docling
SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
Why this rank:Strong adoptionRecent releaseHealthy release cadence
Description
<p align="center"> <a href="https://github.com/docling-project/docling"> <img loading="lazy" alt="Docling" src="https://github.com/docling-project/docling/raw/main/docs/assets/docling_processing.png" width="100%"/> </a> </p> # Docling <p align="center"> <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </p> [](https://arxiv.org/abs/2408.09869) [](https://docling-project.github.io/docling/) [](https://pypi.org/project/docling/) [](https://pypi.org/project/docling/) [](https://github.com/astral-sh/uv) [](https://github.com/astral-sh/ruff) [](https://pydantic.dev) [](https://github.com/pre-commit/pre-commit) [](https://opensource.org/licenses/MIT) [](https://pepy.tech/projects/docling) [](https://apify.com/vancura/docling) [](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github) [](https://docling.ai/discord) [](https://www.bestpractices.dev/projects/10101) [](https://lfaidata.foundation/projects/) Docling simplifies document processing, parsing diverse formats โ including advanced PDF understanding โ and providing seamless integrations with the gen AI ecosystem. ## Features * ๐๏ธ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, WebVTT, images (PNG, TIFF, JPEG, ...), LaTeX, plain text, and more * ๐ Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more * ๐งฌ Unified, expressive [DoclingDocument][docling_document] representation format * โช๏ธ Various [export formats][supported_formats] and options, including Markdown, HTML, WebVTT, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON * ๐ Support of several application-specifc XML schemas incl. [USPTO](https://www.uspto.gov/patents) patents, [JATS](https://jats.nlm.nih.gov/) articles, and [XBRL](https://www.xbrl.org/) financial reports. * ๐ Local execution capabilities for sensitive data and air-gapped environments * ๐ค Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI * ๐ Extensive OCR support for scanned PDFs and images * ๐ Support of several Visual Language Models ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M)) * ๐๏ธ Audio support with Automatic Speech Recognition (ASR) models * ๐ Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/) * ๐ป Simple and convenient CLI ### What's new * ๐ค Structured [information extraction][extraction] \[๐งช beta\] * ๐ New layout model (**Heron**) by default, for faster PDF parsing * ๐ [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications * ๐ผ Parsing of XBRL (eXtensible Business Reporting Language) documents for financial reports * ๐ฌ Parsing of WebVTT (Web Video Text Tracks) files and export to WebVTT format * ๐ฌ Parsing of LaTeX files * ๐ Parsing of plain-text files (`.txt`, `.text`) and Markdown supersets (`.qmd`, `.Rmd`) * ๐ Chart understanding (Barchart, Piechart, LinePlot): converting them into tables, code or adding detailed descriptions ### Coming soon * ๐ Metadata extraction, including title, authors, references & language * ๐ Complex chemistry understanding (Molecular structures) ## Installation To use Docling, simply install `docling` from your package manager, e.g. pip: ```bash pip install docling ``` > **Note:** Python 3.9 support was dropped in docling version 2.70.0. Please use Python 3.10 or higher
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| v2.97.0 | ### Feature * Add email parsing to the backends ([#3475](https://github.com/docling-project/docling/issues/3475)) ([`b741c4a`](https://github.com/docling-project/docling/commit/b741c4affd736fa3ee5d760cc45956320da3fbb0)) * Row-section support in HTML backend ([#3360](https://github.com/docling-project/docling/issues/3360)) ([`d9c71cb`](https://github.com/docling-project/docling/commit/d9c71cb172ac2aa844e3ca7141e9673da41ae700)) * **cli:** Fetch HTML images ([#3506](https://github.com/docling-proj | High | 6/3/2026 |
| v2.96.0 | ### Feature * Add threaded docling-parse (v6) PDF backend ([#3377](https://github.com/docling-project/docling/issues/3377)) ([`3c26f5a`](https://github.com/docling-project/docling/commit/3c26f5a3a8a5904e45848bc1a9e43105fdeba3e3)) ### Fix * Accept JSON transformers model type ([#3488](https://github.com/docling-project/docling/issues/3488)) ([`d25aea1`](https://github.com/docling-project/docling/commit/d25aea129a81cec331e8078a13dbda1078891d98)) ### Documentation * Fix rendering of icons ([#3 | High | 5/28/2026 |
| v2.95.0 | ### Feature * Add scoped settings context manager ([#3440](https://github.com/docling-project/docling/issues/3440)) ([`d907d21`](https://github.com/docling-project/docling/commit/d907d21018cf5f71280cf8c4985b2c83dac7de49)) * Add more document metadata in callbacks ([#3485](https://github.com/docling-project/docling/issues/3485)) ([`48b4d1c`](https://github.com/docling-project/docling/commit/48b4d1c7fdf12907da05ae0bdbdb0509f18e4133)) * **html:** Add custom headers support for HTML backend image f | High | 5/21/2026 |
| v2.94.0 | ### Feature * **latex:** Add optional Tectonic TikZ rendering ([#3369](https://github.com/docling-project/docling/issues/3369)) ([`eceedc2`](https://github.com/docling-project/docling/commit/eceedc2f4015d058f70cbe506dd4c14b2309281c)) * Add image_placeholder and use_markdown_images as fields in the BaseChunkerOptions ([#3436](https://github.com/docling-project/docling/issues/3436)) ([`5fadc6d`](https://github.com/docling-project/docling/commit/5fadc6d180fbee352c83c0158925b53d5fbd1b18)) * **extra | High | 5/18/2026 |
| v2.93.0 | ### Feature * **vlm:** Upgrade Granite Vision model to 4.1 for table + chart extraction ([#3382](https://github.com/docling-project/docling/issues/3382)) ([`24f2d14`](https://github.com/docling-project/docling/commit/24f2d148d9b904362c80844f554f7ea28a20ba40)) ### Fix * **docx:** Fix OMML equation handling and improve type safety ([#3381](https://github.com/docling-project/docling/issues/3381)) ([`e00735d`](https://github.com/docling-project/docling/commit/e00735dd59e9103bd7671139e0671b88e2d28 | High | 5/5/2026 |
| v2.92.0 | ### Feature * Extend the kserve-triton OCR model to have multi-lingual support ([#3368](https://github.com/docling-project/docling/issues/3368)) ([`8b67fae`](https://github.com/docling-project/docling/commit/8b67fae6873a10b7af3ac061b766e4caaa6fe137)) * **docx:** Add checkbox parsing support ([#3349](https://github.com/docling-project/docling/issues/3349)) ([`c455a65`](https://github.com/docling-project/docling/commit/c455a65e36f1897543793bc9df37bb633d0ca7ae)) * Introduce modular docling-slim pa | High | 4/29/2026 |
| v2.91.0 | ### Feature * **docx:** Extract VML images with v:imagedata elements ([#3343](https://github.com/docling-project/docling/issues/3343)) ([`2ddaa3b`](https://github.com/docling-project/docling/commit/2ddaa3be97dbf6d34614ccd5e33f510ba6102033)) ### Fix * Strengthen input validation for METSโGBS processing ([#3336](https://github.com/docling-project/docling/issues/3336)) ([`c1dbac2`](https://github.com/docling-project/docling/commit/c1dbac22c7a0d55f22d82af5262c9e60df915083)) * EasyOCR model | High | 4/23/2026 |
| 2.90.0 | Imported from PyPI (2.90.0) | Low | 4/21/2026 |
| v2.90.0 | ### Feature * Implement GraniteVisionTableStructureModel for VLM-based table extraction ([#3323](https://github.com/docling-project/docling/issues/3323)) ([`1569e42`](https://github.com/docling-project/docling/commit/1569e42f8484f7abda8b8fb615e9c67d47e83855)) ### Fix * **latex:** Fully unwrap deeply nested formatting macros ([#3249](https://github.com/docling-project/docling/issues/3249)) ([`101233e`](https://github.com/docling-project/docling/commit/101233ebe211ece703605a16a23225da836e3c46)) | High | 4/17/2026 |
| v2.89.0 | ### Feature * Explicit TikZ environment handling in LaTeX backend ([#3187](https://github.com/docling-project/docling/issues/3187)) ([`a15c16e`](https://github.com/docling-project/docling/commit/a15c16e19fc9531e68916d15a1976ba76414c545)) ### Fix * **ocr:** Align RapidOCR english assets with 3.8 mobile models ([#3291](https://github.com/docling-project/docling/issues/3291)) ([`251c8b2`](https://github.com/docling-project/docling/commit/251c8b217a72453205242993e03ca8004cb2877e)) * **docx:** Iso | High | 4/16/2026 |
| v2.88.0 | ### Feature * **service:** Establish client SDK for docling serve ([#3264](https://github.com/docling-project/docling/issues/3264)) ([`42157a3`](https://github.com/docling-project/docling/commit/42157a3e100ae306f74938310018be3909cabf8c)) ### Fix * **ocr:** Support rapidocr 3.8 mobile model naming ([#3277](https://github.com/docling-project/docling/issues/3277)) ([`6b257ec`](https://github.com/docling-project/docling/commit/6b257ece330db9c39b8834b2b5a87b9c1eecb1fa)) ### Documentation * Add a | Medium | 4/13/2026 |
| v2.87.0 | ### Feature * **vlm:** Add Nanonets OCR2 onboarding ([#3274](https://github.com/docling-project/docling/issues/3274)) ([`9970d1e`](https://github.com/docling-project/docling/commit/9970d1ef94c5e826080834d0f8858cfd8f9e7edb)) ### Fix * Transformers v5 compatibility for AUTOMODEL_CAUSALLM VLMs ([#3276](https://github.com/docling-project/docling/issues/3276)) ([`d431224`](https://github.com/docling-project/docling/commit/d43122447f9b5b9dcad1f88819b8cb2a59f62b33)) * **vlm:** Add explicit MLX suppo | Medium | 4/13/2026 |
| v2.86.0 | ### Feature * Support for GraniteVision v4 ([#3217](https://github.com/docling-project/docling/issues/3217)) ([`fd83420`](https://github.com/docling-project/docling/commit/fd834204fadcb15190f3f2c289841143773b5f9d)) * Add signature/stamp html block to DC document ([#3251](https://github.com/docling-project/docling/issues/3251)) ([`9b4b67b`](https://github.com/docling-project/docling/commit/9b4b67b23e77d6d9063ee141196707412bde1673)) * **vlm:** Add PARTIAL_SUCCESS status for VLM pipeline pages ([# | Medium | 4/10/2026 |
| v2.85.0 | ### Feature * Add support for Falcon-OCR ([#3237](https://github.com/docling-project/docling/issues/3237)) ([`d0e19be`](https://github.com/docling-project/docling/commit/d0e19be14ff3dbe8d44b5bf8bfe4cf53b58249f6)) * Add support for LightOnOCR-2-1B ([#3213](https://github.com/docling-project/docling/issues/3213)) ([`f2affd7`](https://github.com/docling-project/docling/commit/f2affd76149aa7c1ed84df1e84ef537f3905559b)) ### Fix * **latex:** Expand custom macro parameters ([#3223](https://github.co | Medium | 4/7/2026 |
| v2.84.0 | ### Feature * Glm ocr ([#3146](https://github.com/docling-project/docling/issues/3146)) ([`a9265d8`](https://github.com/docling-project/docling/commit/a9265d854a195993d2e63bfc8c4bb2f76be7f9d9)) * Switch to the latest version of DocumentFigureClassifier model v2.5 ([#3171](https://github.com/docling-project/docling/issues/3171)) ([`d046390`](https://github.com/docling-project/docling/commit/d046390bf4bff2c538cb33eebb03dce56d122d37)) * Remove the deprecation of extraction ([#3220](https://github. | Medium | 4/1/2026 |
| v2.83.0 | ### Feature * Upgrade to transformers v5 ([#3200](https://github.com/docling-project/docling/issues/3200)) ([`d2c6357`](https://github.com/docling-project/docling/commit/d2c6357982d79629440919188d73bda18bc678c8)) * OCR model for remote KServe v2 API ([#3189](https://github.com/docling-project/docling/issues/3189)) ([`8522b00`](https://github.com/docling-project/docling/commit/8522b00146a2217760ad1944934926ed0e9f5d39)) ### Fix * **pdf:** Propagate hyperlinks to DoclingDocument text items ([#31 | Medium | 3/31/2026 |
| v2.82.0 | ### Feature * Implementation of HTML backend with headless browser ([#2969](https://github.com/docling-project/docling/issues/2969)) ([`1c74a9b`](https://github.com/docling-project/docling/commit/1c74a9b9c7c2019b85abef8f0f94381a83b721df)) ### Fix * **omml:** Correct LaTeX output for fractions, math operators, and functions ([#3122](https://github.com/docling-project/docling/issues/3122)) ([`e36125b`](https://github.com/docling-project/docling/commit/e36125ba2ddfbe584fc752e6dc7ca0f0f8f58d87)) | Medium | 3/25/2026 |
| v2.81.0 | ### Feature * Route plain-text and Quarto/R Markdown files to the Markdown backend ([#3161](https://github.com/docling-project/docling/issues/3161)) ([`96d7c7e`](https://github.com/docling-project/docling/commit/96d7c7ec79992d8dddedfafaaedb7f9bf6e14f40)) ### Fix * **docx:** Missing list items after numbered header (#2665) ([#2678](https://github.com/docling-project/docling/issues/2678)) ([`2f7c09e`](https://github.com/docling-project/docling/commit/2f7c09e0d8f07a5fa0aaf4f33bdfb1f71d3f3063)) * | Low | 3/20/2026 |
| v2.80.0 | ### Feature * Add the VllmCudaGraphMode ([#3125](https://github.com/docling-project/docling/issues/3125)) ([`f950679`](https://github.com/docling-project/docling/commit/f950679f60ab6b1a9b057e7131fc8c8334e6e62e)) | Low | 3/14/2026 |
| v2.79.0 | ### Feature * Add fact metadata and linkbase relationships for XBRL ([#3084](https://github.com/docling-project/docling/issues/3084)) ([`7952efe`](https://github.com/docling-project/docling/commit/7952efee2fcbae2a9c516d75acd8995c004fc949)) ### Fix * Use OCR cells with TableFormer v2 ([#3107](https://github.com/docling-project/docling/issues/3107)) ([`93f6fee`](https://github.com/docling-project/docling/commit/93f6feeabcef81b1f71a189458b0166af9db176c)) * Add self-consistency check in the table | Low | 3/12/2026 |
| v2.78.0 | ### Feature * Add support for TableFormer v2 ([#3013](https://github.com/docling-project/docling/issues/3013)) ([`4ccd1d4`](https://github.com/docling-project/docling/commit/4ccd1d465deb8d521c09e2da61b537a9236d6560)) * Add gRPC transport for KServe v2 API engine ([#3074](https://github.com/docling-project/docling/issues/3074)) ([`3d90778`](https://github.com/docling-project/docling/commit/3d90778e3e5762b16758e1c121f42890e32f0560)) ### Fix * **html:** Fix broken document tree and quadratic com | Low | 3/10/2026 |
| v2.77.0 | ### Feature * Track vlm_inference time for mlx_model pipeline ([#3060](https://github.com/docling-project/docling/issues/3060)) ([`38c4bb2`](https://github.com/docling-project/docling/commit/38c4bb26e8e3a7797d1caec3f690a7c8d5d9a735)) * Add configurable graph_optimization_level for ONNX Runtime engines ([#3071](https://github.com/docling-project/docling/issues/3071)) ([`cfc6636`](https://github.com/docling-project/docling/commit/cfc6636a2a0e6b149dd51714d20e9b93f3f6463b)) ### Fix * **docx:** Pr | Low | 3/6/2026 |
| v2.76.0 | ### Feature * Export to WebVTT format ([#3036](https://github.com/docling-project/docling/issues/3036)) ([`d276e60`](https://github.com/docling-project/docling/commit/d276e6056106b6aa04fee65def96d3e10557d632)) ### Fix * **xlsx:** Handle OneCellAnchor images in Excel backend ([#3045](https://github.com/docling-project/docling/issues/3045)) ([`859c302`](https://github.com/docling-project/docling/commit/859c302310289c5bab45a6e160e7cc3b9c538343)) * Normalize Unicode ligatures in PDF text extracti | Low | 3/2/2026 |
| v2.75.0 | ### Feature * Create a backend parser for XBRL instance reports ([#3017](https://github.com/docling-project/docling/issues/3017)) ([`334ba6e`](https://github.com/docling-project/docling/commit/334ba6e51fa7feb5f2ae15fce4612c7b3fad67d6)) * Unified model-family inference engines (including image-classification) and KServe v2 API support ([#2979](https://github.com/docling-project/docling/issues/2979)) ([`0353293`](https://github.com/docling-project/docling/commit/03532938b52fb1513e2ea3afffc6da6a7d | Low | 2/24/2026 |
| v2.74.0 | ### Feature * Introduce docling-parse v5 and deprecate old docling-parse backends ([#2872](https://github.com/docling-project/docling/issues/2872)) ([`bf417e6`](https://github.com/docling-project/docling/commit/bf417e6d264ebaf93bda7f53534e2cc50ccb2284)) ### Fix * Security vulnerabilities with XML External Entity and related attacks ([#3009](https://github.com/docling-project/docling/issues/3009)) ([`576bada`](https://github.com/docling-project/docling/commit/576bada7b7d542ea308778a053bc3c4d49 | Low | 2/17/2026 |
| v2.73.1 | ### Fix * **asciidoc:** Handle commas in image alt text ([#2983](https://github.com/docling-project/docling/issues/2983)) ([`86b6912`](https://github.com/docling-project/docling/commit/86b691204d2e4c2a54c99d80063e2dd5b5428168)) * Use timezone-aware datetime ([#2947](https://github.com/docling-project/docling/issues/2947)) ([`e2870f9`](https://github.com/docling-project/docling/commit/e2870f94ed78caeb6db9d735b5a73fa80e5e2104)) * Add failed pages to DoclingDocument for page break consistency ([#2 | Low | 2/13/2026 |
| v2.73.0 | ### Feature * Inference engines abstraction for object detection model family with HF Transformers and ONNX runtime ([#2959](https://github.com/docling-project/docling/issues/2959)) ([`14e474c`](https://github.com/docling-project/docling/commit/14e474c95555f04e5c4ac55351ad802d372858fc)) * Added support for parsing LaTeX (.tex) documents ([#2890](https://github.com/docling-project/docling/issues/2890)) ([`e6ccb8b`](https://github.com/docling-project/docling/commit/e6ccb8b2c1d99fa6e2660d7c4bb866a | Low | 2/11/2026 |
| v2.72.0 | ### Feature * Add chart extraction models ([#2848](https://github.com/docling-project/docling/issues/2848)) ([`fe45c71`](https://github.com/docling-project/docling/commit/fe45c71fe7ad137088e3719dc99e337860120d33)) ### Fix * **backend:** Improve Excel table bounds detection and flatten merged cells ([#2778](https://github.com/docling-project/docling/issues/2778)) ([`3110c43`](https://github.com/docling-project/docling/commit/3110c439da48fe215379492a29a310e64e9d67e7)) * **pptx:** Handle picture | Low | 2/3/2026 |
| v2.71.0 | ### Feature * Webvtt and source tracker ([#2787](https://github.com/docling-project/docling/issues/2787)) ([`0602a7c`](https://github.com/docling-project/docling/commit/0602a7cdab17b0e42057e1ef502048e95bd589f4)) * Add support for Word document comments extraction ([#2834](https://github.com/docling-project/docling/issues/2834)) ([`b6ca094`](https://github.com/docling-project/docling/commit/b6ca09451963c606b5d280b74e559278717bb911)) ### Fix * Allow newer typer versions ([#2930](https://github. | Low | 1/30/2026 |
| v2.70.0 | ### Feature * Drop support for Python 3.9 ([#2905](https://github.com/docling-project/docling/issues/2905)) ([`7f38658`](https://github.com/docling-project/docling/commit/7f386587ed9a28a839a928f3815d5ce1f3e05f8b)) ### Fix * **md:** Handle pipe symbols that are not table markers ([#2904](https://github.com/docling-project/docling/issues/2904)) ([`86eaef5`](https://github.com/docling-project/docling/commit/86eaef5b4544d638099657d38f18966ddd3e73f2)) * Remove direct vllm dependency ([#2910](https | Low | 1/23/2026 |
| v2.69.1 | ### Fix * Off-by-one error for page indexing in vlm_pipeline ([#2902](https://github.com/docling-project/docling/issues/2902)) ([`08f49e2`](https://github.com/docling-project/docling/commit/08f49e2abc74bfbc6be3433f64698c2b4ac7ddce)) | Low | 1/21/2026 |
| v2.69.0 | ### Feature * New picture classifier v2.0 ([#2889](https://github.com/docling-project/docling/issues/2889)) ([`43badc3`](https://github.com/docling-project/docling/commit/43badc3838ccfc98fd28d9d66ffe0811585f90fd)) * Add classification filters for picture description ([#2836](https://github.com/docling-project/docling/issues/2836)) ([`ac16a26`](https://github.com/docling-project/docling/commit/ac16a26a047ccf5edd88775197ca43d146d00528)) ### Fix * Torch compatibility for xpu ([#2894](https://git | Low | 1/20/2026 |
| v2.68.0 | ### Feature * Support for DeepSeek-OCR in VLM pipeline ([#2798](https://github.com/docling-project/docling/issues/2798)) ([`19af03f`](https://github.com/docling-project/docling/commit/19af03f539b40d88eedd132644ed085b572664d7)) ### Fix * **logging:** Include page numbers in preprocess error messages ([#2858](https://github.com/docling-project/docling/issues/2858)) ([`89bea24`](https://github.com/docling-project/docling/commit/89bea245392b840a0c25c5fc35c931477a34d881)) * **docx:** Handle groupe | Low | 1/13/2026 |
| v2.67.0 | ### Feature * Enrichment annotations in the new meta format ([#2859](https://github.com/docling-project/docling/issues/2859)) ([`aab3ff5`](https://github.com/docling-project/docling/commit/aab3ff5d82fc54864657c0c2ff8e0aa21461f23f)) * Add XPU device support for Intel GPUs ([#2809](https://github.com/docling-project/docling/issues/2809)) ([`2b83fdd`](https://github.com/docling-project/docling/commit/2b83fdd0deeec0f1ad016cc78ea42d3144a86cad)) * Add option to report timings details ([#2772](https:/ | Low | 1/9/2026 |
| v2.66.0 | ### Feature * Add preset for using granite-docling via vllm and other apis ([#2792](https://github.com/docling-project/docling/issues/2792)) ([`241d19e`](https://github.com/docling-project/docling/commit/241d19ed6f1b6d4327df250497ff8d8dd2686b5d)) ### Fix * **docx:** Handle tables with merged cells causing IndexError ([#2813](https://github.com/docling-project/docling/issues/2813)) ([`faff935`](https://github.com/docling-project/docling/commit/faff935b0e9f7a6f450b3bbc0329a05ac1b00ff2)) * **mar | Low | 12/24/2025 |
| v2.65.0 | ### Feature * Add YAML output format to CLI ([#2768](https://github.com/docling-project/docling/issues/2768)) ([`da7678a`](https://github.com/docling-project/docling/commit/da7678a754b62df5cf0a9a1efe98c288bda20bd7)) ### Fix * **rapidocr:** Use correct parameter name for rec_keys_path ([#2762](https://github.com/docling-project/docling/issues/2762)) ([`1d78418`](https://github.com/docling-project/docling/commit/1d78418cefb5b90691481fa92c35e8b4909b6de5)) * **docx:** Handle missing value in para | Low | 12/15/2025 |
| v2.64.1 | ### Fix * Clear word/char cells when force_full_page_ocr is used ([#2738](https://github.com/docling-project/docling/issues/2738)) ([`1df0560`](https://github.com/docling-project/docling/commit/1df0560ec2cafcd95f2240e6188385e1ec117110)) * Add missing font download in the rapidocr artifacts ([#2735](https://github.com/docling-project/docling/issues/2735)) ([`edbabfc`](https://github.com/docling-project/docling/commit/edbabfcac2fd53345b1a0677e81f206285d58bae)) * Ensure proper image_scale for gene | Low | 12/9/2025 |
| v2.64.0 | ### Feature * **experimental:** Add experimental TableCropsLayoutModel ([#2669](https://github.com/docling-project/docling/issues/2669)) ([`1344362`](https://github.com/docling-project/docling/commit/134436245a1ebdadbfd8ba3c870f0f3c866f39a7)) * Factory and plugin-capability for Layout and Table models ([#2637](https://github.com/docling-project/docling/issues/2637)) ([`ad97e52`](https://github.com/docling-project/docling/commit/ad97e5285126388847ba9a219ac73f006c759f09)) ### Fix * InputFormat. | Low | 12/2/2025 |
| v2.63.0 | ### Feature * Add save and load for conversion result ([#2648](https://github.com/docling-project/docling/issues/2648)) ([`b559813`](https://github.com/docling-project/docling/commit/b559813b9becf7950bc539c1334e55ef17bed2ad)) ### Fix * Respect document_timeout in new threaded StandardPdfPipeline ([#2653](https://github.com/docling-project/docling/issues/2653)) ([`2087c6b`](https://github.com/docling-project/docling/commit/2087c6bf9f65f279dd2ff0631768996aecd640fe)) * In DocumentConverter.conve | Low | 11/20/2025 |
| v2.62.0 | ### Feature * Add the Image backend ([#2627](https://github.com/docling-project/docling/issues/2627)) ([`3495b73`](https://github.com/docling-project/docling/commit/3495b73de875c2438108b4362dbac770b6d322ca)) * **experimental:** Layout + VLM model with layout prompt ([#2244](https://github.com/docling-project/docling/issues/2244)) ([`4852d8b`](https://github.com/docling-project/docling/commit/4852d8b4f2938434f1d6250984fa18ec5428055f)) ### Fix * Correct the model-repo name ([#2624](https://gith | Low | 11/17/2025 |
| v2.61.2 | ### Fix * Default to EasyOCR in Python 3.14 ([#2605](https://github.com/docling-project/docling/issues/2605)) ([`5c27567`](https://github.com/docling-project/docling/commit/5c27567c4160b6ec43857855c8d5cd3a58c031c5)) | Low | 11/10/2025 |
| v2.61.1 | ### Fix * **docx:** Slow table parsing ([#2553](https://github.com/docling-project/docling/issues/2553)) ([`ef623ff`](https://github.com/docling-project/docling/commit/ef623ffceefe40aa237e163b564310ed81296bcf)) * **html:** Slow table parsing ([#2582](https://github.com/docling-project/docling/issues/2582)) ([`0ba8d5d`](https://github.com/docling-project/docling/commit/0ba8d5d9e325390626268744f289458e91689b4b)) ### Documentation * Make navigation menus collapse and expand ([#2573](https://gith | Low | 11/6/2025 |
| v2.61.0 | ### Feature * **vlm:** Track generated tokens and stop reasons for VLM models ([#2543](https://github.com/docling-project/docling/issues/2543)) ([`6a04e27`](https://github.com/docling-project/docling/commit/6a04e273528691eb22a5708f1270d4c5fa8f5b7c)) ### Fix * Temporarily pin NuExtract to working revision ([#2588](https://github.com/docling-project/docling/issues/2588)) ([`fa92574`](https://github.com/docling-project/docling/commit/fa925741b6dc00c7bd2806c62cb75cb539649c9f)) * **ocr:** Use PSM | Low | 11/6/2025 |
| v2.60.1 | ### Fix * Extract response from api_image_request in picture description ([#2571](https://github.com/docling-project/docling/issues/2571)) ([`8360aa5`](https://github.com/docling-project/docling/commit/8360aa54492bc5b5e07fcd07b0b85284910f1a14)) | Low | 11/4/2025 |
| v2.60.0 | ### Feature * Use threading in the standard pipeline and move old behavior to legacy ([#2452](https://github.com/docling-project/docling/issues/2452)) ([`268d027`](https://github.com/docling-project/docling/commit/268d027c8f2abae7339b4c7d33642c3135c56e7a)) ### Fix * **pdf:** Threadsafe for pypdfium2 backend ([#2527](https://github.com/docling-project/docling/issues/2527)) ([`a51275d`](https://github.com/docling-project/docling/commit/a51275d08037a30ebaa07e33b0c4e82623791259)) ### Documentati | Low | 10/31/2025 |
| v2.59.0 | ### Feature * **vlm:** Add num_tokens as attribtue for VlmPrediction ([#2489](https://github.com/docling-project/docling/issues/2489)) ([`b6c892b`](https://github.com/docling-project/docling/commit/b6c892b505bf29a12ce7e8d9b4e88e1253440ebc)) * Support for Python 3.14 ([#2530](https://github.com/docling-project/docling/issues/2530)) ([`cdffb47`](https://github.com/docling-project/docling/commit/cdffb47b9a12da23489e345ea633786914776f7d)) ### Fix * Xlsx cell parsing, now returning values instead | Low | 10/30/2025 |
| v2.58.0 | ### Feature * **pdf:** Support for password-protected PDF documents ([#2499](https://github.com/docling-project/docling/issues/2499)) ([`bbe82a6`](https://github.com/docling-project/docling/commit/bbe82a68d08e5dc33191524bb636f06112edff87)) * **backend:** Add generic options support and HTML image handling modes ([#2011](https://github.com/docling-project/docling/issues/2011)) ([`a30e6a7`](https://github.com/docling-project/docling/commit/a30e6a76148079cc48fb179e4b9ca36371026b6f)) * **ASR:** MLX | Low | 10/22/2025 |
| v2.57.0 | ### Feature * **docx:** Process drawingml objects in docx ([#2453](https://github.com/docling-project/docling/issues/2453)) ([`1682993`](https://github.com/docling-project/docling/commit/16829939cf1f8d89974c51c1d7c5cdc2fe8045da)) ### Fix * Use proper page concatentation in VLM pipeline MD/HTML conversion ([#2458](https://github.com/docling-project/docling/issues/2458)) ([`cd7f7ba`](https://github.com/docling-project/docling/commit/cd7f7ba145c401fb6567ef1c7337c840100cded1)) ### Documentation | Low | 10/15/2025 |
| v2.56.1 | ### Fix * Avoid downloading easyocr models by default ([#2454](https://github.com/docling-project/docling/issues/2454)) ([`688a7df`](https://github.com/docling-project/docling/commit/688a7dfd38ba3e3aea64f7fe027815e910818785)) | Low | 10/13/2025 |
| v2.56.0 | ### Feature * AutoOCR model selecting the best OCR model available and deprecating the usage of EasyOCR ([#2391](https://github.com/docling-project/docling/issues/2391)) ([`f7244a4`](https://github.com/docling-project/docling/commit/f7244a433378327576e3554d41d80928ee38e2a7)) * Add Tesseract PSM options support ([#2411](https://github.com/docling-project/docling/issues/2411)) ([`f11f8c0`](https://github.com/docling-project/docling/commit/f11f8c0a8188f99179acd7e47a48b908b1ea64d0)) ### Fix * **a | Low | 10/13/2025 |
| v2.55.1 | ### Fix * **markdown:** Setext heading support ([#2359](https://github.com/docling-project/docling/issues/2359)) ([`ee73ffa`](https://github.com/docling-project/docling/commit/ee73ffae15b2bb60c42e333fca4684bd57eeff31)) * **docs:** Fixed the color scheme ([#2371](https://github.com/docling-project/docling/issues/2371)) ([`246de77`](https://github.com/docling-project/docling/commit/246de77d8ce53fbeb7a93a6412c461df82269685)) * Empty table handling ([#2365](https://github.com/docling-project/doclin | Low | 10/3/2025 |
| v2.55.0 | ### Feature * Repetition-based StoppingCriteria for GraniteDocling ([#2323](https://github.com/docling-project/docling/issues/2323)) ([`1e9dc43`](https://github.com/docling-project/docling/commit/1e9dc43b722aeffa4574ae2a87bae1eb180c1201)) * Rich tables support for HTML backend ([#2324](https://github.com/docling-project/docling/issues/2324)) ([`c803abe`](https://github.com/docling-project/docling/commit/c803abed9ae98489184791a70bf49cac0c83ab89)) ### Fix * Pin wider range of typer ([#2309](htt | Low | 9/30/2025 |
| v2.54.0 | ### Feature * Rich tables for MSWord backend ([#2291](https://github.com/docling-project/docling/issues/2291)) ([`e2482a2`](https://github.com/docling-project/docling/commit/e2482a2ada52b2b8a41c4402b27e125adbe4385f)) * Add a backend parser for WebVTT files ([#2288](https://github.com/docling-project/docling/issues/2288)) ([`46efaae`](https://github.com/docling-project/docling/commit/46efaaefee17a6b83e02a050f9f3c8a51afbbd53)) ### Fix * Correct y-axis scaling in draw_table_cells ([#2287](https: | Low | 9/22/2025 |
| v2.53.0 | ### Feature * Add granite-docling model ([#2272](https://github.com/docling-project/docling/issues/2272)) ([`17afb66`](https://github.com/docling-project/docling/commit/17afb664d005168b5a6f12a2df4432076a9329bb)) * **RapidOcr:** Support generic extra arguments for RapidOcr ([#2266](https://github.com/docling-project/docling/issues/2266)) ([`0e95171`](https://github.com/docling-project/docling/commit/0e95171dd64733ba52f2f0906642be24f6237977)) ### Fix * Handle empty result from RapidOCR to avoid | Low | 9/17/2025 |
| v2.52.0 | ### Feature * Enrichment steps on all convert pipelines (incl docx, html, etc) ([#2251](https://github.com/docling-project/docling/issues/2251)) ([`2c91234`](https://github.com/docling-project/docling/commit/2c9123419f541feda8cc98c53aeb37288fabcaee)) ### Fix * Add missing features in ThreadedStandardPdfPipeline ([#2252](https://github.com/docling-project/docling/issues/2252)) ([`0700af2`](https://github.com/docling-project/docling/commit/0700af212cce8d90dbe0477dcb06d69370649e97)) * Address de | Low | 9/11/2025 |
| v2.51.0 | ### Feature * Updating default parameters to get better performance with docling-parse ([#2208](https://github.com/docling-project/docling/issues/2208)) ([`b49d1ad`](https://github.com/docling-project/docling/commit/b49d1ad4f1af6eeadc3f8d0e35123dc52c6e228e)) * Updated the backend for new docling-parse ([#2187](https://github.com/docling-project/docling/issues/2187)) ([`b3d7542`](https://github.com/docling-project/docling/commit/b3d754206172d08d6d01f29f132dcb66383f955b)) ### Documentation * Ad | Low | 9/5/2025 |
| v2.50.0 | ### Feature * Heron layout model as new default ([#1971](https://github.com/docling-project/docling/issues/1971)) ([`e38aa0f`](https://github.com/docling-project/docling/commit/e38aa0f7f2e8a7881c0f97131bf776556778f9a2)) ### Fix * **html:** Access to variable not yet declared ([#2171](https://github.com/docling-project/docling/issues/2171)) ([`293e81b`](https://github.com/docling-project/docling/commit/293e81bf9d341edd1d35f3b66faf726b82ad4885)) | Low | 9/3/2025 |
| v2.49.0 | ### Feature * [Beta] Extraction with schema ([#2138](https://github.com/docling-project/docling/issues/2138)) ([`9f4bc5b`](https://github.com/docling-project/docling/commit/9f4bc5b2f19d700208b0b233c88fbe960758bdbd)) * **msexcel:** Set ContentLayer.INVISIBLE for invisible sheet ([#1876](https://github.com/docling-project/docling/issues/1876)) ([`a283ccf`](https://github.com/docling-project/docling/commit/a283ccff25a25ebbe6e9b2decfaaad6f300597db)) ### Fix * **pypdfium2:** Fix OCR bounding box m | Low | 9/1/2025 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
pdf2imageA wrapper around the pdftoppm and pdftocairo command line tools to convert PDF to a PIL Image list.1.17.0
More from pypi
markitdownUtility tool for converting various files to Markdown
fastapiFastAPI framework, high performance, easy to learn, fast to code, ready for production
djangoA high-level Python web framework that encourages rapid development and clean, pragmatic design.
flaskA simple framework for building complex web applications.
More in Frameworks
langchainThe agent engineering platform
deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
tqdmFast, Extensible Progress Meter
simBuild, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.