NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add pipeline timings and toggle visualization, establish debug settings (#183)

Browse Source 
* 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>
This commit is contained in:
Christoph Auer
2024-10-30 15:04:19 +01:00
committed by GitHub
parent 94a5290789
commit 2a2c65bf4f
23 changed files with 998 additions and 771 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
docling/pipeline/simple_pipeline.py
View File

@@ -5,9 +5,10 @@ from docling.backend.abstract_backend import (
DeclarativeDocumentBackend,
)
from docling.datamodel.base_models import ConversionStatus
from docling.datamodel.document import ConversionResult, InputDocument
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PipelineOptions
from docling.pipeline.base_pipeline import BasePipeline
from docling.utils.profiling import ProfilingScope, TimeRecorder
_log = logging.getLogger(__name__)
@@ -22,13 +23,11 @@ class SimplePipeline(BasePipeline):
def __init__(self, pipeline_options: PipelineOptions):
super().__init__(pipeline_options)
def _build_document(
self, in_doc: InputDocument, conv_res: ConversionResult
) -> ConversionResult:
def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
if not isinstance(in_doc._backend, DeclarativeDocumentBackend):
if not isinstance(conv_res.input._backend, DeclarativeDocumentBackend):
raise RuntimeError(
f"The selected backend {type(in_doc._backend).__name__} for {in_doc.file} is not a declarative backend. "
f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a declarative backend. "
f"Can not convert this with simple pipeline. "
f"Please check your format configuration on DocumentConverter."
)
@@ -38,13 +37,11 @@ class SimplePipeline(BasePipeline):
# Instead of running a page-level pipeline to build up the document structure,
# the backend is expected to be of type DeclarativeDocumentBackend, which can output
# a DoclingDocument straight.
conv_res.document = in_doc._backend.convert()
with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
conv_res.document = conv_res.input._backend.convert()
return conv_res
def _determine_status(
self, in_doc: InputDocument, conv_res: ConversionResult
) -> ConversionStatus:
def _determine_status(self, conv_res: ConversionResult) -> ConversionStatus:
# This is called only if the previous steps didn't raise.
# Since we don't have anything else to evaluate, we can
# safely return SUCCESS.