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...
Also shipped Sep 22, 2026IBM in September 2026 →
Shopify connector (Beta)
The Shopify connector is now available in Lakeflow Connect in Beta . Workspace admins can control access to this feature from the Previews page. The connector ingests e-commerce data such as products, orders, customers, inventory, fulfillments, and discounts from Shopify into Databricks. Authentication uses the Shopify OAuth client credentials grant.
Lakebase backup schedule API (Beta)
You can now manage Lakebase backup schedules programmatically. The snapshot schedule API lets you read and set a root branch's automated snapshot cadences (daily, weekly, or monthly) and how long each cadence's snapshots are retained. This API is in Beta and available to all Lakebase workspaces. See Create a backup schedule .
OpenAI GPT-6 Sol and GPT-6 Luna are now generally available on Amazon Bedrock
Today, AWS announces the general availability of GPT-6 Sol and GPT-6 Luna from OpenAI on Amazon Bedrock. Expanding the GPT-6 family alongside Astra, these two models give teams more ways to balance intelligence, speed, and cost across every workload. Sol is the daily model for recurring complex tasks and software development.
Claude Opus 5.5 launches with a 1M token context window and 128k output
Anthropic released Claude Opus 5.5 for long-running agentic coding and knowledge work, with a default 1M token context, 128k max output and always-on adaptive thinking. It costs $4 / $20 per MTok, below Claude Opus 5, and is on the Claude API, Bedrock, Google Cloud and Microsoft Foundry.
Fast mode research preview available for Claude Opus 5.5 on the Claude API
Fast mode, in research preview, can now be used with Claude Opus 5.5 on the Claude API.
Claude API beta lets tools be defined inside mid-conversation system messages
With the inline-tools-2026-09-15 beta header, a tool_addition block can carry a full tool definition, so agents can add tools, change schemas or upgrade server tools mid-conversation without invalidating the prompt cache. The same header covers adding and removing tools by reference.
More from DoclingEvery Docling release →
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 2.131.0
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 2.127.0
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 2.132.0
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 2.133.0
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 2.134.0
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 2.135.0
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)...