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>

README.md

@@ -34,12 +34,12 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 Local execution capabilities for sensitive data and air-gapped environments
 * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 Extensive OCR support for scanned PDFs and images
+* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 💻 Simple and convenient CLI
 
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
-* 📝 Inclusion of Visual Language Models ([SmolDocling](https://huggingface.co/blog/smolervlm#smoldocling))
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)