@opendataloader/pdf 2.5.6 → 2.5.8
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.md +31 -0
- package/lib/opendataloader-pdf-cli.jar +0 -0
- package/package.json +10 -10
package/README.md
CHANGED
|
@@ -133,6 +133,7 @@ opendataloader_pdf.convert(
|
|
|
133
133
|
| Non-English scanned PDF | Hybrid + OCR | `pip install "opendataloader-pdf[hybrid]"` | `opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang "ko,en"` | `opendataloader-pdf --hybrid docling-fast file1.pdf file2.pdf folder/` |
|
|
134
134
|
| Mathematical formulas | Hybrid + formula | `pip install "opendataloader-pdf[hybrid]"` | `opendataloader-pdf-hybrid --enrich-formula` | `opendataloader-pdf --hybrid docling-fast --hybrid-mode full file1.pdf file2.pdf folder/` |
|
|
135
135
|
| Charts needing description | Hybrid + picture | `pip install "opendataloader-pdf[hybrid]"` | `opendataloader-pdf-hybrid --enrich-picture-description` | `opendataloader-pdf --hybrid docling-fast --hybrid-mode full file1.pdf file2.pdf folder/` |
|
|
136
|
+
| Nested sections for RAG chunking | Hybrid + heading levels | `pip install "opendataloader-pdf[hybrid]"` | `opendataloader-pdf-hybrid --port 5002 --heading-hierarchy` | `opendataloader-pdf --hybrid docling-fast file1.pdf file2.pdf folder/` |
|
|
136
137
|
| Untagged PDFs needing accessibility | Auto-tagging → Tagged PDF | `pip install opendataloader-pdf` | None needed | `opendataloader-pdf --format tagged-pdf file1.pdf file2.pdf folder/` |
|
|
137
138
|
|
|
138
139
|
## Quick Start
|
|
@@ -278,6 +279,36 @@ Output in JSON:
|
|
|
278
279
|
|
|
279
280
|
> Uses SmolVLM (256M), a lightweight vision model. Custom prompts supported via `--picture-description-prompt`.
|
|
280
281
|
|
|
282
|
+
### Heading Hierarchy
|
|
283
|
+
|
|
284
|
+
The layout model labels a region as a section header without a depth, so by default every
|
|
285
|
+
heading comes back at level 1 and subsections sit at the same depth as the document title.
|
|
286
|
+
Flat headings make it hard to tell a section title from a document title when chunking for RAG.
|
|
287
|
+
|
|
288
|
+
`--heading-hierarchy` infers the depth — from the PDF outline first, then section numbering
|
|
289
|
+
(`1.` → `1.1` → `1.1.1`), then visual style:
|
|
290
|
+
|
|
291
|
+
```bash
|
|
292
|
+
# Server
|
|
293
|
+
opendataloader-pdf-hybrid --port 5002 --heading-hierarchy
|
|
294
|
+
|
|
295
|
+
# Client — no extra flag needed
|
|
296
|
+
opendataloader-pdf --hybrid docling-fast file1.pdf file2.pdf folder/
|
|
297
|
+
```
|
|
298
|
+
|
|
299
|
+
```diff
|
|
300
|
+
# 3. Methodology
|
|
301
|
+
- # 3.1. Multi-Object Rectification Network
|
|
302
|
+
+ ## 3.1. Multi-Object Rectification Network
|
|
303
|
+
- # Abstract
|
|
304
|
+
+ ## Abstract
|
|
305
|
+
```
|
|
306
|
+
|
|
307
|
+
Numbering covers numbered sections; style is what pulls an unnumbered `Abstract` or
|
|
308
|
+
`References` out from under the document title.
|
|
309
|
+
|
|
310
|
+
Off by default, so existing output is unchanged. Levels are capped at H6.
|
|
311
|
+
|
|
281
312
|
### Hancom Data Loader Integration — Coming Soon
|
|
282
313
|
|
|
283
314
|
Enterprise-grade AI document analysis via [Hancom Data Loader](https://sdk.hancom.com/en/services/1?utm_source=github&utm_medium=readme&utm_campaign=opendataloader-pdf) — customer-customized models trained on your domain-specific documents. 30+ element types (tables, charts, formulas, captions, footnotes, etc.), VLM-based image/chart understanding, complex table extraction (merged cells, nested tables), SLA-backed OCR for scanned documents, and native HWP/HWPX support. Supports PDF, DOCX, XLSX, PPTX, HWP, PNG, JPG. [Live demo](https://livedemo.sdk.hancom.com/en/dataloader?utm_source=github&utm_medium=readme&utm_campaign=opendataloader-pdf)
|
|
Binary file
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@opendataloader/pdf",
|
|
3
|
-
"version": "2.5.
|
|
3
|
+
"version": "2.5.8",
|
|
4
4
|
"description": "A Node.js wrapper for the opendataloader-pdf Java CLI.",
|
|
5
5
|
"main": "./dist/index.cjs",
|
|
6
6
|
"module": "./dist/index.js",
|
|
@@ -48,17 +48,17 @@
|
|
|
48
48
|
},
|
|
49
49
|
"devDependencies": {
|
|
50
50
|
"@eslint/js": "^10.0.1",
|
|
51
|
-
"@types/node": "^26.
|
|
52
|
-
"@typescript-eslint/eslint-plugin": "^8.
|
|
53
|
-
"@typescript-eslint/parser": "^8.
|
|
54
|
-
"eslint": "^10.
|
|
51
|
+
"@types/node": "^26.4.0",
|
|
52
|
+
"@typescript-eslint/eslint-plugin": "^8.68.0",
|
|
53
|
+
"@typescript-eslint/parser": "^8.68.0",
|
|
54
|
+
"eslint": "^10.9.1",
|
|
55
55
|
"glob": "^13.0.6",
|
|
56
|
-
"globals": "^17.
|
|
57
|
-
"prettier": "^3.
|
|
56
|
+
"globals": "^17.11.0",
|
|
57
|
+
"prettier": "^3.9.6",
|
|
58
58
|
"tsup": "^8.5.1",
|
|
59
|
-
"typescript": "^6.0.
|
|
60
|
-
"vite": "^8.
|
|
61
|
-
"vitest": "^4.1.
|
|
59
|
+
"typescript": "^6.0.3",
|
|
60
|
+
"vite": "^8.2.2",
|
|
61
|
+
"vitest": "^4.1.11"
|
|
62
62
|
},
|
|
63
63
|
"files": [
|
|
64
64
|
"dist",
|