docling-project/docling
1
0
Fork 0
mirror of https://github.com/docling-project/docling.git synced 2026-05-17 13:10:38 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
dev/complex_html_renderer_example
docling/CHANGELOG.md
T
github-actions[bot] 61c37a23a9 chore: bump version to 2.93.0 [skip ci]
2026-05-05 19:53:32 +00:00

170 KiB
Raw Permalink Blame History

v2.93.0 - 2026-05-05

Feature

  • vlm: Upgrade Granite Vision model to 4.1 for table + chart extraction (#3382) (24f2d14)

Fix

  • docx: Fix OMML equation handling and improve type safety (#3381) (e00735d)

v2.92.0 - 2026-04-29

Feature

  • Extend the kserve-triton OCR model to have multi-lingual support (#3368) (8b67fae)
  • docx: Add checkbox parsing support (#3349) (c455a65)
  • Introduce modular docling-slim package (#3285) (ed32c5e)
  • Add ResponseFormat.DOCLANG and parsing branch in VLM pipeline (#3350) (0f6f8d0)

Fix

  • pptx: Skip malformed picture shapes instead of aborting conversion (#3372) (7294248)
  • docx: OMML conversion failures for unsupported limit functions (#3359) (3df80e7)
  • Make VLLM model_impl configurable (#3358) (a6a37ca)

v2.91.0 - 2026-04-23

Feature

  • docx: Extract VML images with v:imagedata elements (#3343) (2ddaa3b)

Fix

v2.90.0 - 2026-04-17

Feature

  • Implement GraniteVisionTableStructureModel for VLM-based table extraction (#3323) (1569e42)

Fix

  • latex: Fully unwrap deeply nested formatting macros (#3249) (101233e)
  • docx: Handle inline formulas in list items (#3304) (c761512)
  • format: Add MD fallback for .txt files in _guess_from_content (#3311) (3bab6b4)
  • Strip soft hyphen when joining merged text elements (#3232) (8274892)
  • pptx: Handle NotImplementedError from shape.shape_type (#3309) (043ed2d)

Documentation

  • Fix nanonets_ocr2 runtime support matrix (#3317) (8ec14f2)

v2.89.0 - 2026-04-16

Feature

  • Explicit TikZ environment handling in LaTeX backend (#3187) (a15c16e)

Fix

  • ocr: Align RapidOCR english assets with 3.8 mobile models (#3291) (251c8b2)
  • docx: Isolate list state in table cells (#3294) (740c386)
  • pipeline: Prevent cache miss due to pipeline options mutation during chart extraction (#3300) (5b84911)

Documentation

  • Add indexed picture placeholder example to serialization notebook (#3293) (cd2e5b6)

Performance

  • markdown: Avoid eager string formatting in Markdown backend debug logs (#3301) (a64c378)

v2.88.0 - 2026-04-13

Feature

  • service: Establish client SDK for docling serve (#3264) (42157a3)

Fix

  • ocr: Support rapidocr 3.8 mobile model naming (#3277) (6b257ec)

Documentation

  • Add agent skill bundle for coding assistants (SKILL.md, pipelines, convert/evaluate) (#3174) (c23622f)

v2.87.0 - 2026-04-13

Feature

Fix

  • Transformers v5 compatibility for AUTOMODEL_CAUSALLM VLMs (#3276) (d431224)
  • vlm: Add explicit MLX support for OCR presets (#3272) (27d3cf4)
  • markdown: Normalize repeated leading dash markers (#3286) (a6aeddf)
  • docx: Preserve inline SDT references (#3280) (6cb1bc0)
  • pptx: Respect page_range during conversion (#3282) (e4fd937)
  • vlm: Support tool-calling API responses (#3271) (9c3ab93)
  • pdf: Extend ligature map with Dutch IJ and PUA glyph U+F0A0 (#3254) (ab5254d)

Documentation

  • Add AG2 multi-agent document analysis example (#3261) (1fed840)

v2.86.0 - 2026-04-10

Feature

  • Support for GraniteVision v4 (#3217) (fd83420)
  • Add signature/stamp html block to DC document (#3251) (9b4b67b)
  • vlm: Add PARTIAL_SUCCESS status for VLM pipeline pages (#3215) (6699642)

Fix

  • latex: Discard arguments of filtered spacing commands (#3245) (6180925)

Documentation

v2.85.0 - 2026-04-07

Feature

Fix

v2.84.0 - 2026-04-01

Feature

v2.83.0 - 2026-03-31

Feature

Fix

  • pdf: Propagate hyperlinks to DoclingDocument text items (#3131) (524edcc)
  • xlsx: Guard last-row bounds in Excel table scan (#3197) (85ac377)
  • Parse LaTeX macros in multicolumn/multirow table cells (#3204) (89c68f8)
  • Handle empty CSV file without crashing (#3196) (f283484)

Documentation

  • Add line-based chunker documentation and examples (#3210) (3a64f41)

v2.82.0 - 2026-03-25

Feature

  • Implementation of HTML backend with headless browser (#2969) (1c74a9b)

Fix

  • omml: Correct LaTeX output for fractions, math operators, and functions (#3122) (e36125b)
  • Manage PDFium backend resource lifecycles to avoid SIGSEGV/SIGTRAP crashes (#3180) (a0fc3c9)
  • docx: Split multiple OMML equations into separate formula items (#3123) (90d6dd4)
  • Let user params override engine defaults in API VLM engine (#3116) (fdf5e20)
  • vlm: Handle content_filter finish reason in API responses (#3051) (f0e3d1d)
  • cli: Avoid generating images for non-image exports (#3127) (5473e07)
  • Honor picture description batching and scale options (#3132) (9abf0fd)

Documentation

  • Fix Erroneous vLLM VLM pipeline engine option params causing empty/bad responses (#3167) (fffd445)

v2.81.0 - 2026-03-20

Feature

  • Route plain-text and Quarto/R Markdown files to the Markdown backend (#3161) (96d7c7e)

Fix

  • docx: Missing list items after numbered header (#2665) (#2678) (2f7c09e)
  • Avoid thread-unsafe close of pypdfium backend (#3160) (afb4bb6)
  • Handle external image relationships in MsWordDocumentBackend (#3114) (8ae0974)
  • Handle PermissionError for directory input on Windows CLI (#3149) (a39317a)
  • Avoid in-place mutation of pipeline options breaking cache key (#3115) (412af62)
  • Preserve torch_dtype in get_engine_config and add it to CodeFormulaV2 (#3117) (53a5f80)
  • Release image backend resources after frame extraction (#3134) (1e841eb)

v2.80.0 - 2026-03-14

Feature

v2.79.0 - 2026-03-12

Feature

  • Add fact metadata and linkbase relationships for XBRL (#3084) (7952efe)

Fix

  • Use OCR cells with TableFormer v2 (#3107) (93f6fee)
  • Add self-consistency check in the table-structure model (#3105) (2a0e11f)
  • Correct typos in log messages and add missing error log (#3097) (198d0af)
  • Don't force cast to float32 in API Kserve v2 inputs (#3101) (fef01f8)

v2.78.0 - 2026-03-10

Feature

Fix

  • html: Fix broken document tree and quadratic complexity in rich table cells (#3025) (80f75b8)
  • Loosen dependency for pandas3 (#3095) (5188180)
  • Add parse timeout to legacy LaTeX documents (#3019) (1192714)
  • msword: Skip GroupItem targets without comments attribute (#3080) (ee16285)

Documentation

  • Fix code in rag langchain chunker tokenizer (#2993) (d113e61)
  • Update code snippet to use modern pipeline options syntax (#3087) (95b759e)
  • Set HuggingFaceEndpoint task for Mixtral examples (#2945) (5d3ac38)

v2.77.0 - 2026-03-06

Feature

  • Track vlm_inference time for mlx_model pipeline (#3060) (38c4bb2)
  • Add configurable graph_optimization_level for ONNX Runtime engines (#3071) (cfc6636)

Fix

  • docx: Preserve URL fragments and query params in hyperlinks (#3050) (cd9dd10)
  • Detect Office Open XML formats from ZIP contents when filename has no extension (#3073) (56f06fe)
  • readingorder: Assign FURNITURE content_layer to footer/header in container groups (#3044) (f7cb304)
  • docx: Handle list items immediately after numbered headings (#3070) (56eb127)
  • rapidocr: ORT thread configuration for RapidOCR backend (#3062) (68336c2)

Documentation

  • Add examples and fix docstring bug in DocumentConverter (#3064) (653940e)
  • Add docstrings to PipelineOptions classes (#3065) (8b99085)

v2.76.0 - 2026-03-02

Feature

Fix

  • xlsx: Handle OneCellAnchor images in Excel backend (#3045) (859c302)
  • Normalize Unicode ligatures in PDF text extraction (#3057) (6198e69)
  • ocr: Update RapidOCR torch GPU config key (#3049) (477359b)
  • Convert PIL images to RGB before picture description (#3014) (90ce93d)
  • msword: Use outlineLvl for heading levels and clamp to minimum 1 (#2916) (a3d2b4b)

Documentation

v2.75.0 - 2026-02-24

Feature

  • Create a backend parser for XBRL instance reports (#3017) (334ba6e)
  • Unified model-family inference engines (including image-classification) and KServe v2 API support (#2979) (0353293)

Fix

  • Skip ASR segments when length is zero (#2998) (6b824f8)
  • docx: Guard against None hyperlink address in _get_paragraph_elements (#2367) (#3022) (236216e)

v2.74.0 - 2026-02-17

Feature

  • Introduce docling-parse v5 and deprecate old docling-parse backends (#2872) (bf417e6)

Fix

  • Security vulnerabilities with XML External Entity and related attacks (#3009) (576bada)
  • csv: Set default delimiter by default (#3005) (a1b0e3f)
  • Improved deserialization of engine_options (#3008) (dbba6ea)

v2.73.1 - 2026-02-13

Fix

  • asciidoc: Handle commas in image alt text (#2983) (86b6912)
  • Use timezone-aware datetime (#2947) (e2870f9)
  • Add failed pages to DoclingDocument for page break consistency (#2939) (1f91482)

v2.73.0 - 2026-02-11

Feature

  • Inference engines abstraction for object detection model family with HF Transformers and ONNX runtime (#2959) (14e474c)
  • Added support for parsing LaTeX (.tex) documents (#2890) (e6ccb8b)
  • Introduce pluggable VLM runtime system with preset-based configuration (#2919) (d4c8713)

Fix

  • Restore expected behavior for artifacts_path and accelerator_options in VLM engines (#2961) (9721321)
  • Allow offline chart extraction model artifacts (#2957) (ae4fdbb)

Documentation

v2.72.0 - 2026-02-03

Feature

Fix

  • backend: Improve Excel table bounds detection and flatten merged cells (#2778) (3110c43)
  • pptx: Handle picture shapes with external image references (#2914) (5e452a2)

Documentation

v2.71.0 - 2026-01-30

Feature

Fix

v2.70.0 - 2026-01-23

Feature

Fix

  • md: Handle pipe symbols that are not table markers (#2904) (86eaef5)
  • Remove direct vllm dependency (#2910) (7a1952a)
  • PPTX parsing: bullet points not grouped correctly under subheadings (#2663) (#2855) (999dbb2)

Documentation

  • Add comprehensive docstrings to PdfPipelineOptions (#2827) (ab91786)

v2.69.1 - 2026-01-21

Fix

  • Off-by-one error for page indexing in vlm_pipeline (#2902) (08f49e2)

v2.69.0 - 2026-01-20

Feature

Fix

Documentation

  • Correct broken link to supported formats (#2878) (16e88d5)

v2.68.0 - 2026-01-13

Feature

  • Support for DeepSeek-OCR in VLM pipeline (#2798) (19af03f)

Fix

  • logging: Include page numbers in preprocess error messages (#2858) (89bea24)
  • docx: Handle grouped pictures (#2861) (5c1f8f0)

Documentation

  • Fix Colab badge links and Weaviate typo in docs examples (#2871) (72851cc)
  • example: Fix update sample image path to be relative (#2864) (211c759)
  • Add Semantica integration (#2860) (bf80e32)

v2.67.0 - 2026-01-09

Feature

Fix

  • Lock new deps and update python 3.14 warnings (#2844) (d9295df)
  • Correct type hint for table_structure_options usage (#2823) (a0530a2)
  • Transformers models lazy-loaded (#2826) (3ef4525)
  • Font download by passing font_path to RapidOcr (#2822) (ffafe58)
  • cli: Add Layout and Table models to --show-external-plugins (#2832) (ed57089)

v2.66.0 - 2025-12-24

Feature

  • Add preset for using granite-docling via vllm and other apis (#2792) (241d19e)

Fix

  • docx: Handle tables with merged cells causing IndexError (#2813) (faff935)
  • markdown: Allow text before headers also in mixed markdown and html (#2801) (595115d)

Documentation

  • RTX: Guidelines for best performance on RTX GPUs (#2765) (be085c0)
  • Add docstrings to DocumentConverter #2748 (#2782) (cc5e3ce)
  • style: Fix link visibility in dark mode (#2804) (150fe90)

v2.65.0 - 2025-12-15

Feature

Fix

  • rapidocr: Use correct parameter name for rec_keys_path (#2762) (1d78418)
  • docx: Handle missing value in paragraph style name (#2761) (a97d950)

Documentation

  • Add Pydantic field documentation for PipelineOptions (#2771) (7c24b01)
  • gpu: Add benchmarks of standard pipeline with OCR (#2764) (d03439c)

v2.64.1 - 2025-12-09

Fix

  • Clear word/char cells when force_full_page_ocr is used (#2738) (1df0560)
  • Add missing font download in the rapidocr artifacts (#2735) (edbabfc)
  • Ensure proper image_scale for generated page images in VLM pipelines (#2728) (609069d)
  • html: Tackle paragraphs with block-level elements (#2720) (d007ba0)
  • html: Prevent hierarchy reset in rich table cells (#2716) (aebe25c)
  • docx: Parse integrals as n-ary objects without chr element (#2712) (c97715f)

v2.64.0 - 2025-12-02

Feature

  • experimental: Add experimental TableCropsLayoutModel (#2669) (1344362)
  • Factory and plugin-capability for Layout and Table models (#2637) (ad97e52)

Fix

  • InputFormat.IMAGE must have correct pipeline (#2707) (6ef4ffd)
  • Do not consider singleton cells in xlsx as TableItems but rather TextItems (#2589) (54cd6d7)
  • docx: Missing list items after numbered header (#2665) (e580554)

Documentation

  • Example on how to apply external OCR as post processing (#2517) (fa21128)
  • More GPU results and improvements in the example docs (#2674) (b75c646)
  • Fix typo on jobkit page (#2671) (146b4f0)

v2.63.0 - 2025-11-20

Feature

Fix

  • Respect document_timeout in new threaded StandardPdfPipeline (#2653) (2087c6b)
  • In DocumentConverter.convert_string() make nullable name parameter optional (#2660) (6fb9a5f)
  • Enable GPU for RapidOCR when available (#2659) (463a3fd)
  • Remove py3.14 requirement for default rapidocr (#2639) (da4c2e9)

Documentation

  • Add Hector as compatible AI agent platform integration (#2662) (ce5a099)
  • Added documentation to use SuryaOCR via plugin docling-surya (#2533) (b216ad8)
  • Fix broken homepage links (#2651) (03e7c7d)
  • examples: Processing parquet file of images (#2641) (8af228f)
  • Move Installation and Quickstart (Usage) under Getting started (#2644) (d549445)
  • Add redirection from getting started page (#2640) (ac9fc58)
  • examples: Remove deprecation warnings with export_to_dataframe (#2638) (f552862)

v2.62.0 - 2025-11-17

Feature

Fix

Documentation

v2.61.2 - 2025-11-10

Fix

v2.61.1 - 2025-11-06

Fix

Documentation

  • Make navigation menus collapse and expand (#2573) (8da3d28)

v2.61.0 - 2025-11-06

Feature

  • vlm: Track generated tokens and stop reasons for VLM models (#2543) (6a04e27)

Fix

  • Temporarily pin NuExtract to working revision (#2588) (fa92574)
  • ocr: Use PSM integer values directly instead of constructor (#2578) (1a5146a)

v2.60.1 - 2025-11-04

Fix

  • Extract response from api_image_request in picture description (#2571) (8360aa5)

v2.60.0 - 2025-10-31

Feature

  • Use threading in the standard pipeline and move old behavior to legacy (#2452) (268d027)

Fix

Documentation

v2.59.0 - 2025-10-30

Feature

Fix

  • Xlsx cell parsing, now returning values instead of formulas (#2520) (d9c90eb)

Documentation

  • Add details and examples on optimal GPU setup (#2531) (97aa06b)
  • Update opensearch notebook and backend documentation (#2519) (9a6fdf9)

v2.58.0 - 2025-10-22

Feature

  • pdf: Support for password-protected PDF documents (#2499) (bbe82a6)
  • backend: Add generic options support and HTML image handling modes (#2011) (a30e6a7)
  • ASR: MLX Whisper Support for Apple Silicon (#2366) (657ce8b)

Fix

  • markdown: Set the correct discriminator in md backend options (#2501) (4227fcc)
  • xlsx: Speed up by detecting the true last non-empty row/column (#2404) (b66624b)

Documentation

Performance

v2.57.0 - 2025-10-15

Feature

Fix

  • Use proper page concatentation in VLM pipeline MD/HTML conversion (#2458) (cd7f7ba)

Documentation

v2.56.1 - 2025-10-13

Fix

  • Avoid downloading easyocr models by default (#2454) (688a7df)

v2.56.0 - 2025-10-13

Feature

  • AutoOCR model selecting the best OCR model available and deprecating the usage of EasyOCR (#2391) (f7244a4)
  • Add Tesseract PSM options support (#2411) (f11f8c0)

Fix

  • asr: Implement robust status check in AsrPipeline (#2442) (db985bb)
  • Deal with chartsheets in workbooks (#2433) (cce18b2)
  • Skip temporary docx files (#2413) (ee55013)
  • AsrPipeline to handle absolute paths and BytesIO streams correctly (#2407) (b5f7fef)
  • Enrichment of documents without pages metadata (pptx and xlsx) (#2401) (0610d01)
  • Proper heading support in rich tables for HTML backend (#2394) (9705f40)

Documentation

v2.55.1 - 2025-10-03

Fix

Documentation

v2.55.0 - 2025-09-30

Feature

  • Repetition-based StoppingCriteria for GraniteDocling (#2323) (1e9dc43)
  • Rich tables support for HTML backend (#2324) (c803abe)

Fix

  • Pin wider range of typer (#2309) (68ae7cc)
  • Update Transformers & VLLM inference code, CLI and VLM specs (#2322) (654c70f)
  • Support escaped characters in markdown backend (#2304) (9d67bb9)

Documentation

v2.54.0 - 2025-09-22

Feature

Fix

  • Correct y-axis scaling in draw_table_cells (#2287) (b5628f1)

Documentation

v2.53.0 - 2025-09-17

Feature

Fix

  • Handle empty result from RapidOCR to avoid crash (#2264) (609d902)

Documentation

v2.52.0 - 2025-09-11

Feature

  • Enrichment steps on all convert pipelines (incl docx, html, etc) (#2251) (2c91234)

Fix

  • Add missing features in ThreadedStandardPdfPipeline (#2252) (0700af2)
  • Address deprecation warnings of dependencies (#2237) (c696549)

Documentation

  • Add an example of RAG with OpenSearch (#2238) (f8cc545)
  • Add instructions for using Docling with MCP to README (#2219) (e5cd702)
  • Document VLM support requirement in extraction example (#2231) (55f5f37)

v2.51.0 - 2025-09-05

Feature

  • Updating default parameters to get better performance with docling-parse (#2208) (b49d1ad)
  • Updated the backend for new docling-parse (#2187) (b3d7542)

Documentation

v2.50.0 - 2025-09-03

Feature

Fix

  • html: Access to variable not yet declared (#2171) (293e81b)

v2.49.0 - 2025-09-01

Feature

  • [Beta] Extraction with schema (#2138) (9f4bc5b)
  • msexcel: Set ContentLayer.INVISIBLE for invisible sheet (#1876) (a283ccf)

Fix

  • pypdfium2: Fix OCR bounding box misalignment caused by mismatched rotation metadata (#2039) (4d94e38)
  • Translation example (#2166) (9f0286b)
  • Extend offline mode for rapidocr fonts (#2155) (9904d14)

Documentation

v2.48.0 - 2025-08-26

Feature

Fix

  • html: Preserve code blocks in list items (#2131) (fa3327e)

v2.47.1 - 2025-08-23

Fix

v2.47.0 - 2025-08-22

Feature

  • CLI: Option to download arbitrary HuggingFace model (#2123) (cdf079d)
  • Batching support for VLMs in transformers backend, add initial VLLM backend (#2094) (3c660c0)
  • html: Support formatting tags in HTML texts (#2111) (94fcc46)

Fix

  • Improve numbered list detection for msword docs (#2100) (3f03709)

Documentation

v2.46.0 - 2025-08-20

Feature

Fix

  • HTML: Parse footer tag as a group in furniture content layer (#2106) (c5f2e2f)

Performance

  • Clean up resources with docling-parse v4, no parsed_page output by default (#2105) (5f57ff2)
  • Speed up function _parse_orientation (#1934) (8820b55)

v2.45.0 - 2025-08-18

Feature

  • Add backend for METS with Google Books profile (#1989) (31087f3)
  • html: Support in-line anchor tags in HTML texts (#1659) (9687297)
  • vlm: Ability to preprocess VLM response (#1907) (5f050f9)

Documentation

v2.44.0 - 2025-08-12

Feature

  • Add convert_string to document-converter (#2069) (b09033c)

Fix

  • html: Parse rawspan and colspan when they include non numerical values (#2048) (ed56f2d)
  • Support new mlx-vlm module (#2001) (0130e3a)
  • Extend error reporting when verbose logging is enabled (#2017) (2eb760d)
  • HTML: Replace non-standard Unicode characters (#2006) (86f7012)

Documentation

v2.43.0 - 2025-07-28

Feature

Fix

  • markdown: Ensure correct parsing of nested lists (#1995) (aec29a7)
  • HTML: Remove an unnecessary print command (#1988) (945721a)

v2.42.2 - 2025-07-24

Fix

  • HTML: Concatenation of child strings in table cells and list items (#1981) (5132f06)
  • docx: Adding plain latex equations to table cells (#1986) (0b83609)
  • Preserve PARTIAL_SUCCESS status when document timeout hits (#1975) (98e2fcf)
  • Multi-page image support (tiff) (#1928) (8d50a59)

Documentation

v2.42.1 - 2025-07-22

Fix

Documentation

v2.42.0 - 2025-07-18

Feature

  • Add option to control empty clusters in layout postprocessing (#1940) (a436be7)

Fix

  • Safe pipeline init, use device_map in transformers models (#1917) (cca05c4)
  • Fix HTML table parser and JATS backend bugs (#1948) (e1e3053)
  • KeyError: 'fPr' when processing latex fractions in DOCX files (#1926) (95e7096)
  • Change granite vision model URL from preview to stable version (#1925) (c5fb353)

Documentation

v2.41.0 - 2025-07-10

Feature

Fix

  • ocr-utils: Unit test and fix the rotate_bounding_box function (#1897) (931eb55)
  • Docs are missing osd packages for tesseract on RHEL (#1905) (e25873d)
  • Use only backend for picture classifier (#1904) (edd4356)
  • Typo in asr options (#1902) (dd8fde7)

v2.40.0 - 2025-07-04

Feature

  • Introduce LayoutOptions to control layout postprocessing behaviour (#1870) (ec6cf6f)
  • Integrate ListItemMarkerProcessor into document assembly (#1825) (56a0e10)

Fix

  • Secure torch model inits with global locks (#1884) (598c9c5)
  • Ensure that TesseractOcrModel does not crash in case OSD is not installed (#1866) (ae39a94)

Performance

  • msexcel: _find_table_bounds use iter_rows/iter_cols instead of Worksheet.cell (#1875) (13865c0)
  • Move expensive imports closer to usage (#1863) (3089cf2)

v2.39.0 - 2025-06-27

Feature

  • Leverage new list modeling, capture default markers (#1856) (0533da1)

Fix

  • markdown: Make parsing of rich table cells valid (#1821) (e79e4f0)

v2.38.1 - 2025-06-25

Fix

  • Updated granite vision model version for picture description (#1852) (d337825)
  • markdown: Fix single-formatted headings & list items (#1820) (7c5614a)
  • Fix response type of ollama (#1850) (41e8cae)
  • Handle missing runs to avoid out of range exception (#1844) (4002de1)

v2.38.0 - 2025-06-23

Feature

Fix

  • docx: Ensure list items have a list parent (#1827) (d26dac6)
  • msword_backend: Identify text in the same line after an image #1425 (#1610) (1350a8d)
  • Ensure uninitialized pages are removed before assembling document (#1812) (dd7f64f)
  • Formula conversion with page_range param set (#1791) (dbab30e)

Documentation

v2.37.0 - 2025-06-16

Feature

  • Make Page.parsed_page the only source of truth for text cells, add OCR cells to it (#1745) (7d3302c)
  • Support xlsm files (#1520) (df14022)

Fix

  • Pptx line break and space handling (#1664) (f28d23c)
  • asciidoc: Set default size when missing in image directive (#1769) (b886e4d)
  • Handle NoneType error in MsPowerpointDocumentBackend (#1747) (7a275c7)
  • Prov for merged-elems (#1728) (6613b9e)
  • tesseract: Initialize df_osd to avoid uninitialized variable error (#1718) (e979750)
  • Allow custom torch_dtype in vlm models (#1735) (f7f3113)
  • Improve extraction from textboxes in Word docs (#1701) (9dbcb3d)
  • Add WEBP to the list of image file extensions (#1711) (a2b83fe)

Documentation

v2.36.1 - 2025-06-04

Fix

Documentation

v2.36.0 - 2025-06-03

Feature

v2.35.0 - 2025-06-02

Feature

  • Add visualization of bbox on page with html export. (#1663) (b356b33)

Fix

  • Guess HTML content starting with script tag (#1673) (984cb13)
  • UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 0: invalid continuation byte (#1665) (51d3450)

Documentation

v2.34.0 - 2025-05-22

Feature

  • ocr: Auto-detect rotated pages in Tesseract (#1167) (45265bf)
  • Establish confidence estimation for document and pages (#1313) (9087524)

Fix

  • Fix ZeroDivisionError for cell_bbox.area() (#1636) (c2f595d)
  • integration: Update the Apify Actor integration (#1619) (14d4f5b)

v2.33.0 - 2025-05-20

Feature

  • Add textbox content extraction in msword_backend (#1538) (12a0e64)

Fix

  • Fix issue with detecting docx files, and files with upper case extensions (#1609) (f4d9d41)
  • Load_from_doctags static usage (#1617) (0e00a26)
  • Incorrect force_backend_text behaviour for VLM DocTag pipelines (#1371) (f2e9c07)
  • pypdfium: Resolve overlapping text when merging bounding boxes (#1549) (98b5eeb)

v2.32.0 - 2025-05-14

Feature

  • Improve parallelization for remote services API calls (#1548) (3a04f2a)
  • Support image/webp file type (#1415) (12dab0a)

Fix

  • ocr: Orig field in TesseractOcrCliModel as str (#1553) (9f8b479)
  • settings: Fix nested settings load via environment variables (#1551) (2efb7a7)

Documentation

  • Add advanced chunking & serialization example (#1589) (9f28abf)

v2.31.2 - 2025-05-13

Fix

  • AsciiDoc header identification (#1562) (#1563) (4046d0b)
  • Restrict click version and update lock file (#1582) (8baa85a)

v2.31.1 - 2025-05-12

Fix

  • Add smoldocling in download utils (#1577) (127e386)
  • HTML: Handle row spans in header rows (#1536) (776e7ec)
  • Mime error in document streams (#1523) (f1658ed)
  • Usage of hashlib for FIPS (#1512) (7c70573)
  • Guard against attribute errors in TesseractOcrModel del (#1494) (4ab7e9d)
  • Enable cuda_use_flash_attention2 for PictureDescriptionVlmModel (#1496) (cc45396)
  • Updated the time-recorder label for reading order (#1490) (976e92e)
  • Incorrect scaling of TableModel bboxes when do_cell_matching is False (#1459) (94d66a0)

Documentation

v2.31.0 - 2025-04-25

Feature

  • Add tutorial using Milvus and Docling for RAG pipeline (#1449) (a2fbbba)

Fix

  • html: Handle address, details, and summary tags (#1436) (ed20124)
  • Treat overflowing -v flags as DEBUG (#1419) (8012a3e)
  • codecov: Fix codecov argument and yaml file (#1399) (fa7fc9e)

Documentation

v2.30.0 - 2025-04-14

Feature

  • cli: Add option for html with split-page mode (#1355) (c0ba88e)
  • xlsx: Create a page for each worksheet in XLSX backend (#1332) (eef2bde)
  • OllamaVlmModel for Granite Vision 3.2 (#1337) (c605edd)

Fix

  • deps: Widen typer upper bound (#1375) (7e40ad3)
  • Auto-recognize .xlsx, .docx and .pptx files (#1340) (0de70e7)
  • docx: Declare image_data variable when handling pictures (#1359) (415b877)
  • Implement PictureDescriptionApiOptions.bitmap_area_threshold (#1248) (2503999)
  • Properly address page in pipeline _assemble_document when page_range is provided (#1334) (6b696b5)

v2.29.0 - 2025-04-10

Feature

Fix

  • docx: Adding new latex symbols, simplifying how equations are added to text (#1295) (14e9c0c)
  • pptx: Check if picture shape has an image attached (#1316) (dc3bf9c)
  • docx: Improve text parsing (#1268) (d2d6874)
  • Tesseract OCR CLI can't process images composed with numbers only (#1201) (b3d111a)

Documentation

v2.28.4 - 2025-03-29

Fix

v2.28.3 - 2025-03-28

Fix

v2.28.2 - 2025-03-26

Fix

  • Improve HTML layer detection, various MD fixes (#1241) (9210812)
  • html: Fix HTML parsed heading level (#1244) (85c4df8)

v2.28.1 - 2025-03-25

Fix

  • converter: Cache same pipeline class with different options (#1152) (825b226)
  • debug: Missing translation of bbox to to_bounding_box (#1220) (6df8827)
  • docx: Identifying numbered headers (#1231) (f739d0e)

Documentation

  • examples: Batch conversion doc raises_on_error (#1147) (0974ba4)

v2.28.0 - 2025-03-19

Feature

  • SmolDocling: Support MLX acceleration in VLM pipeline (#1199) (1c26769)
  • Add PPTX notes slides (#474) (b454aa1)
  • Updated vlm pipeline (with latest changes from docling-core) (#1158) (2f72167)

Fix

  • Determine correct page size in DoclingParseV4Backend (#1196) (f5adfb9)
  • msword: Fixing function return in equations handling (#1194) (0b707d0)

Documentation

v2.27.0 - 2025-03-18

Feature

  • Add factory for ocr engines via plugins (#1010) (6eaae3c)
  • Add DoclingParseV4 backend, using high-level docling-parse API (#905) (3960b19)
  • actor: Docling Actor on Apify infrastructure (#875) (772487f)
  • Equations to latex in MSWord backend (with inline groups) (#1114) (6eb718f)

Fix

Documentation

v2.26.0 - 2025-03-11

Feature

  • Use new TableFormer model weights and default to accurate model version (#1100) (eb97357)

Fix

Documentation

  • Add description of DOCLING_ARTIFACTS_PATH env var (#1124) (e1c49ad)

Performance

  • New revision code formula model and document picture classifier (#1140) (5e30381)

v2.25.2 - 2025-03-05

Fix

  • Proper handling of orphan IDs in layout postprocessing (#1118) (c56ab3a)

Documentation

v2.25.1 - 2025-03-03

Fix

  • Enable locks for threadsafe pdfium (#1052) (8dc0562)
  • html: Use 'start' attribute when parsing ordered lists from HTML docs (#1062) (de7b963)

Documentation

  • Improve docs on token limit warning triggered by HybridChunker (#1077) (db3ceef)

v2.25.0 - 2025-02-26

Feature

  • [Experimental] Introduce VLM pipeline using HF AutoModelForVision2Seq, featuring SmolDocling model (#1054) (3c9fe76)
  • cli: Add option for downloading all models, refine help messages (#1061) (ab683e4)

Fix

Documentation

  • Extend chunking docs, add FAQ on token limit (#1053) (c84b973)

v2.24.0 - 2025-02-20

Feature

v2.23.1 - 2025-02-20

Fix

  • Runtime error when Pandas Series is not always of string type (#1024) (6796f0a)

Documentation

v2.23.0 - 2025-02-17

Feature

Fix

  • Revise DocTags, fix iterate_items to output content_layer in items (#965) (6e75f0b)

v2.22.0 - 2025-02-14

Feature

  • Add support for CSV input with new backend to transform CSV files to DoclingDocument (#945) (00d9405)
  • Introduce the enable_remote_services option to allow remote connections while processing (#941) (2716c7d)
  • Allow artifacts_path to be defined as ENV (#940) (5101e25)

Fix

Documentation

  • Update example Dockerfile with download CLI (#929) (7493d5b)
  • Examples for picture descriptions (#951) (2d66e99)

v2.21.0 - 2025-02-10

Feature

  • Add content_layer property to items to address body, furniture and other roles (#735) (cf78d5b)

v2.20.0 - 2025-02-07

Feature

  • Describe pictures using vision models (#259) (4cc6e3e)

Fix

v2.19.0 - 2025-02-07

Feature

Fix

  • markdown: Handle nested lists (#910) (90b766e)
  • Test cases for RTL programmatic PDFs and fixes for the formula model (#903) (9114ada)
  • msword_backend: Handle conversion error in label parsing (#896) (722a6eb)
  • Enrichment models batch size and expose picture classifier (#878) (5ad6de0)

Documentation

  • Introduce example with custom models for RapidOCR (#874) (6d3fea0)

v2.18.0 - 2025-02-03

Feature

Fix

  • markdown: Fix parsing if doc ending with table (#873) (5ac2887)
  • markdown: Add support for HTML content (#855) (94751a7)
  • docx: Merged table cells not properly converted (#857) (0cd81a8)
  • Processing of placeholder shapes in pptx that have text but no bbox (#868) (eff16b6)
  • KeyError in tableformer prediction (#854) (b1cf796)
  • Fixed docx import with headers that are also lists (#842) (2c037ae)
  • Use new add_code in html backend and add more typing hints (#850) (2a1f8af)
  • markdown: Fix empty block handling (#843) (bccb022)
  • Fix for the crash when encountering WMF images in pptx and docx (#837) (fea0a99)

Documentation

  • Updated the readme with upcoming features (#831) (d7c0828)
  • Add example for inspection of picture content (#624) (f9144f2)

v2.17.0 - 2025-01-28

Feature

  • CLI: Expose code and formula models in the CLI (#820) (6882e6c)
  • Add platform info to CLI version printout (#816) (95b293a)
  • ocr: Expose rec_keys_path in RapidOcrOptions to support custom dictionaries (#786) (5332755)
  • Introduce automatic language detection in TesseractOcrCliModel (#800) (3be2fb5)

Fix

  • Fix single newline handling in MD backend (#824) (5aed9f8)
  • Use file extension if filetype fails with PDF (#827) (adf6353)
  • Parse html with omitted body tag (#818) (a112d7a)

Documentation

v2.16.0 - 2025-01-24

Feature

  • New document picture classifier (#805) (16a218d)
  • Add Docling JSON ingestion (#783) (88a0e66)
  • Code and equation model for PDF and code blocks in markdown (#752) (3213b24)
  • Add "auto" language for TesseractOcr (#759) (8543c22)

Fix

  • Added extraction of byte-images in excel (#804) (a458e29)
  • Update docling-parse-v2 backend version with new parsing fixes (#769) (670a08b)

Documentation

v2.15.1 - 2025-01-10

Fix

  • Improve OCR results, stricten criteria before dropping bitmap areas (#719) (5a060f2)
  • Allow earlier requests versions (#716) (e64b5a2)

Documentation

v2.15.0 - 2025-01-08

Feature

  • Added http header support for document converter and cli (#642) (0ee849e)

Fix

  • Correct scaling of debug visualizations, tune OCR (#700) (5cb4cf6)
  • Let BeautifulSoup detect the HTML encoding (#695) (42856fd)
  • mspowerpoint: Handle invalid images in PowerPoint slides (#650) (d49650c)

Documentation

v2.14.0 - 2024-12-18

Feature

  • Create a backend to transform PubMed XML files to DoclingDocument (#557) (fd03480)

v2.13.0 - 2024-12-17

Feature

  • Updated Layout processing with forms and key-value areas (#530) (60dc852)
  • Create a backend to parse USPTO patents into DoclingDocument (#606) (4e08750)
  • Add Easyocr parameter recog_network (#613) (3b53bd3)

Documentation

  • Add Haystack RAG example (#615) (3e599c7)
  • Fix the path to the run_with_accelerator.py example (#608) (3bb3bf5)

v2.12.0 - 2024-12-13

Feature

  • Introduce support for GPU Accelerators (#593) (19fad92)

v2.11.0 - 2024-12-12

Feature

  • Add timeout limit to document parsing job. DS4SD#270 (#552) (3da166e)

Fix

  • Do not import python modules from deepsearch-glm (#569) (aee9c0b)
  • Handle no result from RapidOcr reader (#558) (f45499c)
  • Make enum serializable with human-readable value (#555) (a7df337)

Documentation

  • Update chunking usage docs, minor reorg (#550) (d0c9e8e)

v2.10.0 - 2024-12-09

Feature

  • Docling-parse v2 as default PDF backend (#549) (aca57f0)

Fix

  • Call into docling-core for legacy document transform (#551) (7972d47)
  • Introduce Image format options in CLI. Silence the tqdm downloading messages. (#544) (78f61a8)

v2.9.0 - 2024-12-09

Feature

  • Expose new hybrid chunker, update docs (#384) (c8ecdd9)
  • MS Word backend: Make detection of headers and other styles localization agnostic (#534) (3e073df)

Fix

  • Correcting DefaultText ID for MS Word backend (#537) (eb7ffcd)
  • Add py.typed marker file (#531) (9102fe1)
  • Enable HTML export in CLI and add options for image mode (#513) (0d11e30)
  • Missing text in docx (t tag) when embedded in a table (#528) (b730b2d)
  • Restore pydantic version pin after fixes (#512) (c830b92)
  • Folder input in cli (#511) (8ada0bc)

Documentation

v2.8.3 - 2024-12-03

Fix

  • Improve handling of disallowed formats (#429) (34c7c79)

v2.8.2 - 2024-12-03

Fix

  • ParserError EOF inside string (#470) (#472) (c90c41c)
  • PermissionError when using tesseract_ocr_cli_model (#496) (d3f84b2)

Documentation

Performance

  • Prevent temp file leftovers, reuse core type (#487) (051789d)

v2.8.1 - 2024-11-29

Fix

Documentation

v2.8.0 - 2024-11-27

Feature

  • ocr: Added support for RapidOCR engine (#415) (85b2999)

Fix

  • Use correct image index in word backend (#442) (767563b)
  • Update tests and examples for docling-core 2.5.1 (#449) (29807a2)

v2.7.1 - 2024-11-26

Fix

Documentation

  • Add DocETL, Kotaemon, spaCy integrations; minor docs improvements (#408) (7a45b92)

v2.7.0 - 2024-11-20

Feature

  • Add support for ocrmac OCR engine on macOS (#276) (6efa96c)

Fix

v2.6.0 - 2024-11-19

Feature

  • Added support for exporting DocItem to an image when page image is available (#379) (3f91e7d)
  • Expose ocr-lang in CLI (#375) (ed785ea)
  • Added excel backend (#334) (926dfd2)
  • Extracting picture data for raster images found in PPTX (#349) (7a97d71)

Fix

  • Fixing images in the input Word files (#330) (8533039)
  • Reduce logging by keeping option for more verbose (#323) (8b437ad)

Documentation

v2.5.2 - 2024-11-13

Fix

v2.5.1 - 2024-11-12

Fix

  • Handling of single-cell tables in DOCX backend (#314) (fb8ba86)

Documentation

v2.5.0 - 2024-11-12

Feature

  • OCR: Introduce the OcrOptions.force_full_page_ocr parameter that forces a full page OCR scanning (#290) (c6b3763)

Fix

  • Configure env prefix for docling settings (#315) (5d4a10b)
  • Added handling of grouped elements in pptx backend (#307) (81c8243)
  • Allow mps usage for easyocr (#286) (97f214e)

Documentation

v2.4.2 - 2024-11-08

Fix

  • EasyOcrModel: Support the use_gpu pipeline parameter in EasyOcrModel. Initialize easyocr (#282) (0eb065e)

v2.4.1 - 2024-11-08

Fix

  • tesserocr: Raise Exception if tesserocr has not loaded any languages (#279) (704d792)
  • Dockerfile example copy command (#234) (90836db)

Documentation

v2.4.0 - 2024-11-04

Feature

  • Pdf backend, table mode as options and artifacts path (#203) (40ad987)

Documentation

v2.3.1 - 2024-10-30

Fix

  • Simplify torch dependencies and update pinned docling deps (#190) (eb679cc)
  • Allow to explicitly initialize the pipeline (#189) (904d24d)

v2.3.0 - 2024-10-30

Feature

  • Add pipeline timings and toggle visualization, establish debug settings (#183) (2a2c65b)

Fix

  • Fix duplicate title and heading + add e2e tests for html and docx (#186) (f542460)

v2.2.1 - 2024-10-28

Fix

  • Fix header levels for DOCX & HTML (#184) (b9f5c74)
  • Handling of long sequence of unescaped underscore chars in markdown (#173) (94d0729)
  • HTML backend, fixes for Lists and nested texts (#180) (7d19418)
  • MD Backend, fixes to properly handle trailing inline text and emphasis in headers (#178) (88c1673)

Documentation

v2.2.0 - 2024-10-23

Feature

  • Update to docling-parse v2 without history (#170) (4116819)
  • Support AsciiDoc and Markdown input format (#168) (3023f18)

Fix

  • Set valid=false for invalid backends (#171) (3496b48)

v2.1.0 - 2024-10-18

Feature

  • Add coverage_threshold to skip OCR for small images (#161) (b346faf)

Fix

Documentation

v2.0.0 - 2024-10-16

Feature

Breaking

Documentation

v1.20.0 - 2024-10-11

Feature

  • New experimental docling-parse v2 backend (#131) (5e4944f)

v1.19.1 - 2024-10-11

Fix

  • Remove stderr from tesseract cli and introduce fuzziness in the text validation of OCR tests (#138) (dae2a3b)

Documentation

  • Simplify LlamaIndex example using Docling extension (#135) (5f1bd9e)

v1.19.0 - 2024-10-08

Feature

  • Add options for choosing OCR engines (#118) (f96ea86)

v1.18.0 - 2024-10-03

Feature

v1.17.0 - 2024-10-03

Feature

v1.16.1 - 2024-09-27

Fix

Documentation

v1.16.0 - 2024-09-27

Feature

  • Support tableformer model choice (#90) (d6df76f)

v1.15.0 - 2024-09-24

Feature

v1.14.0 - 2024-09-24

Feature

Fix

  • Fix OCR setting for pypdfium, minor refactor (#102) (d96b96c)

Documentation

v1.13.1 - 2024-09-23

Fix

  • Updated the render_as_doctags with the new arguments from docling-core (#93) (4794ce4)

v1.13.0 - 2024-09-18

Feature

Fix

  • Bumped the glm version and adjusted the tests (#83) (442443a)

Documentation

  • Updated Docling logo.png with transparent background (#88) (0da7519)

v1.12.2 - 2024-09-17

Fix

  • tests: Adjust the test data to match the new version of LayoutPredictor (#82) (fa9699f)

v1.12.1 - 2024-09-16

Fix

  • CLI compatibility with python 3.10 and 3.11 (#79) (2870fdc)

v1.12.0 - 2024-09-13

Feature

Documentation

  • Showcase RAG with LlamaIndex and LangChain (#71) (53569a1)

v1.11.0 - 2024-09-10

Feature

v1.10.0 - 2024-09-10

Feature

  • Linux arm64 support and reducing dependencies (#69) (27a7a15)

v1.9.0 - 2024-09-03

Feature

  • Export document pages as multimodal output (#54) (1de2e4f)

Documentation

v1.8.5 - 2024-08-30

Fix

v1.8.4 - 2024-08-30

Fix

Documentation

  • Add instructions for cpu-only installation (#56) (a8a60d5)

v1.8.3 - 2024-08-28

Fix

  • Table cells overlap and model warnings (#53) (f49ee82)

v1.8.2 - 2024-08-27

Fix

Documentation

v1.8.1 - 2024-08-26

Fix

v1.8.0 - 2024-08-23

Feature

  • Page-level error reporting from PDF backend, introduce PARTIAL_SUCCESS status (#47) (a294b7e)

v1.7.1 - 2024-08-23

Fix

  • Better raise exception when a page fails to parse (#46) (8808463)
  • Upgrade docling-parse to 1.1.1, safety checks for failed parse on pages (#45) (7e84533)

v1.7.0 - 2024-08-22

Feature

  • Upgrade docling-parse PDF backend and interface to use page-by-page parsing (#44) (a8c6b29)

v1.6.3 - 2024-08-22

Fix

  • Usage of bytesio with docling-parse (#43) (fac5745)

v1.6.2 - 2024-08-22

Fix

  • Remove [ocr] extra to fix wheel install (#42) (6995268)

v1.6.1 - 2024-08-21

Fix

v1.6.0 - 2024-08-20

Feature

  • Add adaptive OCR, factor out treatment of OCR areas and cell filtering (#38) (e94d317)

v1.5.0 - 2024-08-20

Feature

  • Allow computing page images on-demand with scale and cache them (#36) (78347bf)

Documentation

v1.4.0 - 2024-08-14

Feature

  • Update parser with bytesio interface and set as new default backend (#32) (90dd676)

Fix

v1.3.0 - 2024-08-12

Feature

  • Output page images and extracted bbox (#31) (63d80ed)

v1.2.1 - 2024-08-07

Fix

Documentation

v1.2.0 - 2024-08-07

Feature

v1.1.2 - 2024-07-31

Fix

  • Set page number using 1-based indexing (#22) (d2d9543)

v1.1.1 - 2024-07-30

Fix

  • Correct text extraction for table cells (#21) (f4bf3d2)

v1.1.0 - 2024-07-26

Feature

  • Add simplified single-doc conversion (#20) (d603137)

v1.0.2 - 2024-07-24

Fix

  • Add easyocr to main deps for valid extra (#19) (54b3dda)

v1.0.1 - 2024-07-24

Fix

v1.0.0 - 2024-07-18

Feature

Breaking

v0.4.0 - 2024-07-17

Feature

  • Optimize table extraction quality, add configuration options (#11) (e9526bb)

v0.3.1 - 2024-07-17

Fix

Documentation

  • Reflect supported Python versions, add badges (#10) (2baa35c)

v0.3.0 - 2024-07-17

Feature

  • Enable python 3.12 support by updating glm (#8) (fb72688)

Documentation

  • Add setup with pypi to Readme (#7) (2803222)

v0.2.0 - 2024-07-16

Feature
Reference in New Issue View Git Blame Copy Permalink