Data and AI releases

548 this month · 176 companies

unstructured 0.18.21

UpdateNot yet verified

0.18.21 Enhancement - Update save_elements unit test to check crop box padding behavior Features Fixes - Update unstructured-inference to 1.1.2 to address CVEs

Read on github.com

Also shipped Nov 24, 2025Unstructured in November 2025 →

WAF Release - 2025-11-24

This week highlights enhancements to detection signatures improving coverage for vulnerabilities in FortiWeb, linked to CVE-2025-64446, alongside new detection logic expanding protection against PHP Wrapper Injection techniques. Key Findings This vulnerability enables an unauthenticated attacker to bypass access controls by abusing the CGIINFO header.

Beta
Source ↗

Debug Guides and Surveys with the Amp Chrome Extension

Description: • Quick access to verify SDK Setup • Troubleshoot guides and surveys or Preview one directly • View user properties • View all forwarded events or send a test event to trigger a g/s Why: Knowing and running JS console commands is a hurdle for customers who need visibility into G/S setup.

Preview
Source ↗

We now support Predicted Outputs for faster generation when large portions of the output are known in advance

We now support Predicted Outputs for faster generation when large portions of the output are known in advance. Provide a draft of the expected response via the prediction field, and the model will efficiently reuse unchanged tokens while regenerating only those that differ. Ideal for code editing, document revisions, and template-based responses.

Update
Source ↗

Nova-3 Model Update

🎯 Nova-3 supports 10 new languages We've added support for 10 new languages with non-English monolingual Nova-3 models. This continues our effort to significantly expand Nova-3 language support beyond English.

Update
Source ↗

More from unstructuredEvery unstructured release →

unstructured 0.18.20

0.18.20 Enhancement - Improve the VoyageAI integration - Add voyage-context-3 support - Flag extracted elements as such in the metadata for downstream use Features Fixes

Update
Source ↗

unstructured 0.18.18

0.18.18 Fixes - Prevent path traversal in email MSG attachment filenames Fixed a security vulnerability (GHSA-gm8q-m8mv-jj5m) where malicious attachment filenames containing path traversal sequences could write files outside the intended directory.

Update
Source ↗

unstructured 0.18.24

Enhancement - Optimize OCRAgentTesseract.extract_word_from_hocr (codeflash) Fixes - Security update: Bumped dependencies to address security vulnerabilities

Update
Source ↗

unstructured 0.18.26

0.18.26 Fixes - Pin deltalake<1.3.0 to fix ARM64 Docker builds (1.3.0 missing Linux ARM64 wheels) 0.18.25 Fixes - Security update: Removed pdfminer.six version constraint and bumped pdfminer.six and urllib3 to address high severity CVEs

Update
Source ↗

unstructured 0.18.27

0.18.27 Fixes - Comment no-ops in zoom_image (codeflash) - Fix an issue where elements with partially filled extracted text are marked as extracted Enhancement - Optimize sentence_count (codeflash) - Optimize _PartitionerLoader._load_partitioner (codeflash) - Optimize detect_languages (codeflash) - Optimize contains_verb (codeflash) - Optimize...

Update
Source ↗

unstructured 0.18.28

Enhancement - Optimize clean_extra_whitespace_with_index_run (codeflash) - Optimize recursive_xy_cut_swapped (codeflash) - Optimize _DocxPartitioner._parse_category_depth_by_style_name (codeflash) - Optimize VertexAIEmbeddingEncoder._add_embeddings_to_elements (codeflash) - Optimize ngrams (codeflash) - Optimize stage_for_datasaur (codeflash)

Update
Source ↗

unstructured 0.18.31

- Feat: patch pdfminer and use rendermode to detect invisible text - fix: add EN DASH to UNICODE_BULLETS for clean_bullets - fix: fix version number - enhancement: render pdfs with pdfium - feat: consider rotated text as low fidelityfeat: consider rotated text - fix: address jaraco CVE - fix: hange default for languages parameter from ["auto"] to None - ⚡️...

Update
Source ↗