Skip to content

perf: 25% speed gain on json serialization through orjson... #455

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
VerdantForge wants to merge 3 commits into
base: main
Choose a base branch
from
Open

perf: 25% speed gain on json serialization through orjson... #455

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5b83903
feat: orjson implementation into save_to_json
VerdantForge Dec 10, 2025
f349410
fix: clean up orjson integration for review approval
claude May 3, 2026
fc0ac8b
chore: align imports and deps with upstream main to resolve conflicts
claude May 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions docling_core/types/doc/document.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,13 @@
import sys
import typing
import warnings
from collections.abc import Iterable
from dataclasses import dataclass
from enum import Enum
from io import BytesIO
from pathlib import Path
from typing import (
Annotated,
Any,
Dict,
Final,
Expand All @@ -28,6 +31,7 @@
)
from urllib.parse import unquote

import orjson
import pandas as pd
import yaml
from PIL import Image as PILImage
Expand All @@ -37,15 +41,17 @@
ConfigDict,
Field,
FieldSerializationInfo,
SerializerFunctionWrapHandler,
StringConstraints,
computed_field,
field_serializer,
field_validator,
model_serializer,
model_validator,
validate_call,
)
from tabulate import tabulate
from typing_extensions import Annotated, Self, deprecated, override
from tabulate import _column_type, tabulate
from typing_extensions import Self, deprecated, override

from docling_core.search.package import VERSION_PATTERN
from docling_core.types.base import _JSON_POINTER_REGEX
Expand Down Expand Up @@ -4860,7 +4866,10 @@ def save_as_json(
coord_precision: Optional[int] = None,
confid_precision: Optional[int] = None,
):
"""Save as json."""
"""
Save as json.
Indent can either be 2 or 0 (no indent).
"""
if isinstance(filename, str):
filename = Path(filename)
artifacts_dir, reference_path = self._get_output_paths(filename, artifacts_dir)
Expand All @@ -4875,8 +4884,8 @@ def save_as_json(
out = new_doc.export_to_dict(
coord_precision=coord_precision, confid_precision=confid_precision
)
with open(filename, "w", encoding="utf-8") as fw:
json.dump(out, fw, indent=indent)
with open(filename, "wb") as fw:
fw.write(orjson.dumps(out, option=orjson.OPT_INDENT_2 if indent else None))

@classmethod
def load_from_json(cls, filename: Union[str, Path]) -> "DoclingDocument":
Expand Down
12 changes: 7 additions & 5 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,25 +31,27 @@ classifiers = [
"Topic :: Software Development :: Libraries :: Python Modules",
"Typing :: Typed",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
]
requires-python = '>=3.9,<4.0'
requires-python = '>=3.10,<4.0'
dependencies = [
'jsonschema (>=4.16.0,<5.0.0)',
'pydantic (>=2.6.0,<3.0.0,!=2.10.0,!=2.10.1,!=2.10.2)',
'jsonref (>=1.1.0,<2.0.0)',
'tabulate (>=0.9.0,<0.10.0)',
'pandas (>=2.1.4,<3.0.0)',
'tabulate (>=0.9.0,<0.11.0)',
'pandas (>=2.1.4,<4.0.0)',
'pillow (>=10.0.0,<13.0.0)',
'pyyaml (>=5.1,<7.0.0)',
'typing-extensions (>=4.12.2,<5.0.0)',
'typer (>=0.12.5,<0.20.0)',
'typer (>=0.12.5,<0.25.0)',
'latex2mathml (>=3.77.0,<4.0.0)',
"defusedxml (>=0.7.1, <0.8.0)",
"pydantic-settings>=2.14.0",
"orjson>=3.11.5,<4.0.0",
]

[project.urls]
Expand Down
22 changes: 11 additions & 11 deletions test/data/doc/constructed_doc.embedded.json.gt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -425,7 +425,7 @@
"orig": "item of leading list",
"text": "item of leading list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/1",
Expand Down Expand Up @@ -507,7 +507,7 @@
"orig": "list item 1",
"text": "list item 1",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/7",
Expand All @@ -521,7 +521,7 @@
"orig": "list item 2",
"text": "list item 2",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/8",
Expand All @@ -539,7 +539,7 @@
"orig": "list item 3",
"text": "list item 3",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/9",
Expand Down Expand Up @@ -613,7 +613,7 @@
"orig": "list item 4",
"text": "list item 4",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/14",
Expand Down Expand Up @@ -663,7 +663,7 @@
"orig": "item 1 of list",
"text": "item 1 of list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/18",
Expand Down Expand Up @@ -705,7 +705,7 @@
"orig": "item 1 of neighboring list",
"text": "item 1 of neighboring list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/21",
Expand All @@ -723,7 +723,7 @@
"orig": "item 2 of neighboring list",
"text": "item 2 of neighboring list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/22",
Expand All @@ -737,7 +737,7 @@
"orig": "item 1 of sub list",
"text": "item 1 of sub list",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/23",
Expand All @@ -755,7 +755,7 @@
"orig": "",
"text": "",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/24",
Expand Down Expand Up @@ -813,7 +813,7 @@
"orig": "",
"text": "",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/28",
Expand Down
22 changes: 11 additions & 11 deletions test/data/doc/constructed_doc.referenced.json.gt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -425,7 +425,7 @@
"orig": "item of leading list",
"text": "item of leading list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/1",
Expand Down Expand Up @@ -507,7 +507,7 @@
"orig": "list item 1",
"text": "list item 1",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/7",
Expand All @@ -521,7 +521,7 @@
"orig": "list item 2",
"text": "list item 2",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/8",
Expand All @@ -539,7 +539,7 @@
"orig": "list item 3",
"text": "list item 3",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/9",
Expand Down Expand Up @@ -613,7 +613,7 @@
"orig": "list item 4",
"text": "list item 4",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/14",
Expand Down Expand Up @@ -663,7 +663,7 @@
"orig": "item 1 of list",
"text": "item 1 of list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/18",
Expand Down Expand Up @@ -705,7 +705,7 @@
"orig": "item 1 of neighboring list",
"text": "item 1 of neighboring list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/21",
Expand All @@ -723,7 +723,7 @@
"orig": "item 2 of neighboring list",
"text": "item 2 of neighboring list",
"enumerated": false,
"marker": "\u25a0"
"marker": "■"
},
{
"self_ref": "#/texts/22",
Expand All @@ -737,7 +737,7 @@
"orig": "item 1 of sub list",
"text": "item 1 of sub list",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/23",
Expand All @@ -755,7 +755,7 @@
"orig": "",
"text": "",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/24",
Expand Down Expand Up @@ -813,7 +813,7 @@
"orig": "",
"text": "",
"enumerated": false,
"marker": "\u25a1"
"marker": "□"
},
{
"self_ref": "#/texts/28",
Expand Down
Loading
Loading