sparrow-parse 0.3.11__py3-none-any.whl → 0.3.12__py3-none-any.whl

sparrow_parse/__init__.py

@@ -1 +1 @@
-__version__ = '0.3.11'
+__version__ = '0.3.12'

sparrow_parse/extractors/vllm_extractor.py

@@ -55,33 +55,33 @@ if __name__ == "__main__":
 
     extractor = VLLMExtractor()
 
-    # export HF_TOKEN="hf_"
-    config = {
-        "method": "mlx",  # Could be 'huggingface', 'mlx' or 'local_gpu'
-        "model_name": "mlx-community/Qwen2-VL-72B-Instruct-4bit",
-        # "hf_space": "katanaml/sparrow-qwen2-vl-7b",
-        # "hf_token": os.getenv('HF_TOKEN'),
-        # Additional fields for local GPU inference
-        # "device": "cuda", "model_path": "model.pth"
-    }
-
-    # Use the factory to get the correct instance
-    factory = InferenceFactory(config)
-    model_inference_instance = factory.get_inference_instance()
-
-    input_data = [
-        {
-            "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/oracle_10k_2014_q1_small.pdf",
-            "text_input": "retrieve table, description, latest_amount, previous_amount. return response in JSON format, by strictly following this JSON schema: {\"table\": [{\"description\": \"str\", \"latest_amount\": 0, \"previous_amount\": 0}]}"
-        }
-    ]
-
-    # Now you can run inference without knowing which implementation is used
-    results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, generic_query=False,
-                                     debug_dir=None,
-                                     debug=True,
-                                     mode=None)
-
-    for i, result in enumerate(results_array):
-        print(f"Result for page {i + 1}:", result)
-    print(f"Number of pages: {num_pages}")
+    # # export HF_TOKEN="hf_"
+    # config = {
+    #     "method": "mlx",  # Could be 'huggingface', 'mlx' or 'local_gpu'
+    #     "model_name": "mlx-community/Qwen2-VL-72B-Instruct-4bit",
+    #     # "hf_space": "katanaml/sparrow-qwen2-vl-7b",
+    #     # "hf_token": os.getenv('HF_TOKEN'),
+    #     # Additional fields for local GPU inference
+    #     # "device": "cuda", "model_path": "model.pth"
+    # }
+    #
+    # # Use the factory to get the correct instance
+    # factory = InferenceFactory(config)
+    # model_inference_instance = factory.get_inference_instance()
+    #
+    # input_data = [
+    #     {
+    #         "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/oracle_10k_2014_q1_small.pdf",
+    #         "text_input": "retrieve table, description, latest_amount, previous_amount. return response in JSON format, by strictly following this JSON schema: {\"table\": [{\"description\": \"str\", \"latest_amount\": 0, \"previous_amount\": 0}]}"
+    #     }
+    # ]
+    #
+    # # Now you can run inference without knowing which implementation is used
+    # results_array, num_pages = extractor.run_inference(model_inference_instance, input_data, generic_query=False,
+    #                                  debug_dir=None,
+    #                                  debug=True,
+    #                                  mode=None)
+    #
+    # for i, result in enumerate(results_array):
+    #     print(f"Result for page {i + 1}:", result)
+    # print(f"Number of pages: {num_pages}")

{sparrow_parse-0.3.11.dist-info → sparrow_parse-0.3.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.3.11
+Version: 0.3.12
 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
@@ -24,7 +24,7 @@ Requires-Dist: pypdf==4.3.0
 Requires-Dist: easyocr==1.7.1
 Requires-Dist: gradio-client
 Requires-Dist: pdf2image
-Requires-Dist: mlx-vlm==0.1.3; sys_platform == "darwin" and platform_machine == "arm64"
+Requires-Dist: mlx-vlm==0.1.4; sys_platform == "darwin" and platform_machine == "arm64"
 
 # Sparrow Parse
 

{sparrow_parse-0.3.11.dist-info → sparrow_parse-0.3.12.dist-info}/RECORD

@@ -1,7 +1,7 @@
-sparrow_parse/__init__.py,sha256=ffGYSp8ZNa0Q4_Q7ecO1MiMLkWV8z2pOxdetmy6GsVI,22
+sparrow_parse/__init__.py,sha256=_ZihGlMI7X-0KVVWL_iXdUXrQS9gun7MiVTXSd1Xs4o,22
 sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
 sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sparrow_parse/extractors/vllm_extractor.py,sha256=UDKoh5KDdGqNeJJCVdt044yo2SlvWBqWVzhHknSMTlU,3576
+sparrow_parse/extractors/vllm_extractor.py,sha256=E2-Zpfssu2MVkmVjHpjBh9WK3rJ7ywHhMjJX3xZB_H8,3648
 sparrow_parse/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sparrow_parse/helpers/pdf_optimizer.py,sha256=GIqQYWtixFeZGCRFXL0lQfQByapCDuQzzRHAkzcPwLE,3302
 sparrow_parse/processors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -12,8 +12,8 @@ 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=xR40qwjIR0HvrN8x58oOq6F4r1hEANRB-9kcokUQHHU,4748
-sparrow_parse-0.3.11.dist-info/METADATA,sha256=1WHTqOZ-IBrlYHA6z2gJV4lIBunPN0uynpWZ2ikQ3g0,6351
-sparrow_parse-0.3.11.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-sparrow_parse-0.3.11.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
-sparrow_parse-0.3.11.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
-sparrow_parse-0.3.11.dist-info/RECORD,,
+sparrow_parse-0.3.12.dist-info/METADATA,sha256=tgTHQSWokNEc0TOry7EpunttLgYXYd6GEx6bzedb25s,6351
+sparrow_parse-0.3.12.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+sparrow_parse-0.3.12.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
+sparrow_parse-0.3.12.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
+sparrow_parse-0.3.12.dist-info/RECORD,,