response to pirana comments

README.md

@@ -85,8 +85,6 @@ Note: The DataFog library uses asynchronous programming for OCR, so make sure to
 
 ## Examples
 
-TODO: Update README. switch installation method to install requirements-dev.txt and then -e
-
 For more detailed examples, check out our Jupyter notebooks in the `examples/` directory:
 
 - `text_annotation_example.ipynb`: Demonstrates text PII annotation
@@ -118,7 +116,7 @@ For local development:
      ```
 5. Install the package in editable mode:
    ```
-   pip install -e .
+   pip install -r requirements-dev.txt
    ```
 6. Set up the project:
    ```

datafog/processing/text_processing/spacy_pii_annotator.py

@@ -39,7 +39,16 @@ def create(cls) -> "SpacyPIIAnnotator":
             import subprocess
 
             subprocess.run(
-                ["python", "-m", "spacy", "download", "en_core_web_lg"], check=True
+                [
+                    "python",
+                    "-m",
+                    "pip",
+                    "install",
+                    "--no-deps",
+                    "--no-cache-dir",
+                    "https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1-py3-none-any.whl",
+                ],
+                check=True,
             )
             nlp = spacy.load("en_core_web_lg")
 

datafog/services/image_service.py

@@ -8,8 +8,6 @@
 from PIL import Image
 
 from datafog.processing.image_processing.donut_processor import DonutProcessor
-
-# from datafog.processing.image_processing.image_downloader import ImageDownloader
 from datafog.processing.image_processing.pytesseract_processor import (
     PytesseractProcessor,
 )
@@ -41,13 +39,6 @@ def __init__(self, use_donut: bool = False, use_tesseract: bool = True):
             PytesseractProcessor() if self.use_tesseract else None
         )
 
-    # async def download_images(self, urls: List[str]) -> List[Image.Image]:
-    #     async def download_image(url: str) -> Image.Image:
-    #         return await self.downloader.download_image(url)
-
-    #     tasks = [asyncio.create_task(download_image(url)) for url in urls]
-    #     return await asyncio.gather(*tasks)
-
     async def download_images(self, urls: List[str]) -> List[Image.Image]:
         async def download_image(url: str) -> Image.Image:
             return await self.downloader.download_image(url)

requirements.txt

@@ -1,5 +1,5 @@
 pandas
-Requests
+requests==2.32.3
 spacy==3.7.5
 pydantic>=2.8.2,<3.0.0
 Pillow

setup.py

@@ -5,7 +5,7 @@
     long_description = f.read()
 
 # Use a single source of truth for the version
-__version__ = "3.4.0b1"
+__version__ = "3.4.0"
 
 project_urls = {
     "Homepage": "https://datafog.ai",
@@ -26,7 +26,7 @@
     packages=find_packages(),
     install_requires=[
         "pandas",
-        "Requests",
+        "requests==2.32.3",
         "spacy==3.7.5",
         "pydantic",
         "Pillow",

tests/test_image_service.py

@@ -23,12 +23,6 @@
 ]
 
 
-# @pytest.mark.asyncio
-# async def test_download_images():
-#     image_service1 = ImageService()
-#     images = await image_service1.download_images(urls)
-#     assert len(images) == 2
-#     assert all(isinstance(image, Image.Image) for image in images)
 @pytest.mark.asyncio
 async def test_download_images():
     image_service = ImageService()