mirror of
https://github.com/deepset-ai/haystack.git
synced 2026-01-04 19:17:26 +00:00
2c2c7c9f56
* Add first pass at PPTXToDocument converter * Add test and update code * Add doc string * Update docstrings * Add release notes * remove unused imports, add to api docs, update pyproject.toml * Add a new test * Add dep so tests can run
6 lines
219 B
YAML
6 lines
219 B
YAML
---
|
|
features:
|
|
- |
|
|
Add a PPTX to Document converter using the python-pptx library. Extracts all text from each slide. Each slide is separated with a page break "\f"
|
|
so a Document Splitter could split by slide.
|