sparrow-parse 0.5.0__tar.gz → 0.5.2__tar.gz

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.5.0
+Version: 0.5.2
 Summary: Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 Author: Andrej Baranovskij
@@ -60,6 +60,7 @@ input_data = [
 # Now you can run inference without knowing which implementation is used
 results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=False,
                                  generic_query=False,
+                                 crop_size=80,
                                  debug_dir=None,
                                  debug=True,
                                  mode=None)
@@ -71,6 +72,8 @@ print(f"Number of pages: {num_pages}")
 
 Use `tables_only=True` if you want to extract only tables.
 
+Use `crop_size=N` (where `N` is an integer) to crop N pixels from all borders of the input images. This can be helpful for removing unwanted borders or frame artifacts from scanned documents.
+
 Use `mode="static"` if you want to simulate LLM call, without executing LLM backend.
 
 Method `run_inference` will return results and number of pages processed.
@@ -95,7 +98,7 @@ from sparrow_parse.extractor.pdf_optimizer import PDFOptimizer
 pdf_optimizer = PDFOptimizer()
 
 num_pages, output_files, temp_dir = pdf_optimizer.split_pdf_to_pages(file_path,
-                                                                     output_directory,
+                                                                     debug_dir,
                                                                      convert_to_images)
 
 ```
@@ -104,10 +107,30 @@ Example:
 
 *file_path* - `/data/invoice_1.pdf`
 
-*output_directory* - set to not `None`, for debug purposes only
+*debug_dir* - set to not `None`, for debug purposes only
 
 *convert_to_images* - default `False`, to split into PDF files
 
+## Image cropping
+
+```
+from sparrow_parse.helpers.image_optimizer import ImageOptimizer
+
+image_optimizer = ImageOptimizer()
+
+cropped_file_path = image_optimizer.crop_image_borders(file_path, temp_dir, debug_dir, crop_size)
+```
+
+Example:
+
+*file_path* - `/data/invoice_1.jpg`
+
+*temp_dir* - directory to store cropped files
+
+*debug_dir* - set to not `None`, for debug purposes only
+
+*crop_size* - Number of pixels to crop from each border
+
 ## Library build
 
 Create Python virtual environment

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/README.md

@@ -41,6 +41,7 @@ input_data = [
 # Now you can run inference without knowing which implementation is used
 results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=False,
                                  generic_query=False,
+                                 crop_size=80,
                                  debug_dir=None,
                                  debug=True,
                                  mode=None)
@@ -52,6 +53,8 @@ print(f"Number of pages: {num_pages}")
 
 Use `tables_only=True` if you want to extract only tables.
 
+Use `crop_size=N` (where `N` is an integer) to crop N pixels from all borders of the input images. This can be helpful for removing unwanted borders or frame artifacts from scanned documents.
+
 Use `mode="static"` if you want to simulate LLM call, without executing LLM backend.
 
 Method `run_inference` will return results and number of pages processed.
@@ -76,7 +79,7 @@ from sparrow_parse.extractor.pdf_optimizer import PDFOptimizer
 pdf_optimizer = PDFOptimizer()
 
 num_pages, output_files, temp_dir = pdf_optimizer.split_pdf_to_pages(file_path,
-                                                                     output_directory,
+                                                                     debug_dir,
                                                                      convert_to_images)
 
 ```
@@ -85,10 +88,30 @@ Example:
 
 *file_path* - `/data/invoice_1.pdf`
 
-*output_directory* - set to not `None`, for debug purposes only
+*debug_dir* - set to not `None`, for debug purposes only
 
 *convert_to_images* - default `False`, to split into PDF files
 
+## Image cropping
+
+```
+from sparrow_parse.helpers.image_optimizer import ImageOptimizer
+
+image_optimizer = ImageOptimizer()
+
+cropped_file_path = image_optimizer.crop_image_borders(file_path, temp_dir, debug_dir, crop_size)
+```
+
+Example:
+
+*file_path* - `/data/invoice_1.jpg`
+
+*temp_dir* - directory to store cropped files
+
+*debug_dir* - set to not `None`, for debug purposes only
+
+*crop_size* - Number of pixels to crop from each border
+
 ## Library build
 
 Create Python virtual environment

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as fh:
 
 setup(
     name="sparrow-parse",
-    version="0.5.0",
+    version="0.5.2",
     author="Andrej Baranovskij",
     author_email="andrejus.baranovskis@gmail.com",
     description="Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.",

sparrow-parse-0.5.2/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.5.2'

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse/extractors/vllm_extractor.py

@@ -1,7 +1,7 @@
 import json
-
 from sparrow_parse.vllm.inference_factory import InferenceFactory
 from sparrow_parse.helpers.pdf_optimizer import PDFOptimizer
+from sparrow_parse.helpers.image_optimizer import ImageOptimizer
 from sparrow_parse.processors.table_structure_processor import TableDetector
 from rich import print
 import os
@@ -14,7 +14,7 @@ class VLLMExtractor(object):
         pass
 
     def run_inference(self, model_inference_instance, input_data, tables_only=False,
-                      generic_query=False, debug_dir=None, debug=False, mode=None):
+                      generic_query=False, crop_size=None, debug_dir=None, debug=False, mode=None):
         """
         Main entry point for processing input data using a model inference instance.
         Handles generic queries, PDFs, and table extraction.
@@ -27,12 +27,12 @@ class VLLMExtractor(object):
 
         file_path = input_data[0]["file_path"]
         if self.is_pdf(file_path):
-            return self._process_pdf(model_inference_instance, input_data, tables_only, debug, debug_dir, mode)
+            return self._process_pdf(model_inference_instance, input_data, tables_only, crop_size, debug, debug_dir, mode)
 
-        return self._process_non_pdf(model_inference_instance, input_data, tables_only, debug, debug_dir)
+        return self._process_non_pdf(model_inference_instance, input_data, tables_only, crop_size, debug, debug_dir)
 
 
-    def _process_pdf(self, model_inference_instance, input_data, tables_only, debug, debug_dir, mode):
+    def _process_pdf(self, model_inference_instance, input_data, tables_only, crop_size, debug, debug_dir, mode):
         """
         Handles processing and inference for PDF files, including page splitting and optional table extraction.
         """
@@ -40,26 +40,40 @@ class VLLMExtractor(object):
         num_pages, output_files, temp_dir = pdf_optimizer.split_pdf_to_pages(input_data[0]["file_path"],
                                                                              debug_dir, convert_to_images=True)
 
-        results = self._process_pages(model_inference_instance, output_files, input_data, tables_only, debug, debug_dir)
+        results = self._process_pages(model_inference_instance, output_files, input_data, tables_only, crop_size, debug, debug_dir)
 
         # Clean up temporary directory
         shutil.rmtree(temp_dir, ignore_errors=True)
         return results, num_pages
 
 
-    def _process_non_pdf(self, model_inference_instance, input_data, tables_only, debug, debug_dir):
+    def _process_non_pdf(self, model_inference_instance, input_data, tables_only, crop_size, debug, debug_dir):
         """
         Handles processing and inference for non-PDF files, with optional table extraction.
         """
         file_path = input_data[0]["file_path"]
+
         if tables_only:
             return self._extract_tables(model_inference_instance, file_path, input_data, debug, debug_dir), 1
         else:
+            temp_dir = tempfile.mkdtemp()
+
+            if crop_size:
+                if debug:
+                    print(f"Cropping image borders by {crop_size} pixels.")
+                image_optimizer = ImageOptimizer()
+                cropped_file_path = image_optimizer.crop_image_borders(file_path, temp_dir, debug_dir, crop_size)
+                input_data[0]["file_path"] = cropped_file_path
+
+            file_path = input_data[0]["file_path"]
             input_data[0]["file_path"] = [file_path]
             results = model_inference_instance.inference(input_data)
+
+            shutil.rmtree(temp_dir, ignore_errors=True)
+
             return results, 1
 
-    def _process_pages(self, model_inference_instance, output_files, input_data, tables_only, debug, debug_dir):
+    def _process_pages(self, model_inference_instance, output_files, input_data, tables_only, crop_size, debug, debug_dir):
         """
         Processes individual pages (PDF split) and handles table extraction or inference.
 
@@ -68,6 +82,7 @@ class VLLMExtractor(object):
             output_files: List of file paths for the split PDF pages.
             input_data: Input data for inference.
             tables_only: Whether to only process tables.
+            crop_size: Size for cropping image borders.
             debug: Debug flag for logging.
             debug_dir: Directory for saving debug information.
 
@@ -89,11 +104,39 @@ class VLLMExtractor(object):
         else:
             if debug:
                 print(f"Processing {len(output_files)} pages for inference at once.")
-            # Pass all output files to the inference method for processing at once
-            input_data[0]["file_path"] = output_files
+
+            temp_dir = tempfile.mkdtemp()
+            cropped_files = []
+
+            if crop_size:
+                if debug:
+                    print(f"Cropping image borders by {crop_size} pixels from {len(output_files)} images.")
+
+                image_optimizer = ImageOptimizer()
+
+                # Process each file in the output_files array
+                for file_path in output_files:
+                    cropped_file_path = image_optimizer.crop_image_borders(
+                        file_path,
+                        temp_dir,
+                        debug_dir,
+                        crop_size
+                    )
+                    cropped_files.append(cropped_file_path)
+
+                # Use the cropped files for inference
+                input_data[0]["file_path"] = cropped_files
+            else:
+                # If no cropping needed, use original files directly
+                input_data[0]["file_path"] = output_files
+
+            # Process all files at once
             results = model_inference_instance.inference(input_data)
             results_array.extend(results)
 
+            # Clean up temporary directory
+            shutil.rmtree(temp_dir, ignore_errors=True)
+
         return results_array
 
 
@@ -174,8 +217,9 @@ if __name__ == "__main__":
     # ]
     #
     # # Now you can run inference without knowing which implementation is used
-    # results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=True,
+    # results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=False,
     #                                                    generic_query=False,
+    #                                                    crop_size=80,
     #                                                    debug_dir="/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/",
     #                                                    debug=True,
     #                                                    mode=None)

sparrow-parse-0.5.2/sparrow_parse/helpers/image_optimizer.py

@@ -0,0 +1,59 @@
+from PIL import Image
+import os
+
+
+class ImageOptimizer(object):
+    def __init__(self):
+        pass
+
+    def crop_image_borders(self, file_path, temp_dir, debug_dir=None, crop_size=60):
+        """
+        Crops all four borders of an image by the specified size.
+
+        Args:
+            file_path (str): Path to the input image
+            temp_dir (str): Temporary directory to store the cropped image
+            debug_dir (str, optional): Directory to save a debug copy of the cropped image
+            crop_size (int): Number of pixels to crop from each border
+
+        Returns:
+            str: Path to the cropped image in temp_dir
+        """
+        try:
+            # Open the image
+            with Image.open(file_path) as img:
+                # Get image dimensions
+                width, height = img.size
+
+                # Calculate the crop box
+                left = crop_size
+                top = crop_size
+                right = width - crop_size
+                bottom = height - crop_size
+
+                # Ensure we're not trying to crop more than the image size
+                if right <= left or bottom <= top:
+                    raise ValueError("Crop size is too large for the image dimensions")
+
+                # Perform the crop
+                cropped_img = img.crop((left, top, right, bottom))
+
+                # Get original filename without path
+                filename = os.path.basename(file_path)
+                name, ext = os.path.splitext(filename)
+
+                # Save cropped image in temp_dir
+                output_path = os.path.join(temp_dir, f"{name}_cropped{ext}")
+                cropped_img.save(output_path)
+
+                # If debug_dir is provided, save a debug copy
+                if debug_dir:
+                    os.makedirs(debug_dir, exist_ok=True)
+                    debug_path = os.path.join(debug_dir, f"{name}_cropped_debug{ext}")
+                    cropped_img.save(debug_path)
+                    print(f"Debug cropped image saved to: {debug_path}")
+
+                return output_path
+
+        except Exception as e:
+            raise Exception(f"Error processing image: {str(e)}")

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse/helpers/pdf_optimizer.py

@@ -9,7 +9,7 @@ class PDFOptimizer(object):
     def __init__(self):
         pass
 
-    def split_pdf_to_pages(self, file_path, output_dir=None, convert_to_images=False):
+    def split_pdf_to_pages(self, file_path, debug_dir=None, convert_to_images=False):
         # Create a temporary directory
         temp_dir = tempfile.mkdtemp()
         output_files = []
@@ -30,9 +30,9 @@ class PDFOptimizer(object):
                         writer.write(output_file)
                         output_files.append(output_filename)
 
-                    if output_dir:
+                    if debug_dir:
                         # Save each page to the debug folder
-                        debug_output_filename = os.path.join(output_dir, f'page_{page_num + 1}.pdf')
+                        debug_output_filename = os.path.join(debug_dir, f'page_{page_num + 1}.pdf')
                         with open(debug_output_filename, 'wb') as output_file:
                             writer.write(output_file)
 
@@ -49,10 +49,12 @@ class PDFOptimizer(object):
                 image.save(output_filename, 'JPEG')
                 output_files.append(output_filename)
 
-                if output_dir:
+                if debug_dir:
                     # Save each image to the debug folder
-                    debug_output_filename = os.path.join(output_dir, f'{base_name}_page_{i + 1}.jpg')
+                    os.makedirs(debug_dir, exist_ok=True)
+                    debug_output_filename = os.path.join(debug_dir, f'{base_name}_page_{i + 1}_debug.jpg')
                     image.save(debug_output_filename, 'JPEG')
+                    print(f"Debug image saved to: {debug_output_filename}")
 
             # Return the number of pages, the list of file paths, and the temporary directory
             return len(images), output_files, temp_dir
@@ -61,13 +63,13 @@ class PDFOptimizer(object):
 if __name__ == "__main__":
     pdf_optimizer = PDFOptimizer()
 
-    # output_directory = "/Users/andrejb/infra/shared/katana-git/sparrow/sparrow-ml/llm/data/"
+    # debug_dir = "/Users/andrejb/infra/shared/katana-git/sparrow/sparrow-ml/llm/data/"
     # # Ensure the output directory exists
     # os.makedirs(output_directory, exist_ok=True)
     #
     # # Split the optimized PDF into separate pages
     # num_pages, output_files, temp_dir = pdf_optimizer.split_pdf_to_pages("/Users/andrejb/infra/shared/katana-git/sparrow/sparrow-ml/llm/data/oracle_10k_2014_q1_small.pdf",
-    #                                                                      output_directory,
+    #                                                                      debug_dir,
     #                                                                      True)
     #
     # print(f"Number of pages: {num_pages}")

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse/processors/table_structure_processor.py

@@ -131,7 +131,7 @@ class TableDetector(object):
                 cropped_tables.append(cropped_table)
 
                 if debug_dir:
-                    file_name_table = self.append_filename(file_path, debug_dir, f"cropped_{i + 1}")
+                    file_name_table = self.append_filename(file_path, debug_dir, f"table_cropped_{i + 1}")
                     cropped_table.save(file_name_table)
         else:
             if debug:
@@ -141,7 +141,7 @@ class TableDetector(object):
             cropped_tables.append(cropped_table)
 
             if debug_dir:
-                file_name_table = self.append_filename(file_path, debug_dir, "cropped")
+                file_name_table = self.append_filename(file_path, debug_dir, "table_cropped")
                 cropped_table.save(file_name_table)
 
         return cropped_tables

sparrow-parse-0.5.2/sparrow_parse/text_extraction.py

@@ -0,0 +1,30 @@
+from mlx_vlm import load, apply_chat_template, generate
+from mlx_vlm.utils import load_image
+
+# For test purposes, we will use a sample image
+
+# Load model and processor
+qwen_vl_model, qwen_vl_processor = load("mlx-community/Qwen2-VL-7B-Instruct-8bit")
+qwen_vl_config = qwen_vl_model.config
+
+image = load_image("images/graph.png")
+
+messages = [
+    {"role": "system", "content": "You are an expert at extracting text from images. Format your response in json."},
+    {"role": "user", "content": "Extract the names, labels and y coordinates from the image."}
+]
+
+# Apply chat template
+prompt = apply_chat_template(qwen_vl_processor, qwen_vl_config, messages)
+
+# Generate text
+qwen_vl_output = generate(
+    qwen_vl_model,
+    qwen_vl_processor,
+    prompt,
+    image,
+    max_tokens=1000,
+    temperature=0.7,
+)
+
+print(qwen_vl_output)

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse/vllm/mlx_inference.py

@@ -112,8 +112,8 @@ class MLXInference(ModelInference):
             response = generate(
                 model,
                 processor,
-                image,
                 prompt,
+                image,
                 resize_shape=(width, height),
                 max_tokens=4000,
                 temperature=0.0,

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.5.0
+Version: 0.5.2
 Summary: Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 Author: Andrej Baranovskij
@@ -60,6 +60,7 @@ input_data = [
 # Now you can run inference without knowing which implementation is used
 results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, tables_only=False,
                                  generic_query=False,
+                                 crop_size=80,
                                  debug_dir=None,
                                  debug=True,
                                  mode=None)
@@ -71,6 +72,8 @@ print(f"Number of pages: {num_pages}")
 
 Use `tables_only=True` if you want to extract only tables.
 
+Use `crop_size=N` (where `N` is an integer) to crop N pixels from all borders of the input images. This can be helpful for removing unwanted borders or frame artifacts from scanned documents.
+
 Use `mode="static"` if you want to simulate LLM call, without executing LLM backend.
 
 Method `run_inference` will return results and number of pages processed.
@@ -95,7 +98,7 @@ from sparrow_parse.extractor.pdf_optimizer import PDFOptimizer
 pdf_optimizer = PDFOptimizer()
 
 num_pages, output_files, temp_dir = pdf_optimizer.split_pdf_to_pages(file_path,
-                                                                     output_directory,
+                                                                     debug_dir,
                                                                      convert_to_images)
 
 ```
@@ -104,10 +107,30 @@ Example:
 
 *file_path* - `/data/invoice_1.pdf`
 
-*output_directory* - set to not `None`, for debug purposes only
+*debug_dir* - set to not `None`, for debug purposes only
 
 *convert_to_images* - default `False`, to split into PDF files
 
+## Image cropping
+
+```
+from sparrow_parse.helpers.image_optimizer import ImageOptimizer
+
+image_optimizer = ImageOptimizer()
+
+cropped_file_path = image_optimizer.crop_image_borders(file_path, temp_dir, debug_dir, crop_size)
+```
+
+Example:
+
+*file_path* - `/data/invoice_1.jpg`
+
+*temp_dir* - directory to store cropped files
+
+*debug_dir* - set to not `None`, for debug purposes only
+
+*crop_size* - Number of pixels to crop from each border
+
 ## Library build
 
 Create Python virtual environment

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ README.md
 setup.py
 sparrow_parse/__init__.py
 sparrow_parse/__main__.py
+sparrow_parse/text_extraction.py
 sparrow_parse.egg-info/PKG-INFO
 sparrow_parse.egg-info/SOURCES.txt
 sparrow_parse.egg-info/dependency_links.txt
@@ -11,6 +12,7 @@ sparrow_parse.egg-info/top_level.txt
 sparrow_parse/extractors/__init__.py
 sparrow_parse/extractors/vllm_extractor.py
 sparrow_parse/helpers/__init__.py
+sparrow_parse/helpers/image_optimizer.py
 sparrow_parse/helpers/pdf_optimizer.py
 sparrow_parse/processors/__init__.py
 sparrow_parse/processors/table_structure_processor.py

{sparrow-parse-0.5.0 → sparrow-parse-0.5.2}/sparrow_parse.egg-info/requires.txt

@@ -7,4 +7,5 @@ gradio_client
 pdf2image
 
 [:sys_platform == "darwin" and platform_machine == "arm64"]
-mlx-vlm==0.1.10
+mlx>=0.22.0
+mlx-vlm==0.1.11

sparrow-parse-0.5.0/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.5.0'