IBM Release notes and new features

Docling 2.149.0

Docling 2.149.0 adds opt-in embedded PDF image extraction, support for mlx-audio, and a MiniCPM-OCR preset. The CLI has also been refactored for improved usability.

Docling 2.148.0

Docling 2.148.0 adds support for surya v2.5 and introduces an iCalendar backend. The release also includes various fixes for PDF, JATS, ODF, and DOCX document processing.

Docling 2.147.0

Docling 2.147.0 includes fixes for LaTeX link handling, boxnote image captioning, and VLM table processing.

Docling 2.146.0

Feature vlm: Add Unlimited-OCR 2 preset and layout parser (bdb1d20) Add LightOnOCR-3 presets and grounded output parsing (4b382ee) vlm: Add guarded Nemotron 3.5 multi-pass parsing (84599f9) Fix service-client: Keep the presigned rejection when the InBody fallback fails (421b3ba) iwork: Read decimal128 cells without context rounding (2fea2c9) md: Stop the...

Docling 2.145.0

Docling 2.145.0 adds page orientation detection for RapidOCR and includes various fixes for JATS, HTML, and XLSX document parsing.

Docling 2.144.0

Docling 2.144.0 includes new features for PDF heading style signals and OCR replacement for broken text layers, along with various bug fixes for VLM and ASR components.

Docling 2.143.1

Docling 2.143.1 improves table parsing by including OCR word cells in table tokens and optimizing spatial index performance for empty inputs. It also includes fixes for PPTX chart table cell counting and Tesseract OCR resolution.

Docling 2.143.0

Docling 2.143.0 adds support for mixed-format ZIP inputs, ASR presets, and various fixes for document format extraction.

Docling 2.142.1

Docling 2.142.1 includes security and stability fixes for document parsing and decompression.

Docling 2.142.0

Docling 2.142.0 includes various fixes and improvements, such as better parsing for LaTeX, extraction of ODT page headers and footers, and improved handling of VLM section heading depths.

Docling 2.141.0

Feature Add nvidia/Nemotron-3.5-Parse as supported VLM model (2d1d814) cli: Generic engine options for docling convert (f57160e) service: Allow artifact downloads from trusted private origins (8df5b6e) forms: Map form fields with a geometric solver when AcroForm widgets are available (2f13b3d) asciidoc: Keep comments in the notes content layer (ba458a2) Fix...

Docling 2.140.0

Feature asr: Prefetch the native Distil-Whisper presets with docling-tools (483cf13) asciidoc: Parse bold, italic and monospace in paragraphs (fd24b9e) asr: Transcribe with a remote OpenAI-compatible server (b246052) Fix odf: Move hidden ODT sections to the invisible content layer (f690a52) reading-order: Bound page-separator candidate work and honor...

Docling 2.139.0

Feature Expose max_concurrent_results on ThreadedDoclingParseBackendOptions (ce5621b) Expose per-page confidence breakdown in ConfidenceScores (5bdabb9) progress: Add conversion progress bars and an event callback (fdb6321) iwork: Read pictures in Numbers table cells (dd477a9) Allow docling-tools to download whisper artifacts and for docling to run ASR from...

Docling 2.138.0

Feature iwork: Read pictures placed on a Numbers sheet (88fbc05) Fix docx: Emit textboxes in table cells once inside their cell (6bc5770) jats: Parse ordered lists and list item labels (ad2e0e1) mlx: Pass the sampling temperature as temperature to mlx-vlm (fb0818e) odf: Move hidden ODP slides to the invisible content layer (807f6df) pptx: Move hidden shapes...

Docling

Feature heading_hierarchy: Recognize Division/Subdivision heading markers in hierarchy inference (8a6155b) mlx: Add repetition penalty options (dd7c035) Fix ocr: Do not OCR programmatic text because a vector shape crosses it (c6ef3c4) latex: Resolve \input and \includegraphics for str sources (b2a59b9) latex: Keep CMYK JPEG figures (9943158) pptx: Move...

• Docling 2.136.0
• Docling 2.137.0

Docling 2.135.0

Feature iwork: Render Numbers chart images and read iWork '09 chart kinds (f95402a) md: Preserve inline formatting in Markdown table cells (1a264db) Fix vlm: Map DOTS Markdown emphasis to styled spans (0d604da) html: Keep the table or image of a list item without text (97307ec) pdf: Keep failed-page sizes on the conversion, not on the pipeline (a183c15)...

Docling 2.134.0

Feature iwork: Add Apple Numbers (.numbers) support (8d7cc9f) vlm: Expose logprobs on the streaming API path (3073a27) Fix docx: Preserve text from dangling fragment hyperlinks (d15cf10) html: Keep text placed directly inside a figure (caba660) docx: Keep hyperlink runs nested in a wrapper (7833b32) docx: Add use_outline_level_for_headings option to backend...

Docling 2.133.0

Feature ocr: Allow configuring RapidOCR model size (a1c5ff2) Fix opendocument: Read the chart object's own title (4c109c2) code-formula: Keep the extracted text when a batch fails (a25aa1d) latex: Decode Windows-1252 sources and 8-bit TikZ dependencies (b5aa0ef) md: Keep the first-line indentation of code blocks (cc937ec) html: Keep dt/dd groups wrapped in...

Docling 2.132.0

Feature pdf, reading-order: Updating the reading-order algoirthm (42de1e2) Fix Preserve fidelity when mapping external VLM output (Chandra, dots, MinerU) (20ba847) csv: Validate first-line dialect before accepting a sniff (d6f0307) docx: Exclude ' ' from bold detection (bf836f2) image: Recognize .gif files as images (cd05bef) cli: Skip Excel and PowerPoint...

Docling 2.131.0

Feature iwork: Parse Keynote charts as classified pictures with data (9da6935) iwork: Add Apple Keynote (.key) support (87c6ea0) Fix pypdfium2: Build the page object index once to avoid quadratic scans (b93af46) pipeline: Skip enrichment after timeout (152f9ba) vlm: Report failed remote API calls as INFERENCE_ERROR instead of empty success (2b2fb85) mets...

Docling 2.130.0

Feature Add Mineru 2.5 Pro to the supported VLMs ( #4322 ) ( 9a2c3e7 ) Fix service client: Omit only unset arguments but keep values set equal to defaults ( #4349 ) ( 35c6af5 ) Remove double preset registration of chart extraction ( #4348 ) ( 878831c ) md: Honor backslash-escaped pipes in Markdown tables ( #4313 ) ( 52e52fd ) Fix the VLM end token...

Docling 2.129.0

Feature Refactor chart extraction with generic engine options ( #4246 ) ( 0e6c2ca ) Allow ambient credentials for S3 ( #4212 ) ( e689393 ) Fix More improvements for chandra ocr parsing ( #4277 ) ( a83926c ) asciidoc: Recognise a rowspan-only cell specifier ( #4290 ) ( 815f34a ) html: Default a zero colspan or rowspan to 1 in HTML tables ( #4287 ) ( 6cb036c...

Docling 2.128.0

Feature Add minimal AFP document support ( #4177 ) ( 1cdae27 ) Add nvidia/NVIDIA-Nemotron-Parse-2.0 as vlm model ( #4253 ) ( 01b5738 ) pdf: Refactor the docling-parse backend to remove pypdfium ( #4244 ) ( ca0ecd4 ) Fix asciidoc: Block titles, picture parenting, skipped headings, and list dedent ( #4171 ) ( 7fe1b3c ) image: Apply the EXIF orientation when...

Docling 2.127.0

Feature Addition of 'region' to S3Coordinates ( #4221 ) ( 5ea6490 ) mhtml: Add MHTML input backend ( #4184 ) ( 7e05ed6 ) Add RTF input support via LibreOffice ( be443e8 ) jats: Embed local figure images ( #4041 ) ( 3d33038 ) Canonicalize the OCR languages across all engines according to the BCP-47 standard ( #4075 ) ( 9a2d947 ) Fix html: Flag pivot-table...

Docling 2.126.0

Feature Add native pdf pipeline ( #3979 ) ( 1c96dd3 ) jats: Preserve external hyperlinks ( #4029 ) ( cf38d90 ) iwork: Complete the parsing of Apple Pages documents ( #4062 ) ( 554b10a ) Fix markdown: Preserve ordered list start numbers in conversion ( #4138 ) ( a4e9462 ) docx: Inherit heading numId through the style basedOn chain ( #3916 ) ( #3917 ) (...

Docling 2.125.0

Feature Introduce min-version check for VLM engines (fixes chandra-ocr-v2 MLX) ( #4150 ) ( 9876e73 ) Fix vlm: Handle tables labeled as forms by Chandra ( #4135 ) ( d6a6de4 ) html: Parse tables and captions inside tags ( #4050 ) ( 70eb711 ) ebcdic: Require record names to be unique ( #4126 ) ( a72a3c1 ) asciidoc: Preserve ordered lists and literal blocks (...

Docling 2.124.0

Feature cli: Add latex output format ( #4101 ) ( c4b0fc7 ) Add terminal task callback event ( #4095 ) ( d2283ad ) Fix service_client: Handle Retry-After HTTP-date with unknown timezone ( #3786 ) ( 3bba8da ) Silence transformers generation-config deprecation warning and add max_new_tokens CLI overrides ( #4115 ) ( 01fc722 ) Drop the UTF-8 BOM when decoding...

Docling 2.123.1

Fix vlm: Preserve spacing for Chandra br tags ( #4092 ) ( 3a2aca4 ) cli: Defer heavy imports so CLI works on lightweight installs ( #4100 ) ( 21aa5c9 ) csv: Drop the UTF-8 BOM instead of keeping it in the first cell ( #4098 ) ( 0865b9a )

Docling 2.123.0

Feature Default to threaded docling-parse across SDK, CLI, service, and extraction ( #3764 ) ( feb0f26 ) Fix Avoid pipeline option cache key collisions ( #4076 ) ( 4c28ee6 ) csv: Detect the dialect when a quoted field spans several lines ( #3985 ) ( 6b7dc94 ) Improvements (layout element shuffling and allow more strategies) in experimental two-stages...

Docling 2.122.0

Feature Add compact_tables to ConvertDocumentsOptions ( #4032 ) ( e1965bc ) iwork: Recover titles, headings and iWork '09 tables ( #4031 ) ( 9e73870 ) Fix pdf: Preserve a line-final hyphen that does not split a word ( #4043 ) ( #4052 ) ( 49579ee ) asciidoc: Stop a dedented list from crashing the backend ( #3826 ) ( 72fb46d ) docx: Keep node identity for...