Install & Compatibility
Where this runs
tested against v? · pip install
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
muslpy 3.10–3.95 runs
build_error
Code
Verified usage
Verified import paths — ran on the pinned version, not inferred.
DoclingLoader
✓ from langchain_docling.loader import DoclingLoader
✗ from langchain_docling import DoclingLoader
In v2.0.0 the canonical import path is from the loader submodule; direct import from package root may not work.
DoclingChunker
✓ from langchain_docling.chunking import DoclingChunker
✗ from langchain_docling.chunker import DoclingChunker
Submodule is named 'chunking' (with 'ing'), not 'chunker'. This is a common mistake.
DoclingDocumentConverter
✓ from langchain_docling.converter import DoclingDocumentConverter
Load a PDF document with DoclingLoader and split into chunks using DoclingChunker.
from langchain_docling.loader import DoclingLoader
from langchain_docling.chunking import DoclingChunker
from langchain_docling.converter import DoclingDocumentConverter
from langchain_core.documents import Document
# Initialize converter with desired pipeline options
converter = DoclingDocumentConverter()
# Example: loading a document from a file path
loader = DoclingLoader(file_path="example.pdf", converter=converter)
docs = loader.load()
print(docs[0].page_content[:200])
# Example: chunking documents
chunker = DoclingChunker(chunk_size=512, chunk_overlap=50)
chunks = chunker.split_documents(docs)
print(f"Number of chunks: {len(chunks)}")
Errors
Common errors & fixes
ImportError: cannot import name 'DoclingLoader' from 'langchain_docling'
Symbol is not exposed at package root; must import from submodule.
fixUse 'from langchain_docling.loader import DoclingLoader'.
AttributeError: 'DoclingLoader' object has no attribute 'load'
DoclingLoader might have been instantiated incorrectly or version mismatch.
fixEnsure you are using the correct import path and version 2.0.0+. Call loader.load() after proper instantiation.
TypeError: DoclingLoader.__init__() got an unexpected keyword argument 'converter'
The 'converter' argument was renamed or removed in older versions (pre-2.0.0).
fixUpgrade to langchain-docling >=2.0.0 and pass converter as keyword argument.
ValueError: Document must have page_content to be chunked
Attempting to chunk a document that is not produced by Docling's converter.
fixEnsure documents are created by DoclingLoader or DoclingDocumentConverter.
Upgrade
Version history
2.0.0latest on PyPI · released Nov 17, 2025
Audit
Dependencies
langchain-corerequiredRequired for base classes (Document, BaseLoader, etc.).
doclingrequiredCore document conversion engine.