sparrow-parse 0.3.10__py3-none-any.whl → 0.3.12__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
sparrow_parse/__init__.py CHANGED
@@ -1 +1 @@
1
- __version__ = '0.3.10'
1
+ __version__ = '0.3.12'
@@ -71,8 +71,8 @@ if __name__ == "__main__":
71
71
  #
72
72
  # input_data = [
73
73
  # {
74
- # "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/bonds_table.png",
75
- # "text_input": "retrieve all data. return response in JSON format"
74
+ # "file_path": "/Users/andrejb/Work/katana-git/sparrow/sparrow-ml/llm/data/oracle_10k_2014_q1_small.pdf",
75
+ # "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}]}"
76
76
  # }
77
77
  # ]
78
78
  #
@@ -52,7 +52,7 @@ class MLXInference(ModelInference):
52
52
  formatted_json = json.loads(cleaned_text)
53
53
  return json.dumps(formatted_json, indent=2)
54
54
  except json.JSONDecodeError as e:
55
- print(f"Failed to parse JSON: {e}")
55
+ print(f"Failed to parse JSON in MLX inference backend: {e}")
56
56
  return output_text
57
57
 
58
58
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: sparrow-parse
3
- Version: 0.3.10
3
+ Version: 0.3.12
4
4
  Summary: Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.
5
5
  Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
6
6
  Author: Andrej Baranovskij
@@ -24,7 +24,7 @@ Requires-Dist: pypdf==4.3.0
24
24
  Requires-Dist: easyocr==1.7.1
25
25
  Requires-Dist: gradio-client
26
26
  Requires-Dist: pdf2image
27
- Requires-Dist: mlx-vlm==0.1.3; sys_platform == "darwin" and platform_machine == "arm64"
27
+ Requires-Dist: mlx-vlm==0.1.4; sys_platform == "darwin" and platform_machine == "arm64"
28
28
 
29
29
  # Sparrow Parse
30
30
 
@@ -1,7 +1,7 @@
1
- sparrow_parse/__init__.py,sha256=YyN4-dnVQeKd30rccto2XJ8ERgp51WS0HBUkdIT5w30,22
1
+ sparrow_parse/__init__.py,sha256=_ZihGlMI7X-0KVVWL_iXdUXrQS9gun7MiVTXSd1Xs4o,22
2
2
  sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
3
3
  sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
- sparrow_parse/extractors/vllm_extractor.py,sha256=X59LFA4882JE6wrvUQDjbfY7aHOT4gFLwO4ll_qPPfs,3464
4
+ sparrow_parse/extractors/vllm_extractor.py,sha256=E2-Zpfssu2MVkmVjHpjBh9WK3rJ7ywHhMjJX3xZB_H8,3648
5
5
  sparrow_parse/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
6
6
  sparrow_parse/helpers/pdf_optimizer.py,sha256=GIqQYWtixFeZGCRFXL0lQfQByapCDuQzzRHAkzcPwLE,3302
7
7
  sparrow_parse/processors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -11,9 +11,9 @@ sparrow_parse/vllm/huggingface_inference.py,sha256=EJnG6PesGKMc_0qGPN8ufE6pSnhAg
11
11
  sparrow_parse/vllm/inference_base.py,sha256=4mwGoAY63MB4cHZpV0czTkJWEzimmiTzqqzKmLNzgjw,820
12
12
  sparrow_parse/vllm/inference_factory.py,sha256=FTM65O-dW2WZchHOrNN7_Q3-FlVoAc65iSptuuUuClM,1166
13
13
  sparrow_parse/vllm/local_gpu_inference.py,sha256=aHoJTejb5xrXjWDIGu5RBQWEyRCOBCB04sMvO2Wyvg8,628
14
- sparrow_parse/vllm/mlx_inference.py,sha256=3srKhlhVRoYqeVy_PziNZRHcHl6D3ksibvcOAug4irA,4723
15
- sparrow_parse-0.3.10.dist-info/METADATA,sha256=72zj9FjWhiP8M0FijRzeC_tJSjlDeOyFo9ZJ2409-Ik,6351
16
- sparrow_parse-0.3.10.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
17
- sparrow_parse-0.3.10.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
18
- sparrow_parse-0.3.10.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
19
- sparrow_parse-0.3.10.dist-info/RECORD,,
14
+ sparrow_parse/vllm/mlx_inference.py,sha256=xR40qwjIR0HvrN8x58oOq6F4r1hEANRB-9kcokUQHHU,4748
15
+ sparrow_parse-0.3.12.dist-info/METADATA,sha256=tgTHQSWokNEc0TOry7EpunttLgYXYd6GEx6bzedb25s,6351
16
+ sparrow_parse-0.3.12.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
17
+ sparrow_parse-0.3.12.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
18
+ sparrow_parse-0.3.12.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
19
+ sparrow_parse-0.3.12.dist-info/RECORD,,