sparrow-parse 0.5.2__py3-none-any.whl → 0.5.3__py3-none-any.whl

sparrow_parse/__init__.py

@@ -1 +1 @@
-__version__ = '0.5.2'
+__version__ = '0.5.3'

sparrow_parse/extractors/vllm_extractor.py

@@ -198,7 +198,7 @@ if __name__ == "__main__":
     # # export HF_TOKEN="hf_"
     # config = {
     #     "method": "mlx",  # Could be 'huggingface', 'mlx' or 'local_gpu'
-    #     "model_name": "mlx-community/Qwen2-VL-7B-Instruct-8bit",
+    #     "model_name": "mlx-community/Qwen2.5-VL-7B-Instruct-8bit",
     #     # "hf_space": "katanaml/sparrow-qwen2-vl-7b",
     #     # "hf_token": os.getenv('HF_TOKEN'),
     #     # Additional fields for local GPU inference
@@ -211,7 +211,7 @@ if __name__ == "__main__":
     #
     # input_data = [
     #     {
-    #         "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/invoice_1.jpg",
+    #         "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/bonds_table.png",
     #         "text_input": "retrieve document data. return response in JSON format"
     #     }
     # ]
@@ -219,7 +219,7 @@ 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=False,
     #                                                    generic_query=False,
-    #                                                    crop_size=80,
+    #                                                    crop_size=0,
     #                                                    debug_dir="/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/",
     #                                                    debug=True,
     #                                                    mode=None)

sparrow_parse/text_extraction.py

@@ -4,7 +4,7 @@ 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_model, qwen_vl_processor = load("mlx-community/Qwen2.5-VL-7B-Instruct-8bit")
 qwen_vl_config = qwen_vl_model.config
 
 image = load_image("images/graph.png")

{sparrow_parse-0.5.2.dist-info → sparrow_parse-0.5.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.5.2
+Version: 0.5.3
 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
@@ -17,20 +17,22 @@ Classifier: Programming Language :: Python :: 3.10
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 Requires-Dist: rich
-Requires-Dist: transformers==4.47.1
+Requires-Dist: transformers==4.48.2
+Requires-Dist: torchvision==0.21.0
+Requires-Dist: torch==2.6.0
 Requires-Dist: sentence-transformers==3.3.1
 Requires-Dist: numpy==2.1.3
 Requires-Dist: pypdf==4.3.0
 Requires-Dist: gradio-client
 Requires-Dist: pdf2image
 Requires-Dist: mlx>=0.22.0; sys_platform == "darwin" and platform_machine == "arm64"
-Requires-Dist: mlx-vlm==0.1.11; sys_platform == "darwin" and platform_machine == "arm64"
+Requires-Dist: mlx-vlm==0.1.12; sys_platform == "darwin" and platform_machine == "arm64"
 
 # Sparrow Parse
 
 ## Description
 
-This module implements Sparrow Parse [library](https://pypi.org/project/sparrow-parse/) library with helpful methods for data pre-processing, parsing and extracting information. This library relies on Visual LLM functionality, Table Transformers and is part of Sparrow. Check main [README](https://github.com/katanaml/sparrow)
+This module implements Sparrow Parse [library](https://pypi.org/project/sparrow-parse/) library with helpful methods for data pre-processing, parsing and extracting information. Library relies on Visual LLM functionality, Table Transformers and is part of Sparrow. Check main [README](https://github.com/katanaml/sparrow)
 
 ## Install
 
@@ -184,6 +186,6 @@ If your organization is seeking to utilize Sparrow under a proprietary license,
 
 ## License
 
-Licensed under the GPL 3.0. Copyright 2020-2024 Katana ML, Andrej Baranovskij. [Copy of the license](https://github.com/katanaml/sparrow/blob/main/LICENSE).
+Licensed under the GPL 3.0. Copyright 2020-2025 Katana ML, Andrej Baranovskij. [Copy of the license](https://github.com/katanaml/sparrow/blob/main/LICENSE).
 
 

{sparrow_parse-0.5.2.dist-info → sparrow_parse-0.5.3.dist-info}/RECORD

@@ -1,8 +1,8 @@
-sparrow_parse/__init__.py,sha256=LADBavpB8x-lrtqob-7SCQZXFPfLZCu34A0lBsgTGGI,21
+sparrow_parse/__init__.py,sha256=IIIADjPr2y0W_XfgU1cH-K2HswMouXAPagGe6_twaIk,21
 sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
-sparrow_parse/text_extraction.py,sha256=TvDjC_R0Yjjj_8zOYSpu9gXtx8C7o36CIKsuCXfu44E,832
+sparrow_parse/text_extraction.py,sha256=JtUU7swvV12xBai5S9ICxWWWrUlkpZTZqvUnbz1h5Mk,834
 sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sparrow_parse/extractors/vllm_extractor.py,sha256=ecuheSYSDz7PNq5gMS4deStJ3wraJTR7JRmOjn31wpM,9560
+sparrow_parse/extractors/vllm_extractor.py,sha256=Cf2sVgxDExj2ud4G6z9JnirVclTgPIEe9YSoCfTkW4k,9563
 sparrow_parse/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sparrow_parse/helpers/image_optimizer.py,sha256=gUAJuNzRAB5ipgfhxTNss4MHbCPPkV5y-BSyrEHcJ0Y,2164
 sparrow_parse/helpers/pdf_optimizer.py,sha256=A2BVkb2JMqTJUz6bdfVzMmFSYaWn1QMav7UadMi0XJg,3423
@@ -14,8 +14,8 @@ sparrow_parse/vllm/inference_base.py,sha256=4mwGoAY63MB4cHZpV0czTkJWEzimmiTzqqzK
 sparrow_parse/vllm/inference_factory.py,sha256=FTM65O-dW2WZchHOrNN7_Q3-FlVoAc65iSptuuUuClM,1166
 sparrow_parse/vllm/local_gpu_inference.py,sha256=aHoJTejb5xrXjWDIGu5RBQWEyRCOBCB04sMvO2Wyvg8,628
 sparrow_parse/vllm/mlx_inference.py,sha256=MUuW56f-aKnVmeMAATxKLxsovEMmp1qlgtlmW8J2C7M,4899
-sparrow_parse-0.5.2.dist-info/METADATA,sha256=9XEpFv0kxRRiaSm2X-BHGq2OWX11nTkHQFkNRrvIAgs,7181
-sparrow_parse-0.5.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-sparrow_parse-0.5.2.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
-sparrow_parse-0.5.2.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
-sparrow_parse-0.5.2.dist-info/RECORD,,
+sparrow_parse-0.5.3.dist-info/METADATA,sha256=NOwPut-aOo6gdWH44k_Ei3WP3-bvkc-Dl7qyKE3r2FQ,7239
+sparrow_parse-0.5.3.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+sparrow_parse-0.5.3.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
+sparrow_parse-0.5.3.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
+sparrow_parse-0.5.3.dist-info/RECORD,,