[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10682":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":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":44,"lastSyncTime":45,"discoverSource":46},10682,"snips-nlu","snipsco\u002Fsnips-nlu","snipsco","Snips Python library to extract meaning from text","https:\u002F\u002Fsnips-nlu.readthedocs.io",null,"Python",3971,503,129,65,0,1,3,30.11,"Apache License 2.0",false,"master",true,[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"bot","chatbot","information-extraction","intent-classification","intent-parser","machine-learning","machine-learning-library","ml","named-entity-recognition","ner","nlp","nlu","python","slot-filling","snips","text-classification","2026-06-12 02:02:25","Snips NLU\n=========\n\n.. image:: https:\u002F\u002Ftravis-ci.org\u002Fsnipsco\u002Fsnips-nlu.svg?branch=master\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fsnipsco\u002Fsnips-nlu\n\n.. image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002Fgithub\u002Fsnipsco\u002Fsnips-nlu?branch=master&svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fsnipsco\u002Fsnips-nlu\n\n.. image:: https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsnips-nlu.svg?branch=master\n   :target: https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Fsnips-nlu\n\n.. image:: https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fsnips-nlu.svg?branch=master\n   :target: https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Fsnips-nlu\n\n.. image:: https:\u002F\u002Fcodecov.io\u002Fgh\u002Fsnipsco\u002Fsnips-nlu\u002Fbranch\u002Fmaster\u002Fgraph\u002Fbadge.svg\n   :target: https:\u002F\u002Fcodecov.io\u002Fgh\u002Fsnipsco\u002Fsnips-nlu\n\n.. image:: https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl\u002Fhttp\u002Fshields.io.svg?style=social\n   :target: https:\u002F\u002Ftwitter.com\u002Fintent\u002Ftweet?text=Extract%20meaning%20from%20text%20with%20Snips%20NLU,%20an%20open%20source%20library%20written%20in%20python%20and%20rust&url=https:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fsnips-nlu&via=snips&hashtags=nlu,nlp,machinelearning,python,rustlang\n\n\n`Snips NLU \u003Chttps:\u002F\u002Fsnips-nlu.readthedocs.io>`_ (Natural Language Understanding) is a Python library that allows to extract structured information from sentences written in natural language.\n\nSummary\n-------\n\n- `What is Snips NLU about ?`_\n- `Getting Started`_\n\n  - `System requirements`_\n  - `Installation`_\n  - `Language Resources`_\n- `API Usage`_\n\n  - `Sample code`_\n  - `Command Line Interface`_\n- `Sample datasets`_\n- `Benchmarks`_\n- `Documentation`_\n- `Citing Snips NLU`_\n- `FAQ & Community`_\n- `Related content`_\n- `How do I contribute ?`_\n- `Licence`_\n\nWhat is Snips NLU about ?\n-------------------------\n\nBehind every chatbot and voice assistant lies a common piece of technology: Natural Language Understanding (NLU). Anytime a user interacts with an AI using natural language, their words need to be translated into a machine-readable description of what they meant.\n\nThe NLU engine first detects what the intention of the user is (a.k.a. `intent`_), then extracts the parameters (called `slots`_) of the query. The developer can then use this to determine the appropriate action or response.\n\n\nLet’s take an example to illustrate this, and consider the following sentence:\n\n.. code-block:: text\n\n    \"What will be the weather in paris at 9pm?\"\n\nProperly trained, the Snips NLU engine will be able to extract structured data such as:\n\n.. code-block:: json\n\n    {\n       \"intent\": {\n          \"intentName\": \"searchWeatherForecast\",\n          \"probability\": 0.95\n       },\n       \"slots\": [\n          {\n             \"value\": \"paris\",\n             \"entity\": \"locality\",\n             \"slotName\": \"forecast_locality\"\n          },\n          {\n             \"value\": {\n                \"kind\": \"InstantTime\",\n                \"value\": \"2018-02-08 20:00:00 +00:00\"\n             },\n             \"entity\": \"snips\u002Fdatetime\",\n             \"slotName\": \"forecast_start_datetime\"\n          }\n       ]\n    }\n\nIn this case, the identified intent is ``searchWeatherForecast`` and two slots were extracted, a locality and a datetime. As you can see, Snips NLU does an extra step on top of extracting entities: it resolves them. The extracted datetime value has indeed been converted into a handy ISO format.\n\nCheck out our `blog post`_ to get more details about why we built Snips NLU and how it works under the hood. We also published a `paper on arxiv`_, presenting the machine learning architecture of the Snips Voice Platform.\n\n\nGetting Started\n---------------\n\n-------------------\nSystem requirements\n-------------------\n\n- Python 2.7 or Python >= 3.5\n- RAM: Snips NLU will typically use between 100MB and 200MB of RAM, depending on the language and the size of the dataset.\n\n\n------------\nInstallation\n------------\n\n.. code-block:: python\n\n    pip install snips-nlu\n\nWe currently have pre-built binaries (wheels) for ``snips-nlu`` and its\ndependencies for MacOS (10.11 and later), Linux x86_64 and Windows.\n\nFor any other architecture\u002Fos `snips-nlu` can be installed from the source\ndistribution. To do so, `Rust \u003Chttps:\u002F\u002Fwww.rust-lang.org\u002Fen-US\u002Finstall.html>`_\nand `setuptools_rust \u003Chttps:\u002F\u002Fgithub.com\u002FPyO3\u002Fsetuptools-rust>`_ must be\ninstalled before running the ``pip install snips-nlu`` command.\n\n------------------\nLanguage resources\n------------------\n\nSnips NLU relies on `external language resources`_ that must be downloaded before the\nlibrary can be used. You can fetch resources for a specific language by\nrunning the following command:\n\n.. code-block:: sh\n\n    python -m snips_nlu download en\n\nOr simply:\n\n.. code-block:: sh\n\n    snips-nlu download en\n\n\nThe list of supported languages is available at \n`this address \u003Chttps:\u002F\u002Fsnips-nlu.readthedocs.io\u002Fen\u002Flatest\u002Flanguages.html>`_.\n\nAPI Usage\n---------\n\n----------------------\nCommand Line Interface\n----------------------\n\nThe easiest way to test the abilities of this library is through the command line interface.\n\nFirst, start by training the NLU with one of the `sample datasets`_:\n\n.. code-block:: sh\n    \n    snips-nlu train path\u002Fto\u002Fdataset.json path\u002Fto\u002Foutput_trained_engine\n\nWhere ``path\u002Fto\u002Fdataset.json`` is the path to the dataset which will be used during training, and ``path\u002Fto\u002Foutput_trained_engine`` is the location where the trained engine should be persisted once the training is done.\n\nAfter that, you can start parsing sentences interactively by running:\n\n.. code-block:: sh\n    \n    snips-nlu parse path\u002Fto\u002Ftrained_engine\n\nWhere ``path\u002Fto\u002Ftrained_engine`` corresponds to the location where you have stored the trained engine during the previous step.\n\n\n-----------\nSample code\n-----------\n\nHere is a sample code that you can run on your machine after having\ninstalled `snips-nlu`, fetched the english resources and downloaded one of the `sample datasets`_:\n\n.. code-block:: python\n\n    >>> from __future__ import unicode_literals, print_function\n    >>> import io\n    >>> import json\n    >>> from snips_nlu import SnipsNLUEngine\n    >>> from snips_nlu.default_configs import CONFIG_EN\n    >>> with io.open(\"sample_datasets\u002Flights_dataset.json\") as f:\n    ...     sample_dataset = json.load(f)\n    >>> nlu_engine = SnipsNLUEngine(config=CONFIG_EN)\n    >>> nlu_engine = nlu_engine.fit(sample_dataset)\n    >>> text = \"Please turn the light on in the kitchen\"\n    >>> parsing = nlu_engine.parse(text)\n    >>> parsing[\"intent\"][\"intentName\"]\n    'turnLightOn'\n\n\nWhat it does is training an NLU engine on a sample weather dataset and parsing\na weather query.\n\nSample datasets\n---------------\n\nHere is a list of some datasets that can be used to train a Snips NLU engine:\n\n- `Lights dataset \u003Csample_datasets\u002Flights_dataset.json>`_: \"Turn on the lights in the kitchen\", \"Set the light to red in the bedroom\"\n- `Beverage dataset \u003Csample_datasets\u002Fbeverage_dataset.json>`_: \"Prepare two cups of cappucino\", \"Make me a cup of tea\"\n- `Flights dataset \u003Csample_datasets\u002Fflights_dataset.json>`_: \"Book me a flight to go to boston this weekend\", \"book me some tickets from istanbul to moscow in three days\"\n\nBenchmarks\n----------\n\nIn January 2018, we reproduced an `academic benchmark`_ which was published during the summer 2017. In this article, authors assessed the performance of API.ai (now Dialogflow, Google), Luis.ai (Microsoft), IBM Watson, and `Rasa NLU`_. For fairness, we used an updated version of Rasa NLU and compared it to the latest version of Snips NLU (both in dark blue).\n\n.. image:: .img\u002Fbenchmarks.png\n\nIn the figure above, `F1 scores`_ of both intent classification and slot filling were computed for several NLU providers, and averaged across the three datasets used in the academic benchmark mentionned before. All the underlying results can be found `here \u003Chttps:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fnlu-benchmark\u002Ftree\u002Fmaster\u002F2018-01-Braum-et-al-extension>`_.\n\n\nDocumentation\n-------------\n\nTo find out how to use Snips NLU please refer to the `package documentation \u003Chttps:\u002F\u002Fsnips-nlu.readthedocs.io>`_, it will provide you with a step-by-step guide on how to setup and use this library.\n\nCiting Snips NLU\n----------------\n\nPlease cite the following paper when using Snips NLU:\n\n.. code-block:: bibtex\n\n   @article{coucke2018snips,\n     title   = {Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces},\n     author  = {Coucke, Alice and Saade, Alaa and Ball, Adrien and Bluche, Th{\\'e}odore and Caulier, Alexandre and Leroy, David and Doumouro, Cl{\\'e}ment and Gisselbrecht, Thibault and Caltagirone, Francesco and Lavril, Thibaut and others},\n     journal = {arXiv preprint arXiv:1805.10190},\n     pages   = {12--16},\n     year    = {2018}\n   }\n\nFAQ & Community\n---------------\n\nPlease join the `forum`_ to ask your questions and get feedback from the community.\n\nRelated content\n---------------\n* `What is Snips about ? \u003Chttps:\u002F\u002Fsnips.ai\u002F>`_\n* Snips NLU Open sourcing `blog post`_\n* `Snips Voice Platform paper (arxiv) \u003Chttps:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10190>`_\n* `Snips NLU Language Resources \u003Chttps:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fsnips-nlu-language-resources>`_\n* `Bug tracker \u003Chttps:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fsnips-nlu\u002Fissues>`_\n* `Snips NLU Rust \u003Chttps:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fsnips-nlu-rs>`_: Rust inference pipeline implementation and bindings (C, Swift, Kotlin, Python)\n* `Rustling \u003Chttps:\u002F\u002Fgithub.com\u002Fsnipsco\u002Frustling-ontology>`_: Snips NLU builtin entities parser\n\n\nHow do I contribute ?\n---------------------\n\nPlease see the `Contribution Guidelines \u003CCONTRIBUTING.rst>`_.\n\nLicence\n-------\n\nThis library is provided by `Snips \u003Chttps:\u002F\u002Fwww.snips.ai>`_ as Open Source software. See `LICENSE \u003CLICENSE>`_ for more information.\n\n\nGeonames Licence\n----------------\n\nThe `snips\u002Fcity`, `snips\u002Fcountry` and `snips\u002Fregion` builtin entities rely on\nsoftware from Geonames, which is made available under a Creative Commons Attribution 4.0\nlicense international. For the license and warranties for Geonames please refer to: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002Flegalcode.\n\n\n.. _external language resources: https:\u002F\u002Fgithub.com\u002Fsnipsco\u002Fsnips-nlu-language-resources\n.. _forum: https:\u002F\u002Fforum.snips.ai\u002F\n.. _blog post: https:\u002F\u002Fmedium.com\u002Fsnips-ai\u002Fan-introduction-to-snips-nlu-the-open-source-library-behind-snips-embedded-voice-platform-b12b1a60a41a\n.. _paper on arxiv: https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.10190\n.. _academic benchmark: http:\u002F\u002Fworkshop.colips.org\u002Fwochat\u002F@sigdial2017\u002Fdocuments\u002FSIGDIAL22.pdf\n.. _Rasa NLU: https:\u002F\u002Fnlu.rasa.ai\u002F\n.. _F1 scores: https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FF1_score\n.. _intent: https:\u002F\u002Fsnips-nlu.readthedocs.io\u002Fen\u002Flatest\u002Fdata_model.html#intent\n.. _slots: https:\u002F\u002Fsnips-nlu.readthedocs.io\u002Fen\u002Flatest\u002Fdata_model.html#slot\n","Snips NLU 是一个Python库，用于从自然语言文本中提取结构化信息。其核心功能包括意图识别和实体抽取，能够将用户的自然语言转化为机器可读的意图和参数（槽位）。该库采用了机器学习技术，并且支持多种语言处理任务，如命名实体识别、意图分类等。适用于构建聊天机器人、语音助手以及其他需要理解自然语言的应用场景。",2,"2026-06-11 03:29:42","top_topic"]