natural-pdf 0.1.2__tar.gz → 0.1.3__tar.gz

{natural_pdf-0.1.2 → natural_pdf-0.1.3}/.gitignore

@@ -5,7 +5,11 @@ docs/tutorials/pdfs
 install.sh
 notebooks/Examples.md
 transcript.md
-
+natural_pdf_index
+results
+docs/tutorials/needs-ocr-searchable.pdf
+sample.py
+sample2.py
 
 # Created by https://www.toptal.com/developers/gitignore/api/python,macos,visualstudiocode,jupyternotebooks
 # Edit at https://www.toptal.com/developers/gitignore?templates=python,macos,visualstudiocode,jupyternotebooks

{natural_pdf-0.1.2 → natural_pdf-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.1.2
+Version: 0.1.3
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -20,8 +20,14 @@ Requires-Dist: torch>=2.0.0
 Requires-Dist: torchvision>=0.15.0
 Requires-Dist: transformers>=4.30.0
 Requires-Dist: huggingface_hub>=0.19.0
+Requires-Dist: ocrmypdf>=16.0.0
+Requires-Dist: pikepdf>=10.0.0
 Provides-Extra: interactive
 Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "interactive"
+Provides-Extra: haystack
+Requires-Dist: haystack-ai>=2.0.0b5; extra == "haystack"
+Requires-Dist: chroma-haystack; extra == "haystack"
+Requires-Dist: sentence-transformers; extra == "haystack"
 Provides-Extra: easyocr
 Requires-Dist: easyocr; extra == "easyocr"
 Provides-Extra: paddle
@@ -39,6 +45,9 @@ Requires-Dist: paddlepaddle; extra == "all"
 Requires-Dist: paddleocr; extra == "all"
 Requires-Dist: doclayout_yolo; extra == "all"
 Requires-Dist: surya-ocr; extra == "all"
+Requires-Dist: haystack-ai>=2.0.0b5; extra == "all"
+Requires-Dist: chroma-haystack; extra == "all"
+Requires-Dist: sentence-transformers; extra == "all"
 Dynamic: license-file
 
 # Natural PDF
@@ -69,6 +78,9 @@ pip install natural-pdf[paddle]
 # Example: Install with interactive viewer support
 pip install natural-pdf[interactive]
 
+# Example: Install with semantic search support (Haystack)
+pip install natural-pdf[haystack]
+
 # Install everything
 pip install natural-pdf[all]
 ```
@@ -117,6 +129,7 @@ Natural PDF offers a range of features for working with PDFs:
 *   **OCR Integration:** Extract text from scanned documents using engines like EasyOCR, PaddleOCR, or Surya.
 *   **Layout Analysis:** Detect document structures (titles, paragraphs, tables) using AI models.
 *   **Document QA:** Ask natural language questions about your document's content.
+*   **Semantic Search:** Index PDFs and find relevant pages or documents based on semantic meaning using Haystack.
 *   **Visual Debugging:** Highlight elements and use an interactive viewer or save images to understand your selections.
 
 ## Learn More

{natural_pdf-0.1.2 → natural_pdf-0.1.3}/README.md

@@ -26,6 +26,9 @@ pip install natural-pdf[paddle]
 # Example: Install with interactive viewer support
 pip install natural-pdf[interactive]
 
+# Example: Install with semantic search support (Haystack)
+pip install natural-pdf[haystack]
+
 # Install everything
 pip install natural-pdf[all]
 ```
@@ -74,6 +77,7 @@ Natural PDF offers a range of features for working with PDFs:
 *   **OCR Integration:** Extract text from scanned documents using engines like EasyOCR, PaddleOCR, or Surya.
 *   **Layout Analysis:** Detect document structures (titles, paragraphs, tables) using AI models.
 *   **Document QA:** Ask natural language questions about your document's content.
+*   **Semantic Search:** Index PDFs and find relevant pages or documents based on semantic meaning using Haystack.
 *   **Visual Debugging:** Highlight elements and use an interactive viewer or save images to understand your selections.
 
 ## Learn More