mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Support tableformer model choice (#90)

Browse Source 
* Support tableformer model choice

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update datamodel structure

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update docs

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Cleanup

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add test unit for table options

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Ensure import backwards-compatibility for PipelineOptions

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update README

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Adjust parameters on custom_convert

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

* Update Dockerfile

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-09-26 21:37:08 +02:00
committed by GitHub
parent 39977b5631
commit d6df76f90b
16 changed files with 711 additions and 592 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@@ -159,6 +159,8 @@ This can improve output quality if you find that multiple columns in extracted t
```python
from docling.datamodel.pipeline_options import PipelineOptions
pipeline_options = PipelineOptions(do_table_structure=True)
pipeline_options.table_structure_options.do_cell_matching = False # uses text cells predicted from table structure model
@@ -168,6 +170,20 @@ doc_converter = DocumentConverter(
)
```
Since docling 1.16.0: You can control which TableFormer mode you want to use. Choose between `TableFormerMode.FAST` (default) and `TableFormerMode.ACCURATE` (better, but slower) to receive better quality with difficult table structures.
```python
from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
pipeline_options = PipelineOptions(do_table_structure=True)
pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE # use more accurate TableFormer model
doc_converter = DocumentConverter(
artifacts_path=artifacts_path,
pipeline_options=pipeline_options,
)
```
### Impose limits on the document size
You can limit the file size and number of pages which should be allowed to process per document: