@heripo/pdf-parser 0.1.31 → 0.1.33
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.
- package/README.ko.md +3 -3
- package/README.md +3 -3
- package/dist/index.cjs +1391 -377
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +21 -2
- package/dist/index.d.ts +21 -2
- package/dist/index.js +1391 -377
- package/dist/index.js.map +1 -1
- package/package.json +6 -6
package/dist/index.d.cts
CHANGED
|
@@ -9,10 +9,20 @@ type ReviewAssistanceTaskId = 'text_ocr_hanja' | 'text_integrity' | 'text_role_f
|
|
|
9
9
|
|
|
10
10
|
interface PDFCorrectionModelOptions {
|
|
11
11
|
textCorrection: LanguageModel;
|
|
12
|
+
/** textCorrection 실패(예: lmstudio 400) 시 LLMCaller fallback. */
|
|
13
|
+
textCorrectionFallback?: LanguageModel;
|
|
12
14
|
pageGate: LanguageModel;
|
|
15
|
+
/** pageGate(page-eligibility) 실패 시 fallback. */
|
|
16
|
+
pageGateFallback?: LanguageModel;
|
|
13
17
|
reviewAssistance: LanguageModel;
|
|
18
|
+
/** review-assistance 공통 fallback (task별 미지정 시 사용). */
|
|
19
|
+
reviewAssistanceFallback?: LanguageModel;
|
|
14
20
|
reviewAssistanceTasks?: Partial<Record<ReviewAssistanceTaskId, LanguageModel>>;
|
|
21
|
+
/** review-assistance task별 fallback. */
|
|
22
|
+
reviewAssistanceTasksFallback?: Partial<Record<ReviewAssistanceTaskId, LanguageModel>>;
|
|
15
23
|
tableCorrection?: LanguageModel;
|
|
24
|
+
/** tableCorrection 실패 시 fallback. */
|
|
25
|
+
tableCorrectionFallback?: LanguageModel;
|
|
16
26
|
}
|
|
17
27
|
interface PDFCorrectionConcurrencyOptions {
|
|
18
28
|
pages?: number;
|
|
@@ -32,24 +42,31 @@ interface PDFCorrectionOptions {
|
|
|
32
42
|
models: PDFCorrectionModelOptions;
|
|
33
43
|
concurrency?: PDFCorrectionConcurrencyOptions;
|
|
34
44
|
maxRetries?: PDFCorrectionMaxRetriesOptions;
|
|
35
|
-
|
|
45
|
+
modelConcurrency?: number;
|
|
36
46
|
workItemTimeoutMs?: number;
|
|
37
47
|
outputLanguage?: string;
|
|
38
48
|
pageGate?: PDFCorrectionPageGateOptions;
|
|
39
49
|
autoApplyThreshold?: number;
|
|
40
50
|
proposalThreshold?: number;
|
|
51
|
+
/**
|
|
52
|
+
* When true, every valid review-assistance command auto-applies regardless of
|
|
53
|
+
* confidence threshold or structural block reason (no manual-review routing).
|
|
54
|
+
* Enabled by the engine demo; defaults to false everywhere else.
|
|
55
|
+
*/
|
|
56
|
+
forceAutoApply?: boolean;
|
|
41
57
|
temperature?: number;
|
|
42
58
|
}
|
|
43
59
|
interface NormalizedPDFCorrectionOptions {
|
|
44
60
|
models: PDFCorrectionModelOptions;
|
|
45
61
|
concurrency: Required<PDFCorrectionConcurrencyOptions>;
|
|
46
62
|
maxRetries: Required<PDFCorrectionMaxRetriesOptions>;
|
|
47
|
-
|
|
63
|
+
modelConcurrency: number;
|
|
48
64
|
workItemTimeoutMs: number;
|
|
49
65
|
outputLanguage: string;
|
|
50
66
|
pageGate: Required<PDFCorrectionPageGateOptions>;
|
|
51
67
|
autoApplyThreshold: number;
|
|
52
68
|
proposalThreshold: number;
|
|
69
|
+
forceAutoApply: boolean;
|
|
53
70
|
temperature: number;
|
|
54
71
|
}
|
|
55
72
|
declare const PDF_CORRECTION_DEFAULTS: Omit<NormalizedPDFCorrectionOptions, 'models'>;
|
|
@@ -86,6 +103,8 @@ type PDFConvertOptions = Omit<ConversionOptions, 'to_formats' | 'image_export_mo
|
|
|
86
103
|
chunkMaxRetries?: number;
|
|
87
104
|
/** Vision model for document language detection when the PDF text layer is insufficient */
|
|
88
105
|
languageDetectionModel?: LanguageModel;
|
|
106
|
+
/** languageDetectionModel 실패 시 fallback. */
|
|
107
|
+
languageDetectionFallbackModel?: LanguageModel;
|
|
89
108
|
/** LLM model for document type validation (opt-in: skipped when not set) */
|
|
90
109
|
documentValidationModel?: LanguageModel;
|
|
91
110
|
};
|
package/dist/index.d.ts
CHANGED
|
@@ -9,10 +9,20 @@ type ReviewAssistanceTaskId = 'text_ocr_hanja' | 'text_integrity' | 'text_role_f
|
|
|
9
9
|
|
|
10
10
|
interface PDFCorrectionModelOptions {
|
|
11
11
|
textCorrection: LanguageModel;
|
|
12
|
+
/** textCorrection 실패(예: lmstudio 400) 시 LLMCaller fallback. */
|
|
13
|
+
textCorrectionFallback?: LanguageModel;
|
|
12
14
|
pageGate: LanguageModel;
|
|
15
|
+
/** pageGate(page-eligibility) 실패 시 fallback. */
|
|
16
|
+
pageGateFallback?: LanguageModel;
|
|
13
17
|
reviewAssistance: LanguageModel;
|
|
18
|
+
/** review-assistance 공통 fallback (task별 미지정 시 사용). */
|
|
19
|
+
reviewAssistanceFallback?: LanguageModel;
|
|
14
20
|
reviewAssistanceTasks?: Partial<Record<ReviewAssistanceTaskId, LanguageModel>>;
|
|
21
|
+
/** review-assistance task별 fallback. */
|
|
22
|
+
reviewAssistanceTasksFallback?: Partial<Record<ReviewAssistanceTaskId, LanguageModel>>;
|
|
15
23
|
tableCorrection?: LanguageModel;
|
|
24
|
+
/** tableCorrection 실패 시 fallback. */
|
|
25
|
+
tableCorrectionFallback?: LanguageModel;
|
|
16
26
|
}
|
|
17
27
|
interface PDFCorrectionConcurrencyOptions {
|
|
18
28
|
pages?: number;
|
|
@@ -32,24 +42,31 @@ interface PDFCorrectionOptions {
|
|
|
32
42
|
models: PDFCorrectionModelOptions;
|
|
33
43
|
concurrency?: PDFCorrectionConcurrencyOptions;
|
|
34
44
|
maxRetries?: PDFCorrectionMaxRetriesOptions;
|
|
35
|
-
|
|
45
|
+
modelConcurrency?: number;
|
|
36
46
|
workItemTimeoutMs?: number;
|
|
37
47
|
outputLanguage?: string;
|
|
38
48
|
pageGate?: PDFCorrectionPageGateOptions;
|
|
39
49
|
autoApplyThreshold?: number;
|
|
40
50
|
proposalThreshold?: number;
|
|
51
|
+
/**
|
|
52
|
+
* When true, every valid review-assistance command auto-applies regardless of
|
|
53
|
+
* confidence threshold or structural block reason (no manual-review routing).
|
|
54
|
+
* Enabled by the engine demo; defaults to false everywhere else.
|
|
55
|
+
*/
|
|
56
|
+
forceAutoApply?: boolean;
|
|
41
57
|
temperature?: number;
|
|
42
58
|
}
|
|
43
59
|
interface NormalizedPDFCorrectionOptions {
|
|
44
60
|
models: PDFCorrectionModelOptions;
|
|
45
61
|
concurrency: Required<PDFCorrectionConcurrencyOptions>;
|
|
46
62
|
maxRetries: Required<PDFCorrectionMaxRetriesOptions>;
|
|
47
|
-
|
|
63
|
+
modelConcurrency: number;
|
|
48
64
|
workItemTimeoutMs: number;
|
|
49
65
|
outputLanguage: string;
|
|
50
66
|
pageGate: Required<PDFCorrectionPageGateOptions>;
|
|
51
67
|
autoApplyThreshold: number;
|
|
52
68
|
proposalThreshold: number;
|
|
69
|
+
forceAutoApply: boolean;
|
|
53
70
|
temperature: number;
|
|
54
71
|
}
|
|
55
72
|
declare const PDF_CORRECTION_DEFAULTS: Omit<NormalizedPDFCorrectionOptions, 'models'>;
|
|
@@ -86,6 +103,8 @@ type PDFConvertOptions = Omit<ConversionOptions, 'to_formats' | 'image_export_mo
|
|
|
86
103
|
chunkMaxRetries?: number;
|
|
87
104
|
/** Vision model for document language detection when the PDF text layer is insufficient */
|
|
88
105
|
languageDetectionModel?: LanguageModel;
|
|
106
|
+
/** languageDetectionModel 실패 시 fallback. */
|
|
107
|
+
languageDetectionFallbackModel?: LanguageModel;
|
|
89
108
|
/** LLM model for document type validation (opt-in: skipped when not set) */
|
|
90
109
|
documentValidationModel?: LanguageModel;
|
|
91
110
|
};
|