Pdfium)?,
+        ))
+    }
+}
+
+pub mod pdf_segmentation {
+    use error_stack::{Report, ResultExt as _};
+    use image::{DynamicImage, GrayImage, RgbaImage};
+    use pdfium_render::prelude::{
+        PdfBitmap, PdfBitmapFormat, PdfDocument, PdfPoints, PdfRenderConfig, Pdfium,
+    };
+
+    use crate::ChonkyError;
+
+    /// Function to read the pdf
+    ///
+    /// # Errors
+    ///
+    /// Will return [`ChonkyError::Pdfium`] if `filename` does not exist or the user does not have
+    /// permission to read it.
+    pub fn load_pdf<'a>(
+        pdfium: &'a Pdfium,
+        file_path: &str,
+    ) -> Result<PdfDocument<'a>, Report<ChonkyError>> {
+        pdfium
+            .load_pdf_from_file(file_path, None)
+            .map_err(|err| Report::new(err).change_context(ChonkyError::Pdfium))
+    }
+
+    // /// TODO: This function returns the extracted text that is segmented in proper reading order
+    // and /// grouped by boundaries such as newline spacing and other layout information,
+    // segments can /// contain texts with different formatting (such as a sentence with a
+    // **bold** inside) ///
+    // /// #Errors
+    // ///
+    // /// TBD
+    //pub fn extract_text(pdf: &PdfDocument) -> () {}
+
+    // /// TODO: Given a list of segments of a PDF this function reads the segments via the bounding
+    // /// box order, with the naive approach of top→bottom (and if same top then left→right) and
+    // /// returns a sorted vector of reading order of segments
+    // ///
+    // /// #Errors
+    // ///
+    // /// TBD
+    //fn obtain_reading_order(segments: Vec<segment>) -> () {}
+
+    // /// TODO: Function returns a smaller segment vector by grouping segments in similar chunks,
+    // but /// have different style formatting The new vector stores this information seperately
+    // ///
+    // /// #Errors
+    // ///
+    // /// TBD
+    //fn group_similar_segments() -> () {}
+
+    /// Takes in a pdf document and returns a vector list where each page
+    /// is processed into a raw image that can be later converted to any image format
+    ///
+    /// # Errors
+    ///
+    /// Return an [`ChonkyError::Pdfium`]  if there was a
+    /// problem with the image processing operation, occurs when image cannot be encoded into
+    /// specific image format
+    pub fn pdf_to_images(pdf: &PdfDocument) -> Result<Vec<DynamicImage>, Report<ChonkyError>> {
+        let mut images: Vec<DynamicImage> = Vec::new();
+
+        //may adjust resolution depending on need
+        let resolution_width = 1000;
+
+        // information about how to store image, like pixed resolution and aspect ratio
+        let config = PdfRenderConfig::new().set_target_width(resolution_width);
+
+        let mut bitmap = create_empty_bitmap(pdf, &config)?;
+
+        for page in pdf.pages().iter() {
+            // Render the entire page to a bitmap
+            page.render_into_bitmap_with_config(&mut bitmap, &config)
+                .change_context(ChonkyError::Pdfium)?;
+
+            // Convert PdfBitmap to DynamicImage
+            let dynamic_image = as_image(&bitmap)?;
+            images.push(dynamic_image);
+        }
+
+        Ok(images)
+    }
+
+    /// Takes in a config with desired resolution of image and a pdf and creates
+    /// an empty bitmap that can be used by the entire pdf
+    ///
+    /// # Errors
+    ///
+    /// Return an [`ChonkyError::Pdfium`] if there was a problem
+    /// with converting the pdfs dimensions to pixels
+    fn create_empty_bitmap<'a>(
+        pdf: &'a PdfDocument,
+        config: &'a PdfRenderConfig,
+    ) -> Result<PdfBitmap<'a>, Report<ChonkyError>> {
+        // read the first page to get page dimesnions
+        let page_dimensions = pdf
+            .pages()
+            .page_sizes()
+            .change_context(ChonkyError::Pdfium)?[0];
+
+        let page = pdf.pages().get(0).change_context(ChonkyError::Pdfium)?;
+
+        //converts the boundings boxes to pixels that can be used for creating bitmap with proper
+        // for correct bitmap dimensions, height point must be set to 0 to get max pixel height
+        let page_dimensions = pdf
+            .pages()
+            .get(0)
+            .change_context(ChonkyError::Pdfium)?
+            .points_to_pixels(page_dimensions.width(), PdfPoints::new(0.0), config)
+            .change_context(ChonkyError::Pdfium)?;
+
+        // some pdfs have dimensions that are larger than the actual "content" resulting in negative
+        // dimensions we aim to get the "net" dimensions by subtracting the 0.0 point pixel
+        // conversion from the height and width
+        let base_page_dimensions = page
+            .points_to_pixels(PdfPoints::new(0.0), page.height(), config)
+            .change_context(ChonkyError::Pdfium)?;
+
+        let page_dimensions = (
+            page_dimensions.0 - base_page_dimensions.0,
+            page_dimensions.1 - base_page_dimensions.1,
+        );
+
+        //create an empty bitmap that follows dimensions of pdf
+        // to prevent repeated memory allocations (we assume all pdfs are same dimension)
+        let bitmap = PdfBitmap::empty(
+            page_dimensions.0,
+            page_dimensions.1,
+            PdfBitmapFormat::BGRA,
+            pdf.bindings(),
+        )
+        .change_context(ChonkyError::Pdfium)?;
+
+        Ok(bitmap)
+    }
+
+    ///A vendored function from pdfium-render's `as_image` function that returns a result instead
+    /// of panicking
+    ///
+    /// Errors#
+    ///
+    /// [`ChonkyError::Pdfium`] when the image had an error being processed
+    fn as_image(bitmap: &PdfBitmap) -> Result<DynamicImage, Report<ChonkyError>> {
+        let bytes = bitmap.as_rgba_bytes();
+
+        // clippy complains if we directly cast into u32 from i32 because of sign loss
+        // since we assume dimensions must be positive this is not as issue
+        let width = u32::try_from(bitmap.width()).change_context(ChonkyError::Pdfium)?;
+
+        let height = u32::try_from(bitmap.height()).change_context(ChonkyError::Pdfium)?;
+
+        Ok(match bitmap.format().map_err(|_foo| ChonkyError::Pdfium)? {
+            PdfBitmapFormat::BGRA | PdfBitmapFormat::BGRx | PdfBitmapFormat::BGR => {
+                RgbaImage::from_raw(width, height, bytes)
+                    .map(DynamicImage::ImageRgba8)
+                    .ok_or(ChonkyError::Pdfium)?
+            }
+            PdfBitmapFormat::Gray => GrayImage::from_raw(width, height, bytes)
+                .map(DynamicImage::ImageLuma8)
+                .ok_or(ChonkyError::Pdfium)?,
+            _ => return Err(Report::new(ChonkyError::Pdfium)),
+        })
+    }
 }
 
 #[cfg(test)]
 mod tests {
+    use error_stack::{Report, ResultExt as _};
+    use insta::assert_binary_snapshot;
+
     use super::*;
 
     #[test]
-    fn it_works() {
-        let result = add(2, 2);
-        assert_eq!(result, 4);
+    fn pdf_load_success() -> Result<(), Report<ChonkyError>> {
+        let pdfium = link_pdfium()?;
+
+        let test_pdf_string = "tests/docs/test-doc.pdf";
+
+        let _pdf = pdf_segmentation::load_pdf(&pdfium, test_pdf_string)
+            .change_context(ChonkyError::Pdfium)?;
+
+        Ok(())
+    }
+
+    #[test]
+    fn pdf_load_failure() -> Result<(), Report<ChonkyError>> {
+        let pdfium = link_pdfium()?;
+
+        let test_pdf_string = "tests/docs/invalid.pdf";
+
+        // Should return an error when loading an invalid PDF
+        let result = pdf_segmentation::load_pdf(&pdfium, test_pdf_string)
+            .change_context(ChonkyError::Pdfium);
+
+        if result.is_err() {
+            // Expected failure, return Ok
+            Ok(())
+        } else {
+            // Unexpected success, return an error
+            Err(Report::new(ChonkyError::Pdfium).attach_printable("Expected load_pdf to fail"))
+        }
+    }
+
+    #[test]
+    fn pdf_image_conversion() -> Result<(), Report<ChonkyError>> {
+        let pdfium = link_pdfium()?;
+
+        let test_pdf_string = "tests/docs/test-doc.pdf";
+
+        let pdf = pdf_segmentation::load_pdf(&pdfium, test_pdf_string)
+            .change_context(ChonkyError::Pdfium)?;
+
+        //number of pages of pdf
+        let num_pages: usize = pdf.pages().len().into();
+
+        let preprocessed_pdf =
+            pdf_segmentation::pdf_to_images(&pdf).change_context(ChonkyError::Pdfium)?;
+
+        //start by checking if proper amount of images are converted
+
+        if preprocessed_pdf.len() != num_pages {
+            return Err(Report::new(ChonkyError::Pdfium)
+                .attach_printable("The length of vector should be number of pages"));
+        }
+
+        // now check if the image contents are the same using insta snapshots
+        // start by converting images to binary
+        // let preprocessed_pdf: Vec<Vec<u8>> = preprocessed_pdf
+        //     .into_iter()
+        //     .map(image::DynamicImage::into_bytes)
+        //     .collect();
+
+        // we only really need to check the first three pages
+        for (index, page) in preprocessed_pdf.into_iter().enumerate().take(3) {
+            let mut buffer = Vec::new();
+            let encoder = image::codecs::bmp::BmpEncoder::new(&mut buffer);
+
+            page.write_with_encoder(encoder)
+                .expect("image should be able to be encoded into a bitmap");
+            assert_binary_snapshot!(format!("page_{}.bmp", index + 1).as_str(), buffer);
+        }
+
+        Ok(())
     }
 }
diff --git a/libs/chonky/src/main.rs b/libs/chonky/src/main.rs
new file mode 100644
index 00000000000..36a4fc90e35
--- /dev/null
+++ b/libs/chonky/src/main.rs
@@ -0,0 +1,33 @@
+use std::env;
+
+use chonky::{ChonkyError, pdf_segmentation};
+use error_stack::{Report, ResultExt as _, ensure};
+
+fn main() -> Result<(), Report<ChonkyError>> {
+    // read file path arguments
+    // TODO: implement with clap
+    let args: Vec<String> = env::args().collect();
+
+    ensure!(args.len() > 1, ChonkyError::Arguments);
+
+    let pdfium = chonky::link_pdfium()?;
+
+    let pdf = pdf_segmentation::load_pdf(&pdfium, &args[1]).change_context(ChonkyError::Pdfium)?;
+
+    let preprocessed_pdf =
+        pdf_segmentation::pdf_to_images(&pdf).change_context(ChonkyError::Pdfium)?;
+    //for now we will print all these images to a folder
+    // this will be a seperate function in the future once knowledge about error-stack increases
+
+    let output_folder = "./out";
+
+    for (index, image) in preprocessed_pdf.iter().enumerate() {
+        // Generate a unique filename for each page image
+        let file_path = format!("{}/page_{}.png", output_folder, index + 1);
+
+        // Save the image as a PNG file
+        image.save(&file_path).change_context(ChonkyError::Write)?;
+    }
+
+    Ok(())
+}
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_1.snap b/libs/chonky/src/snapshots/chonky__tests__page_1.snap
new file mode 100644
index 00000000000..71131a21ad5
--- /dev/null
+++ b/libs/chonky/src/snapshots/chonky__tests__page_1.snap
@@ -0,0 +1,6 @@
+---
+source: libs/chonky/src/lib.rs
+expression: buffer
+extension: bmp
+snapshot_kind: binary
+---
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_1.snap.bmp b/libs/chonky/src/snapshots/chonky__tests__page_1.snap.bmp
new file mode 100644
index 00000000000..800d54de684
Binary files /dev/null and b/libs/chonky/src/snapshots/chonky__tests__page_1.snap.bmp differ
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_2.snap b/libs/chonky/src/snapshots/chonky__tests__page_2.snap
new file mode 100644
index 00000000000..71131a21ad5
--- /dev/null
+++ b/libs/chonky/src/snapshots/chonky__tests__page_2.snap
@@ -0,0 +1,6 @@
+---
+source: libs/chonky/src/lib.rs
+expression: buffer
+extension: bmp
+snapshot_kind: binary
+---
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_2.snap.bmp b/libs/chonky/src/snapshots/chonky__tests__page_2.snap.bmp
new file mode 100644
index 00000000000..46bc92ef731
Binary files /dev/null and b/libs/chonky/src/snapshots/chonky__tests__page_2.snap.bmp differ
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_3.snap b/libs/chonky/src/snapshots/chonky__tests__page_3.snap
new file mode 100644
index 00000000000..71131a21ad5
--- /dev/null
+++ b/libs/chonky/src/snapshots/chonky__tests__page_3.snap
@@ -0,0 +1,6 @@
+---
+source: libs/chonky/src/lib.rs
+expression: buffer
+extension: bmp
+snapshot_kind: binary
+---
diff --git a/libs/chonky/src/snapshots/chonky__tests__page_3.snap.bmp b/libs/chonky/src/snapshots/chonky__tests__page_3.snap.bmp
new file mode 100644
index 00000000000..b69ab120de3
Binary files /dev/null and b/libs/chonky/src/snapshots/chonky__tests__page_3.snap.bmp differ
diff --git a/libs/chonky/tests/docs/test-doc.pdf b/libs/chonky/tests/docs/test-doc.pdf
new file mode 100644
index 00000000000..a2a20201cde
Binary files /dev/null and b/libs/chonky/tests/docs/test-doc.pdf differ