feat: Code and equation model for PDF and code blocks in markdown (#752)

* propagated changes for new CodeItem class

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* Rebased branch on latest main. changes for CodeItem

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* removed unused files

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* chore: update lockfile

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

* pin latest docling-core

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update docling-core pinning

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* pin docling-core

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* use new add_code in backends and update typing in MD backend

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* added if statement for backend

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* removed unused import

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* removed print statements

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* gt for new pdf

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* Update docling/pipeline/standard_pdf_pipeline.py

Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Signed-off-by: Matteo <43417658+Matteo-Omenetti@users.noreply.github.com>

* fixed doc comment of __call__ function of code_formula_model

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>

* fix artifacts_path type

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* move imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* move expansion_factor to base class

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Matteo <43417658+Matteo-Omenetti@users.noreply.github.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

docling/pipeline/base_pipeline.py

@@ -3,7 +3,7 @@ import logging
 import time
 import traceback
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable, List
+from typing import Any, Callable, Iterable, List
 
 from docling_core.types.doc import DoclingDocument, NodeItem
 
@@ -18,7 +18,7 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult, InputDocument
 from docling.datamodel.pipeline_options import PipelineOptions
 from docling.datamodel.settings import settings
-from docling.models.base_model import BaseEnrichmentModel
+from docling.models.base_model import GenericEnrichmentModel
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 from docling.utils.utils import chunkify
 
@@ -30,7 +30,7 @@ class BasePipeline(ABC):
         self.pipeline_options = pipeline_options
         self.keep_images = False
         self.build_pipe: List[Callable] = []
-        self.enrichment_pipe: List[BaseEnrichmentModel] = []
+        self.enrichment_pipe: List[GenericEnrichmentModel[Any]] = []
 
     def execute(self, in_doc: InputDocument, raises_on_error: bool) -> ConversionResult:
         conv_res = ConversionResult(input=in_doc)
@@ -66,7 +66,7 @@ class BasePipeline(ABC):
     def _enrich_document(self, conv_res: ConversionResult) -> ConversionResult:
 
         def _prepare_elements(
-            conv_res: ConversionResult, model: BaseEnrichmentModel
+            conv_res: ConversionResult, model: GenericEnrichmentModel[Any]
         ) -> Iterable[NodeItem]:
             for doc_element, _level in conv_res.document.iterate_items():
                 prepared_element = model.prepare_element(