indexify 0.0.41__tar.gz → 0.0.43__tar.gz

{indexify-0.0.41 → indexify-0.0.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.41
+Version: 0.0.43
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.41 → indexify-0.0.43}/indexify/extractor_sdk/extractor.py

@@ -45,6 +45,8 @@ class Extractor(ABC):
 
     version: str = "0.0.0"
 
+    base_image: Optional[str] = None
+
     system_dependencies: List[str] = []
 
     python_dependencies: List[str] = []

{indexify-0.0.41 → indexify-0.0.43}/indexify/extractors/pdf_parser.py

@@ -2,7 +2,6 @@ import tempfile
 from enum import Enum
 from typing import List, Optional
 
-import deepdoctection as dd
 from pydantic import BaseModel
 
 
@@ -45,6 +44,7 @@ class PDFParser:
         self._data = data
 
     def parse(self) -> List[Page]:
+        import deepdoctection as dd
         analyzer = dd.get_dd_analyzer()
         parsed_pages = []
         with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as f:
@@ -68,7 +68,6 @@ class PDFParser:
                         )
                     )
             figures = parsed_page.get_annotation(category_names=dd.LayoutType.FIGURE)
-            print(len(figures))
             for figure in figures:
                 image_bytes = dd.viz_handler.encode(figure.viz())
                 fragments.append(
@@ -80,7 +79,6 @@ class PDFParser:
                 )
 
             tables = parsed_page.get_annotation(category_names=dd.LayoutType.TABLE)
-            print(len(tables))
             for table in tables:
                 fragments.append(
                     PageFragment(

{indexify-0.0.41 → indexify-0.0.43}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "indexify"
-version = "0.0.41"
+version = "0.0.43"
 description = "Python Client for Indexify"
 authors = ["Diptanu Gon Choudhury <diptanuc@gmail.com>", "Lucas Jackson <lucas@tensorlake.ai>", "Vijay Parthasarathy <vijay2win@gmail.com>"]
 license = "Apache 2.0"