paddleocr-skills 1.0.0 → 1.1.0

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.
Files changed (29) hide show
  1. package/README.md +220 -220
  2. package/bin/paddleocr-skills.js +33 -20
  3. package/lib/copy.js +39 -39
  4. package/lib/installer.js +76 -70
  5. package/lib/prompts.js +67 -67
  6. package/lib/python.js +75 -75
  7. package/lib/verify.js +121 -121
  8. package/package.json +42 -42
  9. package/templates/.env.example +12 -12
  10. package/templates/{paddleocr-vl/references/paddleocr-vl → paddleocr-vl-1.5/references/paddleocr-vl-1.5}/layout_schema.md +64 -64
  11. package/templates/{paddleocr-vl/references/paddleocr-vl → paddleocr-vl-1.5/references/paddleocr-vl-1.5}/output_format.md +154 -154
  12. package/templates/{paddleocr-vl/references/paddleocr-vl → paddleocr-vl-1.5/references/paddleocr-vl-1.5}/vl_model_spec.md +157 -157
  13. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/_lib.py +780 -780
  14. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/configure.py +270 -270
  15. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/optimize_file.py +226 -226
  16. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/requirements-optimize.txt +8 -8
  17. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/requirements.txt +7 -7
  18. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/smoke_test.py +199 -199
  19. package/templates/{paddleocr-vl/scripts/paddleocr-vl → paddleocr-vl-1.5/scripts/paddleocr-vl-1.5}/vl_caller.py +232 -232
  20. package/templates/{paddleocr-vl/skills/paddleocr-vl → paddleocr-vl-1.5/skills/paddleocr-vl-1.5}/SKILL.md +481 -481
  21. package/templates/ppocrv5/references/ppocrv5/agent_policy.md +258 -258
  22. package/templates/ppocrv5/references/ppocrv5/normalized_schema.md +257 -257
  23. package/templates/ppocrv5/references/ppocrv5/provider_api.md +140 -140
  24. package/templates/ppocrv5/scripts/ppocrv5/_lib.py +635 -635
  25. package/templates/ppocrv5/scripts/ppocrv5/configure.py +346 -346
  26. package/templates/ppocrv5/scripts/ppocrv5/ocr_caller.py +684 -684
  27. package/templates/ppocrv5/scripts/ppocrv5/requirements.txt +4 -4
  28. package/templates/ppocrv5/scripts/ppocrv5/smoke_test.py +139 -139
  29. package/templates/ppocrv5/skills/ppocrv5/SKILL.md +272 -272
@@ -1,199 +1,199 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- Smoke Test for PaddleOCR-VL
5
-
6
- Verifies that VL_API_URL and VL_TOKEN are correctly configured
7
- and that the API is accessible.
8
-
9
- Usage:
10
- python scripts/paddleocr-vl/smoke_test.py
11
- python scripts/paddleocr-vl/smoke_test.py --test-url "URL" # Optional custom test
12
- """
13
-
14
- import argparse
15
- import json
16
- import sys
17
- from pathlib import Path
18
-
19
- # Add current directory to Python path
20
- script_dir = Path(__file__).parent
21
- sys.path.insert(0, str(script_dir))
22
-
23
-
24
- def main():
25
- parser = argparse.ArgumentParser(description='PaddleOCR-VL smoke test')
26
- parser.add_argument(
27
- '--test-url',
28
- help='Optional: Custom document URL for testing'
29
- )
30
- parser.add_argument(
31
- '--skip-api-test',
32
- action='store_true',
33
- help='Skip API connectivity test, only check configuration'
34
- )
35
- args = parser.parse_args()
36
-
37
- print("=" * 60)
38
- print("PaddleOCR-VL - Smoke Test")
39
- print("=" * 60)
40
- print()
41
-
42
- # Check configuration
43
- print("\n[1/3] Checking configuration...")
44
-
45
- from _lib import Config
46
-
47
- try:
48
- Config.load_env()
49
-
50
- # Get config values
51
- api_url = Config.get_vl_api_url()
52
- token = Config.get_vl_token()
53
- timeout_ms = Config.get_timeout_ms()
54
- max_retry = Config.get_max_retry()
55
- cache_ttl = Config.get_cache_ttl_sec()
56
-
57
- print(f"+ VL_API_URL: {api_url}")
58
-
59
- # Mask token for display
60
- if len(token) > 12:
61
- masked_token = token[:8] + "..." + token[-4:]
62
- else:
63
- masked_token = "***"
64
- print(f"+ VL_TOKEN: {masked_token}")
65
- print(f"+ Timeout: {timeout_ms}ms")
66
- print(f"+ Max Retry: {max_retry}")
67
- print(f"+ Cache TTL: {cache_ttl}s")
68
- print()
69
-
70
- except Exception as e:
71
- print(f"\nConfiguration error: {e}")
72
- return 1
73
-
74
- # Check imports and dependencies
75
- print("[2/3] Checking dependencies...")
76
- print()
77
-
78
- try:
79
- import httpx
80
- print(f"+ httpx: {httpx.__version__}")
81
-
82
- from dotenv import load_dotenv
83
- print("+ python-dotenv: installed")
84
-
85
- from _lib import VLClient, QualityEvaluator, SimpleCache
86
- print("+ VLClient: OK")
87
- print("+ QualityEvaluator: OK")
88
- print("+ SimpleCache: OK")
89
- print()
90
-
91
- except ImportError as e:
92
- print(f"X Dependency error: {e}")
93
- print()
94
- print("Please install dependencies:")
95
- print(" pip install -r scripts/paddleocr-vl/requirements.txt")
96
- print()
97
- return 1
98
-
99
- # Test API connectivity
100
- if args.skip_api_test:
101
- print("[3/3] Skipping API connectivity test (--skip-api-test)")
102
- print()
103
- print("=" * 60)
104
- print("Configuration Check Complete!")
105
- print("=" * 60)
106
- print()
107
- print("Your PaddleOCR-VL is configured correctly.")
108
- print()
109
- print("To test with a real document, run:")
110
- print(' python scripts/paddleocr-vl/vl_caller.py --file-url "URL"')
111
- print()
112
- return 0
113
-
114
- print("[3/3] Testing API connectivity...")
115
- print()
116
-
117
- # Use provided test URL or default
118
- test_url = args.test_url or "https://paddleocr.bj.bcebos.com/dataset/document_layout_sample.png"
119
-
120
- print(f"Test document: {test_url}")
121
- print("Calling PaddleOCR-VL API...")
122
- print()
123
-
124
- from _lib import make_api_request, QualityEvaluator
125
-
126
- try:
127
- result = make_api_request(
128
- file_url=test_url,
129
- timeout_ms=timeout_ms,
130
- use_cache=False # Force fresh request for testing
131
- )
132
-
133
- if not result.get("ok", False):
134
- error = result.get("error", {})
135
- print(f"X API call failed: {error.get('message', 'Unknown error')}")
136
- print(f" Error code: {error.get('code', 'UNKNOWN')}")
137
- print()
138
- return 1
139
-
140
- print("+ API call successful!")
141
- print()
142
-
143
- # Evaluate quality
144
- quality = QualityEvaluator.evaluate(result)
145
-
146
- print("Response Quality:")
147
- print(f" - Overall Confidence: {quality['overall_confidence']:.2f} / 1.00")
148
- print(f" - Quality Level: {quality['quality_level']}")
149
-
150
- if quality.get('region_stats'):
151
- stats = quality['region_stats']
152
- print(f" - Regions Detected: {stats.get('total_regions', 0)}")
153
-
154
- if stats.get('by_type'):
155
- print(" - Region Types:")
156
- for region_type, count in sorted(stats['by_type'].items()):
157
- print(f" {region_type}: {count}")
158
-
159
- if quality.get('warnings'):
160
- print("\n Warnings:")
161
- for warning in quality['warnings']:
162
- print(f" ! {warning}")
163
-
164
- print()
165
-
166
- # Show sample content
167
- result_data = result.get("result", {})
168
- full_text = result_data.get("full_text", "")
169
-
170
- if full_text:
171
- preview_length = min(200, len(full_text))
172
- print(f"Content Preview ({preview_length} chars):")
173
- print(f" {full_text[:preview_length]}...")
174
- print()
175
-
176
- except Exception as e:
177
- print(f"X API call failed: {e}")
178
- print()
179
- return 1
180
-
181
- # Success
182
- print("=" * 60)
183
- print("All Tests Passed!")
184
- print("=" * 60)
185
- print()
186
- print("Your PaddleOCR-VL setup is working correctly.")
187
- print()
188
- print("Next steps:")
189
- print(' - Parse documents: python scripts/paddleocr-vl/vl_caller.py --file-url "URL"')
190
- print(' - Show quality info: Add --show-quality flag')
191
- print(' - Pretty JSON: Add --pretty flag')
192
- print()
193
-
194
- return 0
195
-
196
-
197
- if __name__ == '__main__':
198
- exit_code = main()
199
- sys.exit(exit_code)
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ Smoke Test for PaddleOCR-VL 1.5
5
+
6
+ Verifies that VL_API_URL and VL_TOKEN are correctly configured
7
+ and that the API is accessible.
8
+
9
+ Usage:
10
+ python scripts/paddleocr-vl-1.5/smoke_test.py
11
+ python scripts/paddleocr-vl-1.5/smoke_test.py --test-url "URL" # Optional custom test
12
+ """
13
+
14
+ import argparse
15
+ import json
16
+ import sys
17
+ from pathlib import Path
18
+
19
+ # Add current directory to Python path
20
+ script_dir = Path(__file__).parent
21
+ sys.path.insert(0, str(script_dir))
22
+
23
+
24
+ def main():
25
+ parser = argparse.ArgumentParser(description='PaddleOCR-VL 1.5 smoke test')
26
+ parser.add_argument(
27
+ '--test-url',
28
+ help='Optional: Custom document URL for testing'
29
+ )
30
+ parser.add_argument(
31
+ '--skip-api-test',
32
+ action='store_true',
33
+ help='Skip API connectivity test, only check configuration'
34
+ )
35
+ args = parser.parse_args()
36
+
37
+ print("=" * 60)
38
+ print("PaddleOCR-VL 1.5 - Smoke Test")
39
+ print("=" * 60)
40
+ print()
41
+
42
+ # Check configuration
43
+ print("\n[1/3] Checking configuration...")
44
+
45
+ from _lib import Config
46
+
47
+ try:
48
+ Config.load_env()
49
+
50
+ # Get config values
51
+ api_url = Config.get_vl_api_url()
52
+ token = Config.get_vl_token()
53
+ timeout_ms = Config.get_timeout_ms()
54
+ max_retry = Config.get_max_retry()
55
+ cache_ttl = Config.get_cache_ttl_sec()
56
+
57
+ print(f"+ VL_API_URL: {api_url}")
58
+
59
+ # Mask token for display
60
+ if len(token) > 12:
61
+ masked_token = token[:8] + "..." + token[-4:]
62
+ else:
63
+ masked_token = "***"
64
+ print(f"+ VL_TOKEN: {masked_token}")
65
+ print(f"+ Timeout: {timeout_ms}ms")
66
+ print(f"+ Max Retry: {max_retry}")
67
+ print(f"+ Cache TTL: {cache_ttl}s")
68
+ print()
69
+
70
+ except Exception as e:
71
+ print(f"\nConfiguration error: {e}")
72
+ return 1
73
+
74
+ # Check imports and dependencies
75
+ print("[2/3] Checking dependencies...")
76
+ print()
77
+
78
+ try:
79
+ import httpx
80
+ print(f"+ httpx: {httpx.__version__}")
81
+
82
+ from dotenv import load_dotenv
83
+ print("+ python-dotenv: installed")
84
+
85
+ from _lib import VLClient, QualityEvaluator, SimpleCache
86
+ print("+ VLClient: OK")
87
+ print("+ QualityEvaluator: OK")
88
+ print("+ SimpleCache: OK")
89
+ print()
90
+
91
+ except ImportError as e:
92
+ print(f"X Dependency error: {e}")
93
+ print()
94
+ print("Please install dependencies:")
95
+ print(" pip install -r scripts/paddleocr-vl-1.5/requirements.txt")
96
+ print()
97
+ return 1
98
+
99
+ # Test API connectivity
100
+ if args.skip_api_test:
101
+ print("[3/3] Skipping API connectivity test (--skip-api-test)")
102
+ print()
103
+ print("=" * 60)
104
+ print("Configuration Check Complete!")
105
+ print("=" * 60)
106
+ print()
107
+ print("Your PaddleOCR-VL 1.5 is configured correctly.")
108
+ print()
109
+ print("To test with a real document, run:")
110
+ print(' python scripts/paddleocr-vl-1.5/vl_caller.py --file-url "URL"')
111
+ print()
112
+ return 0
113
+
114
+ print("[3/3] Testing API connectivity...")
115
+ print()
116
+
117
+ # Use provided test URL or default
118
+ test_url = args.test_url or "https://paddleocr.bj.bcebos.com/dataset/document_layout_sample.png"
119
+
120
+ print(f"Test document: {test_url}")
121
+ print("Calling PaddleOCR-VL 1.5 API...")
122
+ print()
123
+
124
+ from _lib import make_api_request, QualityEvaluator
125
+
126
+ try:
127
+ result = make_api_request(
128
+ file_url=test_url,
129
+ timeout_ms=timeout_ms,
130
+ use_cache=False # Force fresh request for testing
131
+ )
132
+
133
+ if not result.get("ok", False):
134
+ error = result.get("error", {})
135
+ print(f"X API call failed: {error.get('message', 'Unknown error')}")
136
+ print(f" Error code: {error.get('code', 'UNKNOWN')}")
137
+ print()
138
+ return 1
139
+
140
+ print("+ API call successful!")
141
+ print()
142
+
143
+ # Evaluate quality
144
+ quality = QualityEvaluator.evaluate(result)
145
+
146
+ print("Response Quality:")
147
+ print(f" - Overall Confidence: {quality['overall_confidence']:.2f} / 1.00")
148
+ print(f" - Quality Level: {quality['quality_level']}")
149
+
150
+ if quality.get('region_stats'):
151
+ stats = quality['region_stats']
152
+ print(f" - Regions Detected: {stats.get('total_regions', 0)}")
153
+
154
+ if stats.get('by_type'):
155
+ print(" - Region Types:")
156
+ for region_type, count in sorted(stats['by_type'].items()):
157
+ print(f" {region_type}: {count}")
158
+
159
+ if quality.get('warnings'):
160
+ print("\n Warnings:")
161
+ for warning in quality['warnings']:
162
+ print(f" ! {warning}")
163
+
164
+ print()
165
+
166
+ # Show sample content
167
+ result_data = result.get("result", {})
168
+ full_text = result_data.get("full_text", "")
169
+
170
+ if full_text:
171
+ preview_length = min(200, len(full_text))
172
+ print(f"Content Preview ({preview_length} chars):")
173
+ print(f" {full_text[:preview_length]}...")
174
+ print()
175
+
176
+ except Exception as e:
177
+ print(f"X API call failed: {e}")
178
+ print()
179
+ return 1
180
+
181
+ # Success
182
+ print("=" * 60)
183
+ print("All Tests Passed!")
184
+ print("=" * 60)
185
+ print()
186
+ print("Your PaddleOCR-VL 1.5 setup is working correctly.")
187
+ print()
188
+ print("Next steps:")
189
+ print(' - Parse documents: python scripts/paddleocr-vl-1.5/vl_caller.py --file-url "URL"')
190
+ print(' - Show quality info: Add --show-quality flag')
191
+ print(' - Pretty JSON: Add --pretty flag')
192
+ print()
193
+
194
+ return 0
195
+
196
+
197
+ if __name__ == '__main__':
198
+ exit_code = main()
199
+ sys.exit(exit_code)