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>
This commit is contained in:
@@ -1,17 +1,11 @@
|
||||
import logging
|
||||
import os
|
||||
import warnings
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Annotated, Any, Dict, List, Literal, Optional, Tuple, Type, Union
|
||||
from typing import Any, List, Literal, Optional, Union
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
|
||||
from pydantic_settings import (
|
||||
BaseSettings,
|
||||
PydanticBaseSettingsSource,
|
||||
SettingsConfigDict,
|
||||
)
|
||||
from typing_extensions import deprecated
|
||||
from pydantic import BaseModel, ConfigDict, Field, model_validator
|
||||
from pydantic_settings import BaseSettings, SettingsConfigDict
|
||||
|
||||
_log = logging.getLogger(__name__)
|
||||
|
||||
@@ -225,6 +219,8 @@ class PdfPipelineOptions(PipelineOptions):
|
||||
artifacts_path: Optional[Union[Path, str]] = None
|
||||
do_table_structure: bool = True # True: perform table structure extraction
|
||||
do_ocr: bool = True # True: perform OCR, replace programmatic PDF text
|
||||
do_code_enrichment: bool = False # True: perform code OCR
|
||||
do_formula_enrichment: bool = False # True: perform formula OCR, return Latex code
|
||||
|
||||
table_structure_options: TableStructureOptions = TableStructureOptions()
|
||||
ocr_options: Union[
|
||||
|
||||
Reference in New Issue
Block a user