STAGS

unstructured

91 versions indexed · latest 0.27.37 on Nov 6, 2026

Unstructured-IO/unstructured ↗

202656

0.27.37 patch ZH

fix(lang): keep the languages a caller passes on short ASCII text · fix(pdf): extract vector-heavy PDFs with the fast strategy instead of returning nothing

0.27.36 patch ZH

chore: start 0.27.36-dev after 0.27.35 release · fix(xml): keep text that runs through child elements · fix(pptx): filter off-slide shapes by how much of the box is visible

0.27.35 patch ZH

chore: replace per-PR changelog edits with generated release notes · fix(utils): compare bounding boxes for elements with no page number · fix(chunking): measure combine thresholds in tokens when max_tokens is set

0.27.34 patch ZH

perf: Free decode buffers sooner when restoring original elements · perf: Free image buffers sooner during figure extraction · fix: honor encoding= in partition_json and partition_ndjson

0.27.33 patch ZH

fix(chunking): don't repeat a very large split element in every chunk · fix(deps): bump certifi to 2026.10.19

0.27.32 patch ZH

fix: label numbered headings without making them list items, and skip section-break paragraphs · fix(partition): read spooled uploads in place instead of copying them

0.27.30 patch ZH

fix(email): keep non-ASCII sender and recipient names readable

0.27.29 patch ZH

fix(xlsx): read .xls files whose Workbook stream ends in padding

0.27.28 patch ZH

feat: opt-in langdetect-rs backend for partition language detection · fix(html): keep text inside unrecognized elements · fix(html): keep table captions in Table text and text_as_html

0.27.27 patch ZH

fix(json): preserve rehydrated element identity · fix: keep overlap category names from element 100 on · fix: normalize None text to empty string in Text elements

0.27.25 patch ZH

fix(pptx): no page break before the first slide when starting_page_number > 1 · fix(chunking): reject a negative overlap instead of corrupting text · feat(image): partition WEBP images like PNG and JPEG

0.27.22 patch ZH

This release rolls up all changes since 0.27.16.

0.27.16 patch ZH

This release rolls up all changes since 0.27.10; versions 0.27.11–0.27.15 were not published to PyPI individually.

0.27.10 patch ZH

fix(html): extract definition lists instead of discarding them

0.27.9 patch ZH

fix(chunking): retain table rowspans across cell splits

0.27.8 patch ZH

fix: partition multi-section DOCX files in linear time · fix: ignore processing instructions in HTML partitioning · ci: remove release version alert · fix: tolerate non-UTF-8 soffice output in doc/ppt conversion

0.27.6 patch ZH

Fix DOCX text_as_html duplicating merged-cell text instead of colspan/rowspan

0.27.5 patch ZH

chore(deps): bump claude-code-action to v1 · Added Sign up link for Transform and removed pricing · fix: stop treating every hyphen as a bullet delimiter in text partitioning

0.27.1 patch ZH

fix: support core metadata 2.5 publishing

0.27.0 minor ZH

test: stop GLOBAL_WORKING_DIR tests from disturbing other xdist workers · chore: restore telemetry by default · fix(security): bound quadratic array-stream decoding in is_pdf_too_complex (SEC-146)

0.25.2 patch ZH

Terminology update: Platform -> Pipelines in README · perf(html): use indexed parent lookup · feat: add lazy chunking entry points

0.25.0 minor ZH

Partition arbitrary JSON and NDJSON: partition_json() and partition_ndjson() now handle any valid JSON/NDJSON payload, not just serialized Unstructured output.

0.24.1 patch ZH

fix: sanitize v2 HTML output to prevent stored XSS (GHSA-v5mq-3xhg-98m9)

0.24.0 minor ZH

feat: derive category_depth from heading level in the v2 (ontology) HTML parser · fix(ci): stabilize partition benchmark with a rolling-median baseline

0.23.1 patch ZH

feat: extract filled AcroForm field text in PDF partitioning

0.23.0 minor ZH

fix: stop decimating embedded text on dense PDF pages · fix: keep extracted text aligned with rotated PDF page images in hi_res · feat: add enrichment origins metadata field

0.22.32 patch ZH

fix(hi_res): recover text inside PDF figure overlays

0.22.31 patch ZH

fix: rename isolate_tables chunking option to isolate_table

0.22.30 patch ZH

feat: add option for table chunking

0.22.29 patch ZH

fix: handle text too long for spacy issue

0.22.28 patch ZH

fix: chunking dropping table content

0.22.27 patch ZH

fix: ndjson file type detection

0.22.26 patch ZH

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

0.22.23 patch ZH

fix: first table chunk preserve col/row span

0.22.22 patch ZH

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…

0.22.21 patch ZH

feat: add option to skip table chunking

0.22.20 patch ZH

Fix fixtures update CI to regenerate markdown · fix(deps): upgrade vulnerable transitive dependencies [security][bot] · feat: add GHA workflow to build opencv wheels without ffmpeg

opencv-4.12.0.88 release ZH

OpenCV Python contrib-headless wheels built from source with WITH_FFMPEG=OFF.

0.22.18 patch ZH

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

0.22.16 patch ZH

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 ($$ ...

0.22.12 patch ZH

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

0.22.10 patch ZH

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

0.22.6 patch ZH

fix(deps): Update security updates [SECURITY][bot] · fix: Self-contained script for version extraction in release CI

0.22.4 patch ZH

feat: add create_file_from_elements() to re-create document files from elements · Bump dependencies · fix: avoid O(N²) re-scanning in patch_current_chars_with_render_mode · add check if libmagic fails

0.21.5 patch ZH

feat: custom fallback for language detection · Add Github action for time regressions · fix: relax lower bound for pdfminer.six

0.21.1 patch ZH
0.21.0 minor ZH

Replace NLTK with spaCy to remediate CVE-2025-14009: NLTK's downloader uses zipfile.extractall() without path validation, enabling RCE via malicious packages (CVSS 10.0, no patch available).

0.20.8 patch ZH

fix: set max decompressed size for elements JSON · fix: update depdencies

0.20.6 patch ZH

Automate pypi publishing · fix: remove duplicate characters caused by fake bold rendering in PDFs · Improve fast partition cold start · fix: gracefully handle invalide html string during chunking

0.20.1 patch ZH

Add Python 3.11 and 3.13 support · Use bigger runner to publish images

0.19.3 patch ZH

feat: add group_elements_by_parent_id utility function · Preserve newlines in Table and TableChunk elements during PDF partitioning · Fix: make pdf image dpi consistent · chore: bump dependencies for 0.18.34

0.18.32 patch ZH

feat: put pdfium call behind a threadlock

0.18.31 patch ZH

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

0.18.28 patch ZH

Optimize clean_extra_whitespace_with_index_run (codeflash) · Optimize recursive_xy_cut_swapped (codeflash) · Optimize DocxPartitioner.parse_category_depth_by_style_name (codeflash)

0.18.27 patch ZH

Comment no-ops in zoom_image (codeflash) · Fix an issue where elements with partially filled extracted text are marked as extracted

0.18.26 patch ZH

Pin deltalake<1.3.0 to fix ARM64 Docker builds (1.3.0 missing Linux ARM64 wheels)

202533

0.18.24 patch ZH

Optimize OCRAgentTesseract.extract_word_from_hocr (codeflash)

0.18.22 patch ZH

fix(deps): Bump fonttools to address cve

0.18.21 patch ZH

Update save_elements unit test to check crop box padding behavior

0.18.20 patch ZH

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

0.18.18 patch ZH

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…

0.18.15 patch ZH

Setup Codeflash Github Actions to optimize all future code · fix: update deps to resolve cve · ⚡️ Speed up function group_broken_paragraphs by 30% · ⚡️ Speed up method ElementHtml.get_children_html by 234%

0.18.14 patch ZH

Speed up function sentence_count by 59% (codeflash) · Speed up function check_for_nltk_package by 111% (codeflash) · Speed up function under_non_alpha_ratio by 76% (codeflash)

0.18.13 patch ZH

Parse a wider variety of date formats in email headers The partition_email function is now more robust to non-standard date formats, including ISO-8601 dates with 'Z' suffixes.

0.18.12 patch ZH

Prevent large file content in encoding exceptions Replace UnicodeDecodeError with UnprocessableEntityError in encoding detection to avoid storing entire file content in exception objects, which can cause issues in…

0.18.11 patch ZH

add '|' as a delimiter in csv files · feat: map tags by type + add coverage · chore: switch to charset normalizer · bump version and release

0.18.10 patch ZH

Add OCR_AGENT_CACHE_SIZE environment variable Added configurable cache size for OCR agents to control memory usage.

0.18.9 patch ZH

Convert elements to markdown for output Added function to convert elements to markdown format for easy viewing.

0.18.7 patch ZH

Add language detection for PDFs Add document and element level language detection to PDFs.

0.18.6 patch ZH

Improved epub partition errors EPUB partition will now produce new type of error on unprocessable files.

0.18.4 patch ZH

fix(partition, csv): increase csv field limit

0.18.3 patch ZH

chore: bump pillow to address a CVE

0.18.2 patch ZH

fix [NEX-49] : Fix TypeError for empty HTML content · fix: add try/except wrap over row.cells to failproof tc grid_offset · fix: xml processing not escaped · fix: update md to reads umlauts on non-utf-8 files

0.18.1 patch ZH

Add DocumentData element type This is helpful in scenarios where there is large data that does not make sense to represent across each element in the document.

0.17.2 patch ZH

Add image_url of images in html partitioner tags with non-data content include a new image_url metadata field with the content of the src attribute.

0.17.0 minor ZH

feat: include images when partitioning html · fix: pass extract image args to all partitioners · feat: allow passing down of ocr agent and table agent · Feat/remove reference of PageLayout.elements

0.16.25 patch ZH

Fixes filetype detection for jsons passed as byte streams - Now it prioritizes magic mimetype prediction over file extension when detecting filetypes

0.16.24 patch ZH

Support dynamic partitioner file type registration. Use create_file_type to create new file type that can be handled

0.16.23 patch ZH

Fixes detect_filetype when SpooledTemporaryFile is passed. Previously some random name would get assigned to the file and the function raised error.

0.16.22 patch ZH

Fix open CVES in and bump dependencies

0.16.21 patch ZH

Use password to load PDF with all modes

0.16.20 patch ZH

Fix a security issue where rst and org files could read files in the local filesystem. Certain filetypes could 'include' or 'import' local files into their content, allowing partitioning of arbitrary files from the…

0.16.19 patch ZH

Fix a bug where table extraction is skipped when it shouldn't. Pages with just one table as its content or starts with a table misses table extraction. The routing logic is now fixed.

0.16.17 patch ZH

Refactoring the VoyageAI integration to use voyageai package directly, allowing extra features.

0.16.16 patch ZH

Vectorize layout (inferred, extracted, and OCR) data structure Using np.ndarray to store a group of layout elements or text regions instead of using a list of objects.

0.16.15 patch ZH

Update unstructured-inference to 0.8.6 in requirements which removed layoutparser dependency libs · Update pdfminer-six to 20240706

0.16.14 patch ZH

Fix an issue with multiple values for infer_table_structure when paritioning email with image attachements the kwarg calls into partition to partition the image already contains infer_table_structure.

0.16.13 patch ZH

Add character-level filtering for tesseract output. It is controllable via TESSERACT_CHARACTER_CONFIDENCE_THRESHOLD environment variable.

0.16.12 patch ZH

Prepare auto-partitioning for pluggable partitioners. Move toward a uniform partitioner call signature so a custom or override partitioner can be registered without code changes. · Add NDJSON file type support.

20242

0.16.11 patch ZH

Enhance quote standardization tests with additional Unicode scenarios

0.16.10 patch ZH

Fix original file doctype detection from cct converted file paths for metrics calculation.