This release adds 5 notable features for engineering teams evaluating rollout.
Published 23d
RAG & Retrieval
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
ai
convert
document-parser
document-parsing
documents
docx
+9 more
html
markdown
pdf
pdf-converter
pdf-to-json
pdf-to-text
pptx
tables
xlsx
Summary
AI summaryUpdates Fix, Feature, and docx across a mixed release.
Full changelog
Feature
- Allow overriding same-font enforcement (#3737) (
0064a45) - Use PP-OCRv6 RapidOCR defaults (#3677) (
01235ce) - asr: Expose and forward native Whisper decoding options (#3717) (
4f37eee) - Add code language detection (#3721) (
648fcf1) - pdf: Infer heading levels from PDF bookmarks/ToC (#3688) (
9cbef42)
Fix
- html: Parse tables nested inside list items (#3508) (#3738) (
8c162bd) - Forward VLM convert runtime generation settings (#3322) (
1c03fd4) - tests: Correct XBRL source path to point to 'sources/' subdirectory (#3734) (
b77612c) - docx: Support Strict OOXML (.docx) files (#3729) (
528eb5b) - msword: Don't abort conversion on a malformed hyperlink address (#3744) (
c979c6a)
Documentation
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Beta — feedback welcome: [email protected]