diff --git a/.gitignore b/.gitignore
index 6f036496..7c44ec6b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,6 +6,8 @@ test_data
 training
 wandb
 *.dat
+benchmark_data
+report.json
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
diff --git a/poetry.lock b/poetry.lock
index 401fd057..f5735900 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -2007,13 +2007,13 @@ testing = ["docopt", "pytest"]
 
 [[package]]
 name = "pdftext"
-version = "0.3.8"
+version = "0.3.10"
 description = "Extract structured text from pdfs quickly"
 optional = false
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,!=3.8.*,>=3.9"
 files = [
-    {file = "pdftext-0.3.8-py3-none-any.whl", hash = "sha256:d11aeaf792b96ea878139ad7cd64a92d61cc5e01fec4f3b85ca6da1043d98cbe"},
-    {file = "pdftext-0.3.8.tar.gz", hash = "sha256:1fbf53f0dc636b6863ccbbb6aed693c0e435b531a55a58e3d23bd125a2e0c616"},
+    {file = "pdftext-0.3.10-py3-none-any.whl", hash = "sha256:99bd900d0d0692df06719c07ce10a859750ade3eb7f10c543f637118417497f9"},
+    {file = "pdftext-0.3.10.tar.gz", hash = "sha256:90de726e818fb5683a0616cabb1a75a32a7224e873c3058006c93da6e440c66c"},
 ]
 
 [package.dependencies]
@@ -3379,13 +3379,13 @@ tests = ["cython", "littleutils", "pygments", "pytest", "typeguard"]
 
 [[package]]
 name = "surya-ocr"
-version = "0.4.9"
+version = "0.4.8"
 description = "OCR, layout, reading order, and line detection in 90+ languages"
 optional = false
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,!=3.8.*,>=3.9"
 files = [
-    {file = "surya_ocr-0.4.9-py3-none-any.whl", hash = "sha256:1634b14d39e2a07baf6a3ccbdefe4d970ba88b97ec310276a8a9b1780da1f3c5"},
-    {file = "surya_ocr-0.4.9.tar.gz", hash = "sha256:c01e2eba24180045f1ed3fde00bf0074036e43acdd27eb2aa52b36d592bca0ee"},
+    {file = "surya_ocr-0.4.8-py3-none-any.whl", hash = "sha256:6753bf295581f44b3e3452de563a3730a6c91500ea09090927154a1edfe57364"},
+    {file = "surya_ocr-0.4.8.tar.gz", hash = "sha256:01e97db0d43941637ff0ddededa46491f7b0b937dba5c7fbba4ee75177991465"},
 ]
 
 [package.dependencies]
@@ -3975,4 +3975,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.13,!=3.9.7"
-content-hash = "ea6029f8fe580673f23861dadcab04af7dc5ed8085c587bde453dc26c978c21b"
+content-hash = "651ca6f147ab76aaad9508d3719bc5d51d28a56982295877a769df8d5491fc53"
diff --git a/pyproject.toml b/pyproject.toml
index 62928a49..8b824a42 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -33,10 +33,10 @@ tabulate = "^0.9.0"
 ftfy = "^6.1.1"
 texify = "^0.1.9"
 rapidfuzz = "^3.8.1"
-surya-ocr = "^0.4.9"
+surya-ocr = "0.4.8"
 filetype = "^1.2.0"
 regex = "^2024.4.28"
-pdftext = "0.3.8"
+pdftext = "^0.3.10"
 grpcio = "^1.63.0"
 
 [tool.poetry.group.dev.dependencies]