@opendataloader/pdf 1.6.0 → 1.6.2
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 +2 -2
- package/lib/opendataloader-pdf-cli.jar +0 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -193,7 +193,7 @@ For documents with complex tables or OCR needs, enable hybrid mode to route chal
|
|
|
193
193
|
**Results**: Table accuracy jumps from 0.49 → 0.93 (+90%) with acceptable speed trade-off.
|
|
194
194
|
|
|
195
195
|
```bash
|
|
196
|
-
pip install opendataloader-pdf[hybrid]
|
|
196
|
+
pip install -U "opendataloader-pdf[hybrid]"
|
|
197
197
|
```
|
|
198
198
|
|
|
199
199
|
Terminal 1: Start the backend server
|
|
@@ -332,7 +332,7 @@ This means: consistent output (same input = same output), no GPU required, faste
|
|
|
332
332
|
|
|
333
333
|
### How do I get better accuracy for complex tables?
|
|
334
334
|
|
|
335
|
-
Enable hybrid mode with `pip install opendataloader-pdf[hybrid]`. This routes pages with complex tables to an AI backend (like docling-serve) while keeping simple pages fast and local. Table accuracy improves from 0.49 to 0.93 — matching or exceeding dedicated AI parsers while remaining faster and more cost-effective.
|
|
335
|
+
Enable hybrid mode with `pip install -U "opendataloader-pdf[hybrid]"`. This routes pages with complex tables to an AI backend (like docling-serve) while keeping simple pages fast and local. Table accuracy improves from 0.49 to 0.93 — matching or exceeding dedicated AI parsers while remaining faster and more cost-effective.
|
|
336
336
|
|
|
337
337
|
<br/>
|
|
338
338
|
|
|
Binary file
|