sparrow-parse 0.4.9__tar.gz → 0.4.10__tar.gz
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-0.4.9 → sparrow-parse-0.4.10}/PKG-INFO +1 -1
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/setup.py +1 -1
- sparrow-parse-0.4.10/sparrow_parse/__init__.py +1 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/mlx_inference.py +5 -6
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/PKG-INFO +1 -1
- sparrow-parse-0.4.9/sparrow_parse/__init__.py +0 -1
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/README.md +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/setup.cfg +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/__main__.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/extractors/__init__.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/extractors/vllm_extractor.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/helpers/__init__.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/helpers/pdf_optimizer.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/processors/__init__.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/processors/table_structure_processor.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/__init__.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/huggingface_inference.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/inference_base.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/inference_factory.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/vllm/local_gpu_inference.py +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/SOURCES.txt +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/dependency_links.txt +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/entry_points.txt +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/requires.txt +0 -0
- {sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: sparrow-parse
|
3
|
-
Version: 0.4.
|
3
|
+
Version: 0.4.10
|
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
|
@@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as fh:
|
|
8
8
|
|
9
9
|
setup(
|
10
10
|
name="sparrow-parse",
|
11
|
-
version="0.4.
|
11
|
+
version="0.4.10",
|
12
12
|
author="Andrej Baranovskij",
|
13
13
|
author_email="andrejus.baranovskis@gmail.com",
|
14
14
|
description="Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents.",
|
@@ -0,0 +1 @@
|
|
1
|
+
__version__ = '0.4.10'
|
@@ -4,9 +4,8 @@ from mlx_vlm.utils import load_image
|
|
4
4
|
from sparrow_parse.vllm.inference_base import ModelInference
|
5
5
|
import os
|
6
6
|
import json
|
7
|
-
from rich
|
7
|
+
from rich import print
|
8
8
|
|
9
|
-
console = Console()
|
10
9
|
|
11
10
|
class MLXInference(ModelInference):
|
12
11
|
"""
|
@@ -21,7 +20,7 @@ class MLXInference(ModelInference):
|
|
21
20
|
:param model_name: Name of the model to load.
|
22
21
|
"""
|
23
22
|
self.model_name = model_name
|
24
|
-
|
23
|
+
print(f"MLXInference initialized for model: {model_name}")
|
25
24
|
|
26
25
|
|
27
26
|
@staticmethod
|
@@ -33,7 +32,7 @@ class MLXInference(ModelInference):
|
|
33
32
|
:return: Tuple containing the loaded model and processor.
|
34
33
|
"""
|
35
34
|
model, processor = load(model_name)
|
36
|
-
|
35
|
+
print(f"Loaded model: {model_name}")
|
37
36
|
return model, processor
|
38
37
|
|
39
38
|
|
@@ -54,7 +53,7 @@ class MLXInference(ModelInference):
|
|
54
53
|
formatted_json = json.loads(cleaned_text)
|
55
54
|
return json.dumps(formatted_json, indent=2)
|
56
55
|
except json.JSONDecodeError as e:
|
57
|
-
|
56
|
+
print(f"Failed to parse JSON in MLX inference backend: {e}")
|
58
57
|
return output_text
|
59
58
|
|
60
59
|
|
@@ -122,7 +121,7 @@ class MLXInference(ModelInference):
|
|
122
121
|
)
|
123
122
|
results.append(self.process_response(response))
|
124
123
|
|
125
|
-
|
124
|
+
print("Inference completed successfully for: ", file_path)
|
126
125
|
|
127
126
|
return results
|
128
127
|
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: sparrow-parse
|
3
|
-
Version: 0.4.
|
3
|
+
Version: 0.4.10
|
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
|
@@ -1 +0,0 @@
|
|
1
|
-
__version__ = '0.4.9'
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{sparrow-parse-0.4.9 → sparrow-parse-0.4.10}/sparrow_parse/processors/table_structure_processor.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|