mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-11 14:18:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Docling JSON ingestion (#783)

Browse Source 
* feat: add Docling JSON ingestion

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* update conversion as per review comments, add tests, revert Docling JSON disambiguation, document intricacies

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* Update docling/backend/json/docling_json_backend.py

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2025-01-24 18:05:23 +01:00
committed by GitHub
parent e9768ae6a5
commit 88a0e66adc
8 changed files with 144 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docling/document_converter.py
View File

@@ -11,6 +11,7 @@ from docling.backend.abstract_backend import AbstractDocumentBackend
from docling.backend.asciidoc_backend import AsciiDocBackend
from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
from docling.backend.html_backend import HTMLDocumentBackend
from docling.backend.json.docling_json_backend import DoclingJSONBackend
from docling.backend.md_backend import MarkdownDocumentBackend
from docling.backend.msexcel_backend import MsExcelDocumentBackend
from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
@@ -136,6 +137,9 @@ def _get_default_option(format: InputFormat) -> FormatOption:
InputFormat.PDF: FormatOption(
pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend
),
InputFormat.JSON_DOCLING: FormatOption(
pipeline_cls=SimplePipeline, backend=DoclingJSONBackend
),
}
if (options := format_to_default_options.get(format)) is not None:
return options