Data and AI releases

548 this month · 176 companies

unstructured 0.22.21

UpdateNot yet verified

- feat: add option to skip table chunking

Read on github.com

Also shipped Apr 14, 2026Unstructured in April 2026 →

Grafana Advisor is now generally available-health checks for your Grafana instance to keep things running smoothly

Grafana Advisor is now generally available in Grafana v13.0. You can use Advisor to uncover issues affecting the health of your Grafana instances, such as: Data sources with a failing health check that will result in failed queries Outdated plugins, which might be insecure or lacking the latest fixes and features Misconfigured SSO settings Checks run once a...

GA
Source ↗

More from unstructuredEvery unstructured release →

unstructured 0.22.20

- Fix fixtures update CI to regenerate markdown - fix(deps): upgrade vulnerable transitive dependencies [security] - feat: add GHA workflow to build opencv wheels without ffmpeg - Enable vertical text detection for rotated images

Update
Source ↗

unstructured 0.22.22

Security - Replace PyPI opencv wheels with ffmpeg-free builds in Docker image: After uv sync, the Dockerfile now substitutes all PyPI opencv-python variants with a source-built opencv-contrib-python-headless wheel compiled with WITH_FFMPEG=OFF, eliminating 14 bundled ffmpeg CVEs.

Update
Source ↗

unstructured 0.22.18

- fix(chunking): preserve semantic headers in carried table chunks - feat: add page number support to v1 html partition

Update
Source ↗

unstructured 0.22.16

0.22.16 Enhancements - Formula markdown export (element_to_md / elements_to_md): New keyword-only formula_markdown_style ("auto", "display_math", "plain"; default "auto"). In "auto", display math ($ ... $) is used only when the text looks like notation (heuristic score) and contains no $/$ (avoids breaking Markdown and noisy OCR captions).

Update
Source ↗

unstructured 0.22.12

- mem: exclude unused spaCy pipeline components to reduce model memory - fix: pdfminer drops extractable text

Update
Source ↗

unstructured 0.22.10

- fix(chunking): preserve nested table structure in reconstruction - Replace lazyproperty with functools.cached_property - mem: reduce PaddleOCR rec_batch_num from 6 to 1 - fix: isolate Table elements in pre-chunks - feat(chunking): repeat table headers on continuation chunks

Update
Source ↗

unstructured 0.22.6

- Reject oversized PDF renders before bitmap allocation - feat(cli): add unstructured doctor diagnostics command - feat: Track the table extraction method

Update
Source ↗