sparrow-parse 0.3.10__tar.gz → 0.3.11__tar.gz

{sparrow-parse-0.3.10 → sparrow-parse-0.3.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.3.10
+Version: 0.3.11
 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-0.3.10 → sparrow-parse-0.3.11}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as fh:
 
 setup(
     name="sparrow-parse",
-    version="0.3.10",
+    version="0.3.11",
     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-0.3.11/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.3.11'

{sparrow-parse-0.3.10 → sparrow-parse-0.3.11}/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/bonds_table.png",
-    #         "text_input": "retrieve all 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, 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-0.3.10 → sparrow-parse-0.3.11}/sparrow_parse/vllm/mlx_inference.py

@@ -52,7 +52,7 @@ 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: {e}")
+            print(f"Failed to parse JSON in MLX inference backend: {e}")
             return output_text
 
 

{sparrow-parse-0.3.10 → sparrow-parse-0.3.11}/sparrow_parse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.3.10
+Version: 0.3.11
 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-0.3.10/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.3.10'