improve the OCR pipeline processing and outputs formatting

pyproject.toml

@@ -1,3 +1,7 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
 [project]
 name = "ocr-pipeline"
 version = "0.1.0"
@@ -21,18 +25,22 @@ dependencies = [
     "scikit-image>=0.22.0",
 
     # OCR engines
-    "paddleocr>=2.7.0",
+    "paddleocr>=2.7.0,<3.0.0", 
+    "paddlepaddle>=2.6.0", 
     "pytesseract>=0.3.10",
 
     # Table detection
     "torch>=2.2.0",
     "torchvision>=0.17.0",
     "transformers>=4.38.0",
+    "timm>=1.0.0",
     "layoutparser>=0.3.0",
 
     # NLP
     "langchain-text-splitters>=0.0.2",
     "spacy>=3.7.0",
+    "nbformat>=5.9.0",
+    "legacy-cgi>=2.6.2",
 
     # Database
     "sqlite-utils>=3.37.0",
@@ -56,17 +64,17 @@ dev = [
     "mypy>=1.8.0",
     "pre-commit>=3.6.0",
 ]
-grobid = [
-    "grobid-client>=0.8.0",
-]
+grobid = []
 full = [
     "ocr-pipeline[dev]",
-    "ocr-pipeline[grobid]",
 ]
 
 [project.entry-points.console_scripts]
 ocr-pipeline = "ocr_pipeline.cli:app"
 
+[tool.setuptools.packages.find]
+where = ["src"]
+
 [tool.uv]
 dev-dependencies = [
     "pytest>=8.0.0",