[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9621":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":47,"readmeContent":48,"aiSummary":49,"trendingCount":16,"starSnapshotCount":16,"syncStatus":50,"lastSyncTime":51,"discoverSource":52},9621,"unstructured","Unstructured-IO\u002Funstructured","Unstructured-IO","Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models.  Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.","https:\u002F\u002Fwww.unstructured.io\u002F",null,"HTML",14888,1252,72,181,0,6,55,208,43,111.29,"Apache License 2.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"data-pipelines","deep-learning","document-image-analysis","document-image-processing","document-parser","document-parsing","docx","donut","information-retrieval","langchain","llm","machine-learning","ml","natural-language-processing","nlp","ocr","pdf","pdf-to-json","pdf-to-text","preprocessing","2026-06-12 04:00:46","\u003Ch3 align=\"center\">\n  \u003Cimg\n    src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FUnstructured-IO\u002Funstructured\u002Fmain\u002Fimg\u002Funstructured_logo.png\"\n    height=\"200\"\n  >\n\u003C\u002Fh3>\n\n\u003Cdiv align=\"center\">\n\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured\u002Fblob\u002Fmain\u002FLICENSE.md\">![https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Funstructured\u002F](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fl\u002Funstructured.svg)\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Funstructured\u002F\">![https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Funstructured\u002F](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Funstructured.svg)\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002FGitHub.com\u002Funstructured-io\u002Funstructured\u002Fgraphs\u002Fcontributors\">![https:\u002F\u002FGitHub.com\u002Funstructured-io\u002Funstructured.js\u002Fgraphs\u002Fcontributors](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Funstructured-io\u002Funstructured)\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured\u002Fblob\u002Fmain\u002FCODE_OF_CONDUCT.md\">![code_of_conduct.md](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContributor%20Covenant-2.1-4baaaa.svg) \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002FGitHub.com\u002Funstructured-io\u002Funstructured\u002Freleases\">![https:\u002F\u002FGitHub.com\u002Funstructured-io\u002Funstructured.js\u002Freleases](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease\u002Funstructured-io\u002Funstructured)\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Funstructured\u002F\">![https:\u002F\u002Fgithub.com\u002FNaereen\u002Fbadges\u002F](https:\u002F\u002Fbadgen.net\u002Fbadge\u002FOpen%20Source%20%3F\u002FYes%21\u002Fblue?icon=github)\u003C\u002Fa>\n  [![Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Funstructured)](https:\u002F\u002Fpepy.tech\u002Fproject\u002Funstructured)\n  [![Downloads](https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Funstructured\u002Fmonth)](https:\u002F\u002Fpepy.tech\u002Fproject\u002Funstructured)\n  \u003Ca\n   href=\"https:\u002F\u002Fwww.phorm.ai\u002Fquery?projectId=34efc517-2201-4376-af43-40c4b9da3dc5\">\n\t\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPhorm-Ask_AI-%23F2777A.svg?&logo=data:image\u002Fsvg+xml;base64,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\" \u002F>\n   \u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n\u003Cdiv>\n  \u003Cp align=\"center\">\n  \u003Ca\n  href=\"https:\u002F\u002Fshort.unstructured.io\u002Fpzw05l7\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FJOIN US ON SLACK-4A154B?style=for-the-badge&logo=slack&logoColor=white\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Funstructuredio\u002F\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Ch2 align=\"center\">\n  \u003Cp>Open-Source Pre-Processing Tools for Unstructured Data\u003C\u002Fp>\n\u003C\u002Fh2>\n\nThe `unstructured` library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and [many more](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fcore-functionality\u002Fpartitioning). The use cases of `unstructured` revolve around streamlining and optimizing the data processing workflow for LLMs. `unstructured` modular functions and connectors form a cohesive system that simplifies data ingestion and pre-processing, making it adaptable to different platforms and efficient in transforming unstructured data into structured outputs.\n\n## Try the Unstructured Platform Product\n\nReady to move your data processing pipeline to production, and take advantage of advanced features? Check out [Unstructured Platform](https:\u002F\u002Funstructured.io\u002Fenterprise). In addition to better processing performance, take advantage of chunking, embedding, and image and table enrichment generation, all from a low code UI or an API. [Request a demo](https:\u002F\u002Funstructured.io\u002Fcontact) from our sales team to learn more about how to get started.\n\n## :eight_pointed_black_star: Quick Start\n\nThere are several ways to use the `unstructured` library:\n* [Run the library in a container](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured#run-the-library-in-a-container) or\n* Install the library\n    1. [Install from PyPI](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured#installing-the-library)\n    2. [Install for local development](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured#installation-instructions-for-local-development)\n* For installation with `conda` on Windows system, please refer to the [documentation](https:\u002F\u002Funstructured-io.github.io\u002Funstructured\u002Finstalling.html#installation-with-conda-on-windows)\n\n### Run the library in a container\n\nThe following instructions are intended to help you get up and running using Docker to interact with `unstructured`.\nSee [here](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F) if you don't already have docker installed on your machine.\n\nNOTE: we build multi-platform images to support both x86_64 and Apple silicon hardware. `docker pull` should download the corresponding image for your architecture, but you can specify with `--platform` (e.g. `--platform linux\u002Famd64`) if needed.\n\nWe build Docker images for all pushes to `main`. We tag each image with the corresponding short commit hash (e.g. `fbc7a69`) and the application version (e.g. `0.5.5-dev1`). We also tag the most recent image with `latest`. To leverage this, `docker pull` from our image repository.\n\n```bash\ndocker pull downloads.unstructured.io\u002Funstructured-io\u002Funstructured:latest\n```\n\nOnce pulled, you can create a container from this image and shell to it.\n\n```bash\n# create the container\ndocker run -dt --name unstructured downloads.unstructured.io\u002Funstructured-io\u002Funstructured:latest\n\n# this will drop you into a bash shell where the Docker image is running\ndocker exec -it unstructured bash\n```\n\nYou can also build your own Docker image. Note that the base image is `wolfi-base`, which is\nupdated regularly. If you are building the image locally, it is possible `docker-build` could\nfail due to upstream changes in `wolfi-base`.\n\nIf you only plan on parsing one type of data you can speed up building the image by commenting out some\nof the packages\u002Frequirements necessary for other data types. See Dockerfile to know which lines are necessary\nfor your use case.\n\n```bash\nmake docker-build\n\n# this will drop you into a bash shell where the Docker image is running\nmake docker-start-bash\n```\n\nOnce in the running container, you can try things directly in Python interpreter's interactive mode.\n```bash\n# this will drop you into a python console so you can run the below partition functions\npython3\n\n>>> from unstructured.partition.pdf import partition_pdf\n>>> elements = partition_pdf(filename=\"example-docs\u002Flayout-parser-paper-fast.pdf\")\n\n>>> from unstructured.partition.text import partition_text\n>>> elements = partition_text(filename=\"example-docs\u002Ffake-text.txt\")\n```\n\n### Installing the library\nUse the following instructions to get up and running with `unstructured` and test your\ninstallation.\n\n- Install the Python SDK to support all document types with `pip install \"unstructured[all-docs]\"`\n  - For plain text files, HTML, XML, JSON and Emails that do not require any extra dependencies, you can run `pip install unstructured`\n  - To process other doc types, you can install the extras required for those documents, such as `pip install \"unstructured[docx,pptx]\"`\n- Install the following system dependencies if they are not already available on your system.\n  Depending on what document types you're parsing, you may not need all of these.\n    - `libmagic-dev` (filetype detection)\n    - `poppler-utils` (images and PDFs)\n    - `tesseract-ocr` (images and PDFs, install `tesseract-lang` for additional language support)\n    - `libreoffice` (MS Office docs)\n    - `pandoc` is bundled automatically via the `pypandoc-binary` Python package (no system install needed)\n\n- For suggestions on how to install on the Windows and to learn about dependencies for other features, see the\n  installation documentation [here](https:\u002F\u002Funstructured-io.github.io\u002Funstructured\u002Finstalling.html).\n\nAt this point, you should be able to run the following code:\n\n```python\nfrom unstructured.partition.auto import partition\n\nelements = partition(filename=\"example-docs\u002Feml\u002Ffake-email.eml\")\nprint(\"\\n\\n\".join([str(el) for el in elements]))\n```\n\n### Installation Instructions for Local Development\n\nThe following instructions are intended to help you get up and running with `unstructured`\nlocally if you are planning to contribute to the project.\n\nThis project uses [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) for dependency management. Install it first:\n\n```bash\n# macOS \u002F Linux\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n```\n\nThen install all dependencies (base, extras, dev, test, and lint groups):\n\n```bash\nmake install\n```\n\nThis runs `uv sync --locked --all-extras --all-groups`, which creates a virtual environment\nand installs everything in one step. No need to manually create or activate a virtualenv.\n\nTo install only specific document-type extras:\n\n```bash\nuv sync --extra pdf\nuv sync --extra csv --extra docx\n```\n\nTo update the lock file after changing dependencies in `pyproject.toml`:\n\n```bash\nmake lock\n```\n\n* Optional:\n  * To install extras for processing images and PDFs locally, run `uv sync --extra pdf --extra image`.\n  * For processing image files, `tesseract` is required. See [here](https:\u002F\u002Ftesseract-ocr.github.io\u002Ftessdoc\u002FInstallation.html) for installation instructions.\n  * For processing PDF files, `tesseract` and `poppler` are required. The [pdf2image docs](https:\u002F\u002Fpdf2image.readthedocs.io\u002Fen\u002Flatest\u002Finstallation.html) have instructions on installing `poppler` across various platforms.\n\nAdditionally, if you're planning to contribute to `unstructured`, we provide you an optional `pre-commit` configuration\nfile to ensure your code matches the formatting and linting standards used in `unstructured`.\nIf you'd prefer not to have code changes auto-tidied before every commit, you can use  `make check` to see\nwhether any linting or formatting changes should be applied, and `make tidy` to apply them.\n\nIf using the optional `pre-commit`, you'll just need to install the hooks with `pre-commit install` since the\n`pre-commit` package is installed as part of `make install` mentioned above. Finally, if you decided to use `pre-commit`\nyou can also uninstall the hooks with `pre-commit uninstall`.\n\nIn addition to develop in your local OS we also provide a helper to use docker providing a development environment:\n\n```bash\nmake docker-start-dev\n```\n\nThis starts a docker container with your local repo mounted to `\u002Fmnt\u002Flocal_unstructured`. This docker image allows you to develop without worrying about your OS's compatibility with the repo and its dependencies.\n\n## :clap: Quick Tour\n\n### Documentation\nFor more comprehensive documentation, visit https:\u002F\u002Fdocs.unstructured.io . You can also learn\nmore about our other products on the documentation page, including our SaaS API.\n\nHere are a few pages from the [Open Source documentation page](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fintroduction\u002Foverview)\nthat are helpful for new users to review:\n\n- [Quick Start](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fintroduction\u002Fquick-start)\n- [Using the `unstructured` open source package](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fcore-functionality\u002Foverview)\n- [Connectors](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fingest\u002Foverview)\n- [Concepts](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fconcepts\u002Fdocument-elements)\n- [Integrations](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fintegrations)\n\n\n### PDF Document Parsing Example\nThe following examples show how to get started with the `unstructured` library. The easiest way to parse a document in unstructured is to use the `partition` function. If you use `partition` function, `unstructured` will detect the file type and route it to the appropriate file-specific partitioning function. If you are using the `partition` function, you may need to install additional dependencies per doc type.\nFor example, to install docx dependencies you need to run `pip install \"unstructured[docx]\"`.\nSee our  [installation guide](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Finstallation\u002Ffull-installation) for more details.\n\n```python\nfrom unstructured.partition.auto import partition\n\nelements = partition(\"example-docs\u002Flayout-parser-paper.pdf\")\n```\n\nRun `print(\"\\n\\n\".join([str(el) for el in elements]))` to get a string representation of the\noutput, which looks like:\n\n```\n\nLayoutParser : A Unified Toolkit for Deep Learning Based Document Image Analysis\n\nZejiang Shen 1 ( (cid:0) ), Ruochen Zhang 2 , Melissa Dell 3 , Benjamin Charles Germain Lee 4 , Jacob Carlson 3 , and\nWeining Li 5\n\nAbstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural\nnetworks. Ideally, research outcomes could be easily deployed in production and extended for further investigation.\nHowever, various factors like loosely organized codebases and sophisticated model configurations complicate the easy\nreuse of important innovations by a wide audience. Though there have been ongoing efforts to improve reusability and\nsimplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none\nof them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA\nis central to academic research across a wide range of disciplines in the social sciences and humanities. This paper\nintroduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications.\nThe core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models\nfor layout detection, character recognition, and many other document processing tasks. To promote extensibility,\nLayoutParser also incorporates a community platform for sharing both pre-trained models and full document digitization\npipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in\nreal-word use cases. The library is publicly available at https:\u002F\u002Flayout-parser.github.io\n\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis · Character Recognition · Open Source library ·\nToolkit.\n\nIntroduction\n\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks\nincluding document image classification [11,\n```\n\nSee the [partitioning](https:\u002F\u002Fdocs.unstructured.io\u002Fopen-source\u002Fcore-functionality\u002Fpartitioning)\nsection in our documentation for a full list of options and instructions on how to use\nfile-specific partitioning functions.\n\n## :guardsman: Security Policy\n\nSee our [security policy](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured\u002Fsecurity\u002Fpolicy) for\ninformation on how to report security vulnerabilities.\n\n## :bug: Reporting Bugs\n\nEncountered a bug? Please create a new [GitHub issue](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured\u002Fissues\u002Fnew\u002Fchoose) and use our bug report template to describe the problem. To help us diagnose the issue, use the `python scripts\u002Fcollect_env.py` command to gather your system's environment information and include it in your report. Your assistance helps us continuously improve our software - thank you!\n\n## :books: Learn more\n\n| Section | Description |\n|-|-|\n| [Company Website](https:\u002F\u002Funstructured.io) | Unstructured.io product and company info |\n| [Documentation](https:\u002F\u002Fdocs.unstructured.io\u002F) | Full API documentation |\n| [Batch Processing](https:\u002F\u002Fgithub.com\u002FUnstructured-IO\u002Funstructured-ingest) | Ingesting batches of documents through Unstructured |\n\n## :chart_with_upwards_trend: Analytics\n\nTelemetry is **off by default**. To opt in, set `UNSTRUCTURED_TELEMETRY_ENABLED=true` (or `=1`) before importing `unstructured`. To opt out, set `DO_NOT_TRACK` or `SCARF_NO_ANALYTICS` to any non-empty value (e.g. `true`, `1`, `yes`, `false`, `0`—any non-empty string opts out); opt-out takes precedence. Unset the variable or leave it empty if you do not want to opt out. See our [Privacy Policy](https:\u002F\u002Funstructured.io\u002Fprivacy-policy).\n","Unstructured 是一个开源ETL解决方案，旨在将复杂的文档转换为结构化数据，以便于语言模型使用。它支持多种文件格式（如PDF、DOCX等）的解析，并通过OCR技术处理图像中的文本信息。该工具具备强大的预处理能力，包括但不限于文档分割、内容丰富化和嵌入生成等功能，适用于需要从非结构化数据中提取有价值信息的各种场景，如企业级数据流水线建设、深度学习项目的数据准备阶段等。",2,"2026-06-11 03:23:49","top_topic"]