Docling LangChain integration

A Docling integration for LangChain.

Installation

Simply install langchain-docling from your package manager, e.g. pip:

pip install langchain-docling

Development setup

To develop for Docling Core, you need Python >=3.9 <=3.13 and uv. You can then install from your local clone's root dir:

uv sync

Usage

Basic usage

Basic usage of DoclingLoader looks as follows:

from langchain_docling import DoclingLoader

FILE_PATH = ["https://arxiv.org/pdf/2408.09869"]  # Docling Technical Report

loader = DoclingLoader(file_path=FILE_PATH)
docs = loader.load()

Advanced usage

When initializing a DoclingLoader, you can use the following parameters:

• file_path: source as single str (URL or local file) or iterable thereof
• converter (optional): any specific Docling converter instance to use
• convert_kwargs (optional): any specific kwargs for conversion execution
• export_type (optional): export mode to use: ExportType.DOC_CHUNKS (default) or ExportType.MARKDOWN
• md_export_kwargs (optional): any specific Markdown export kwargs (for Markdown mode)
• chunker (optional): any specific Docling chunker instance to use (for doc-chunk mode)
• meta_extractor (optional): any specific metadata extractor to use

Neo4j ingestion

The package also provides a helper to ingest PDF files into a Neo4j vector store using Docling's hybrid chunking strategy:

from langchain_openai import OpenAIEmbeddings
from langchain_docling import ingest_pdfs_to_neo4j

vector_store = ingest_pdfs_to_neo4j(
    file_paths=["/path/to/report.pdf"],
    embedding=OpenAIEmbeddings(),
    url="bolt://localhost:7687",
    username="neo4j",
    password="secret",
)

Docs and examples

For more details and usage examples, check out this page.