docling-core
A python library to define and validate data types in Docling.
Decision gist · record as of 2026-08-14
Yes. Docling Core is actively maintained (release 8 days old), has no known vulnerabilities, uses a permissive MIT license, and offers low install friction. It is production-stable and well-suited for teams building document-centric AI applications. Install if you are working with the Docling framework or need a structured, validated document data model with built-in serialization and chunking.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; development setup requires the uv package.
- Low install friction; pure Python wheel with 13 runtime dependencies.
- Active maintenance with a release 8 days ago and commits through 2026-08-14.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for most projects.
last release 2026-08-06 (8 days) · last repo commit 2026-08-14 · 276 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 6,339,614 downloads/mo, #1,928 on PyPI
Alternatives
Verify before relying
pip install docling-core
from docling_core.types import DoclingDocument
from docling_core.transforms import serialize_document
# Create or load a DoclingDocument
doc = DoclingDocument(...)
markdown_output = serialize_document(doc, format='markdown')- Whether the 13 runtime dependencies (including pandas, pillow, pyyaml) are all required for basic usage or only for specific features.
- Performance characteristics and memory footprint when processing large document collections.
- Concrete examples of how the profiling API scales with collection size.
What it is and what it does
Docling Core is the foundational library for the Docling document processing framework. It defines DoclingDocument as a Pydantic model—a strongly-typed, validated data structure for representing structured documents—and provides a suite of APIs built around it. The library is designed to support generative AI workflows that need to ingest, transform, and analyze documents at scale.
The package centers on four main capabilities: the DoclingDocument model itself (with builders and exporters for formats like Markdown and HTML), a pluggable Serialization API for flexible output formats, a Chunking API for breaking documents into semantically meaningful pieces, and a Profiling API for extracting statistics and distributions from individual documents or collections. It depends on Pydantic for validation, Pillow for image handling, pandas for data operations, and several other utilities for LaTeX math, YAML, and XML processing.
Use it for
- Build a document ingestion pipeline that parses PDFs or scanned documents into a validated, queryable DoclingDocument structure for RAG systems.
- Export extracted document content to multiple formats (Markdown, HTML, JSON) for downstream processing or API consumption.
- Chunk large documents into semantically coherent segments for embedding and vector search in AI applications.
- Analyze document collections to extract structural metrics (page counts, table distributions, image density) for quality assurance or dataset profiling.
- Extend the serialization or chunking logic with custom implementations for domain-specific document processing requirements.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Docling Core is actively maintained (release 8 days old), has no known vulnerabilities, uses a permissive MIT license, and offers low install friction. It is production-stable and well-suited for teams building document-centric AI applications. Install if you are working with the Docling framework or need a structured, validated document data model with built-in serialization and chunking.
Install
docling-core on PyPI
Before you install
Low install friction; pure Python wheel with 13 runtime dependencies. Active maintenance with a release 8 days ago and commits through 2026-08-14. Supports Python 3.10 through 3.14.
Requires Python 3.10 or later; development setup requires the uv package.
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions—suitable for most projects.
Quickstart
pip install docling-core
from docling_core.types import DoclingDocument
from docling_core.transforms import serialize_document
# Create or load a DoclingDocument
doc = DoclingDocument(...)
markdown_output = serialize_document(doc, format='markdown')Verify before relying
- Whether the 13 runtime dependencies (including pandas, pillow, pyyaml) are all required for basic usage or only for specific features.
- Performance characteristics and memory footprint when processing large document collections.
- Concrete examples of how the profiling API scales with collection size.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 13 packagesjsonschemapydanticjsonreftabulatepandaspillowpyyamltyping-extensionstyperlatex2mathmldefusedxmlpydantic-settingsdoclang |
| Maintenance | Actively maintained 8 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 6,339,614 / month, #1,928 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: Science/ResearchNatural Language :: EnglishOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: DatabaseTopic :: Scientific/Engineering :: Information AnalysisTopic :: Software Development :: Libraries :: Python ModulesTyping :: Typed |
Evidence: docling_core-2.91.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “document data model pydantic”
- docling-coreDocling Core defines the foundational DoclingDocument data model and…
- vlmrun-hubProvides a catalog of pre-defined Pydantic schemas for extracting…
- griffe-pydanticExtends Griffe to automatically extract and document Pydantic model…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also docling · docling-slim · langchain-docling · docling-ibm-models · docling-parse · landingai-ade · chonkie-core · langchain-unstructured · pydantic-xml · unstructured