sparrow-parse 0.4.7__py3-none-any.whl → 0.4.9__py3-none-any.whl

sparrow_parse/__init__.py

@@ -1 +1 @@
-__version__ = '0.4.7'
+__version__ = '0.4.9'

sparrow_parse/extractors/vllm_extractor.py

@@ -152,34 +152,34 @@ 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-7B-Instruct-8bit",
-        # "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/invoice_1.jpg",
-            "text_input": "retrieve document data. return response in JSON format"
-        }
-    ]
-
-    # 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,
-                                                       generic_query=False,
-                                                       debug_dir="/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/",
-                                                       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-7B-Instruct-8bit",
+    #     # "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/invoice_1.jpg",
+    #         "text_input": "retrieve document data. return response in JSON format"
+    #     }
+    # ]
+    #
+    # # 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,
+    #                                                    generic_query=False,
+    #                                                    debug_dir="/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/",
+    #                                                    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/vllm/mlx_inference.py

@@ -4,7 +4,9 @@ from mlx_vlm.utils import load_image
 from sparrow_parse.vllm.inference_base import ModelInference
 import os
 import json
+from rich.console import Console
 
+console = Console()
 
 class MLXInference(ModelInference):
     """
@@ -19,7 +21,7 @@ class MLXInference(ModelInference):
         :param model_name: Name of the model to load.
         """
         self.model_name = model_name
-        print(f"MLXInference initialized for model: {model_name}")
+        console.print(f"MLXInference initialized for model: {model_name}")
 
 
     @staticmethod
@@ -31,7 +33,7 @@ class MLXInference(ModelInference):
         :return: Tuple containing the loaded model and processor.
         """
         model, processor = load(model_name)
-        print(f"Loaded model: {model_name}")
+        console.print(f"Loaded model: {model_name}")
         return model, processor
 
 
@@ -52,7 +54,7 @@ class MLXInference(ModelInference):
             formatted_json = json.loads(cleaned_text)
             return json.dumps(formatted_json, indent=2)
         except json.JSONDecodeError as e:
-            print(f"Failed to parse JSON in MLX inference backend: {e}")
+            console.print(f"Failed to parse JSON in MLX inference backend: {e}")
             return output_text
 
 
@@ -120,7 +122,7 @@ class MLXInference(ModelInference):
             )
             results.append(self.process_response(response))
 
-            print("Inference completed successfully for: ", file_path)
+            console.print("Inference completed successfully for: ", file_path)
 
         return results
 

{sparrow_parse-0.4.7.dist-info → sparrow_parse-0.4.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.4.7
+Version: 0.4.9
 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

{sparrow_parse-0.4.7.dist-info → sparrow_parse-0.4.9.dist-info}/RECORD

@@ -1,7 +1,7 @@
-sparrow_parse/__init__.py,sha256=swwUIK4WtUiYyZYTfyyc_9CkUUoMvY9Mrqd1fsqa9_E,21
+sparrow_parse/__init__.py,sha256=HVLYuTxwxepBhsoeROAeognEnSW-LkbZ_mSNgbAcTqA,21
 sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
 sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sparrow_parse/extractors/vllm_extractor.py,sha256=G4kQh0GoZ4V4TdyeDwZWFkOG15MQCQMvSf2UbFQDWeI,7746
+sparrow_parse/extractors/vllm_extractor.py,sha256=PDLgLlKiq3Bv-UOQTzX3AgxNOLcEU2EniGAXLjMC30U,7820
 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
@@ -11,9 +11,9 @@ sparrow_parse/vllm/huggingface_inference.py,sha256=EJnG6PesGKMc_0qGPN8ufE6pSnhAg
 sparrow_parse/vllm/inference_base.py,sha256=4mwGoAY63MB4cHZpV0czTkJWEzimmiTzqqzKmLNzgjw,820
 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=9PgcPf5uvAmbRmuUD1BOs_WZqzx82hFdoWMUcTLdJ50,4876
-sparrow_parse-0.4.7.dist-info/METADATA,sha256=KX74XdEuoK7fGg0haxPlo6Oyx3HLA-kDyfACDJEouJY,6432
-sparrow_parse-0.4.7.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-sparrow_parse-0.4.7.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
-sparrow_parse-0.4.7.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
-sparrow_parse-0.4.7.dist-info/RECORD,,
+sparrow_parse/vllm/mlx_inference.py,sha256=jlycb0WwpQKGkfCrYYgirOdXrqEV6RROB86dmBvAlrU,4961
+sparrow_parse-0.4.9.dist-info/METADATA,sha256=vunHfk8AaOMZGvmR-5oeph45PBfJMiiYKRbSBGZ-AGA,6432
+sparrow_parse-0.4.9.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+sparrow_parse-0.4.9.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
+sparrow_parse-0.4.9.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
+sparrow_parse-0.4.9.dist-info/RECORD,,