docling-project / docling-project/docling

`HybridChunker` not available with just `docling` as dependency

Open
#994 4 comments 1 reaction 0 assignees View on GitHub
bug
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug

Contrary to [the docs](https://ds4sd.github.io/docling/concepts/chunking/#hybrid-chunker), `HybridChunker` is not available with the `docling` dependency.

> If you are using the `docling` package, you can import as follows:
>
>```
>from docling.chunking import HybridChunker
>```

### Steps to reproduce

Add `docling` as dependency.

```text
from docling.chunking import HybridChunker
.venv/lib/python3.12/site-packages/docling/chunking/__init__.py:12: in
from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
.venv/lib/python3.12/site-packages/docling_core/transforms/chunker/hybrid_chunker.py:18: in
raise RuntimeError(
E RuntimeError: Module requires 'chunking' extra; to install, run: `pip install 'docling-core[chunking]'`
```

### Docling version

```text
Docling version: 2.22.0
Docling Core version: 2.18.1
Docling IBM Models version: 3.3.2
Docling Parse version: 3.3.1
Python: cpython-312 (3.12.6)
Platform: macOS-15.3-arm64-arm-64bit
```

### Python version

This section is unnecessary: see previous listing.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.