docling-project / docling-project/docling

Google docs return empty texts

Open
#1,044 2 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug

Native Microsoft files are being extracted fine, but the same formats from Google docs are returning empty texts.

### Steps to reproduce

Create a Google Slide or Google Spreadsheet. Manually download the files. Load the files with DocLing. (Works fine with Google Document)

### Docling version

docling[chunking]===2.15.1
docling[document_converter]===2.15.1
docling_core[transforms]===2.15.1
langchain-docling===0.2.0

### Python version

3.11.4

```
chunker = HybridChunker(
tokenizer="sentence-transformers/all-MiniLM-L6-v2",
)

document_data = []
loader = DoclingLoader(
file_path=path,
export_type=ExportType.DOC_CHUNKS,
chunker=chunker,
)
chunks = loader.load() # empty chunks here
```

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.