Docling/docling/models/base_model.py
Christoph Auer 2a2c65bf4f
feat: Add pipeline timings and toggle visualization, establish debug settings (#183)
* Add settings to turn visualization on or off

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

* Add profiling code to all models

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

* Refactor and fix profiling codes

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

* Visualization codes output PNG to debug dir

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

* Fixes for time logging

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

* Optimize imports

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

* Update lockfile

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

* Add start_timestamps to ProfilingItem

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

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-30 15:04:19 +01:00

29 lines
701 B
Python

from abc import ABC, abstractmethod
from typing import Any, Iterable
from docling_core.types.doc import DoclingDocument, NodeItem
from docling.datamodel.base_models import Page
from docling.datamodel.document import ConversionResult
class BasePageModel(ABC):
@abstractmethod
def __call__(
self, conv_res: ConversionResult, page_batch: Iterable[Page]
) -> Iterable[Page]:
pass
class BaseEnrichmentModel(ABC):
@abstractmethod
def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
pass
@abstractmethod
def __call__(
self, doc: DoclingDocument, element_batch: Iterable[NodeItem]
) -> Iterable[Any]:
pass