feat: updated vlm pipeline (with latest changes from docling-core) (#1158)

* Draft implementation of Doctag backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated VLM pipeline doctags to docling conversion, now properly supports lists

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* preparing to migrate to new doctags deserializer

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* re-using DocTagsDocument.from_doctags_and_image_pairs

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* satisfying mypy and other checks

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added support for force_backend_text parameter

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* removed unnecessary transformation

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Update tests

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

* Updated readme

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2025-03-18 15:44:51 +01:00
committed by GitHub
parent 1a2a9e4eff
commit 2f72167ff6
5 changed files with 62 additions and 396 deletions

View File

@@ -2,7 +2,7 @@
<html lang="en">
<head>
<link rel="icon" type="image/png"
href="https://ds4sd.github.io/docling/assets/logo.png"/>
href="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"/>
<meta charset="UTF-8">
<title>
Powered by Docling