docling-jobkit 1.7.1__tar.gz → 1.8.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/PKG-INFO +3 -3
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/convert/manager.py +18 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/pyproject.toml +3 -3
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/.gitignore +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/LICENSE +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/README.md +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/cli/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/cli/local.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/google_drive_helper.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/google_drive_source_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/google_drive_target_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/http_source_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/s3_helper.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/s3_source_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/s3_target_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/source_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/source_processor_factory.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/target_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/target_processor_factory.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/convert/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/convert/chunking.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/convert/results.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/convert/results_processor.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/callback.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/chunking.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/convert.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/google_drive_coords.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/http_inputs.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/result.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/s3_coords.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/task.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/task_meta.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/task_sources.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/task_targets.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling-s3in-s3out.yaml +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling_s3in_s3out.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling_s3in_s3out_with_infer.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling_s3in_s3out_with_infer.yaml +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/base_notifier.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/base_orchestrator.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/kfp_pipeline.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/notify.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/orchestrator.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/local/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/local/orchestrator.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/local/worker.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/rq/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/rq/orchestrator.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/rq/worker.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/py.typed +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/ray_job/__init__.py +0 -0
- {docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/ray_job/main.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: docling-jobkit
|
|
3
|
-
Version: 1.
|
|
3
|
+
Version: 1.8.0
|
|
4
4
|
Summary: Running a distributed job processing documents with Docling.
|
|
5
5
|
Project-URL: Homepage, https://github.com/docling-project/docling-jobkit
|
|
6
6
|
Project-URL: Repository, https://github.com/docling-project/docling-jobkit
|
|
@@ -25,7 +25,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
|
25
25
|
Classifier: Typing :: Typed
|
|
26
26
|
Requires-Python: >=3.10
|
|
27
27
|
Requires-Dist: boto3~=1.35
|
|
28
|
-
Requires-Dist: docling~=2.
|
|
28
|
+
Requires-Dist: docling~=2.60
|
|
29
29
|
Requires-Dist: fastparquet~=2024.11
|
|
30
30
|
Requires-Dist: httpx~=0.28
|
|
31
31
|
Requires-Dist: pandas~=2.2
|
|
@@ -45,7 +45,7 @@ Provides-Extra: rq
|
|
|
45
45
|
Requires-Dist: msgpack~=1.1; extra == 'rq'
|
|
46
46
|
Requires-Dist: rq~=2.4; extra == 'rq'
|
|
47
47
|
Provides-Extra: vlm
|
|
48
|
-
Requires-Dist: docling[vlm]~=2.
|
|
48
|
+
Requires-Dist: docling[vlm]~=2.60; extra == 'vlm'
|
|
49
49
|
Description-Content-Type: text/markdown
|
|
50
50
|
|
|
51
51
|
# Docling Jobkit
|
|
@@ -50,6 +50,13 @@ class DoclingConverterManagerConfig(BaseModel):
|
|
|
50
50
|
max_num_pages: int = sys.maxsize
|
|
51
51
|
max_file_size: int = sys.maxsize
|
|
52
52
|
|
|
53
|
+
# Threading pipeline
|
|
54
|
+
queue_max_size: Optional[int] = None
|
|
55
|
+
ocr_batch_size: Optional[int] = None
|
|
56
|
+
layout_batch_size: Optional[int] = None
|
|
57
|
+
table_batch_size: Optional[int] = None
|
|
58
|
+
batch_polling_interval_seconds: Optional[float] = None
|
|
59
|
+
|
|
53
60
|
|
|
54
61
|
# Custom serializer for PdfFormatOption
|
|
55
62
|
# (model_dump_json does not work with some classes)
|
|
@@ -202,6 +209,17 @@ class DoclingConverterManager:
|
|
|
202
209
|
request.picture_description_area_threshold
|
|
203
210
|
)
|
|
204
211
|
|
|
212
|
+
# Forward the definition of the following attributes, if they are not none
|
|
213
|
+
for attr in (
|
|
214
|
+
"queue_max_size",
|
|
215
|
+
"ocr_batch_size",
|
|
216
|
+
"layout_batch_size",
|
|
217
|
+
"table_batch_size",
|
|
218
|
+
"batch_polling_interval_seconds",
|
|
219
|
+
):
|
|
220
|
+
if value := getattr(self.config, attr):
|
|
221
|
+
setattr(pipeline_options, attr, value)
|
|
222
|
+
|
|
205
223
|
return pipeline_options
|
|
206
224
|
|
|
207
225
|
def _parse_backend(
|
|
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "docling-jobkit"
|
|
7
|
-
version = "1.
|
|
7
|
+
version = "1.8.0" # DO NOT EDIT, updated automatically
|
|
8
8
|
description = "Running a distributed job processing documents with Docling."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
license = "MIT"
|
|
@@ -41,7 +41,7 @@ classifiers = [
|
|
|
41
41
|
]
|
|
42
42
|
requires-python = ">=3.10"
|
|
43
43
|
dependencies = [
|
|
44
|
-
"docling~=2.
|
|
44
|
+
"docling~=2.60",
|
|
45
45
|
"pydantic~=2.10",
|
|
46
46
|
"pydantic-settings~=2.4",
|
|
47
47
|
"typer~=0.12",
|
|
@@ -55,7 +55,7 @@ dependencies = [
|
|
|
55
55
|
|
|
56
56
|
[project.optional-dependencies]
|
|
57
57
|
vlm = [
|
|
58
|
-
"docling[vlm]~=2.
|
|
58
|
+
"docling[vlm]~=2.60",
|
|
59
59
|
]
|
|
60
60
|
# asr = [
|
|
61
61
|
# "docling[asr]~=2.53",
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/google_drive_helper.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/http_source_processor.py
RENAMED
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/s3_source_processor.py
RENAMED
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/s3_target_processor.py
RENAMED
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/source_processor_factory.py
RENAMED
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/connectors/target_processor_factory.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/datamodel/google_drive_coords.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling-s3in-s3out.yaml
RENAMED
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/kfp_pipeline/docling_s3in_s3out.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/base_orchestrator.py
RENAMED
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/kfp_pipeline.py
RENAMED
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/kfp/orchestrator.py
RENAMED
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/local/__init__.py
RENAMED
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/local/orchestrator.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{docling_jobkit-1.7.1 → docling_jobkit-1.8.0}/docling_jobkit/orchestrators/rq/orchestrator.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|