Christoph Auer 9f4bc5b2f1 feat: [Beta] Extraction with schema (#2138) ...

* Add DocumentConverter.extract and full extraction pipeline

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

* Add DocumentConverter.extract template arg

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

* Add NuExtract model

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

* Add Extraction pipeline

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

* Add proper test, support pydantic class types

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

* Add qr bill example

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

* Add base_extraction_pipeline

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

* Add types

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

* Update typing of ExtractionResult and inner fields

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

* Factor out extract to DocumentExtractor

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

* Address mypy issues

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

* Add DocumentExtractor

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

* Resolve circular import issue

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

* Clean up imports, remove Optional for template arg

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

* Move new type definitions into datamodel

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

* Update comments

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

* Respect page-range, disable test_extraction for CI

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

---------

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

2025-09-01 16:09:48 +02:00

285 KiB

Vendored

1021x1423px

Raw History