{ "info": { "author": "Jay Yip", "author_email": "junpang.yip@gmail.com", "bugtrack_url": null, "classifiers": [ "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3.6", "Topic :: Scientific/Engineering :: Artificial Intelligence" ], "description": "\n# bert-multitask-as-service\n\nA serving service for [bert-multitask-learning](https://github.com/JayYip/bert-multitask-learning)\n\n## Install\n\n```bash\npip install bert-multitask-server\npip install bert-multitask-client\n```\n\n## Getting Started\n\n1. Train and export model.\n\n A typical trained checkpoint dir looks like below.\n\n ```text\n bert_serving_ckpt/\n \u251c\u2500\u2500 *_label_encoder.pkl\n \u251c\u2500\u2500 bert_config.json\n \u251c\u2500\u2500 export_model\n \u251c\u2500\u2500 params.json\n \u2514\u2500\u2500 vocab.txt\n ```\n\n2. Start server using CLI\n\n ```bash\n bert-multitask-serving-start -model_dir ~/CWS_NER_POS_ckpt/ -num_worker=4 -problem \"CWS|NER|POS\"\n ```\n\n3. Use Client to Get Prediction\n\n ```python\n from bert_serving.client import BertClient\n bc = BertClient()\n bc.encode(['\u6211\u7231\u5317\u4eac\u5929\u5b89\u95e8'])\n ```\n\n# Bert\u591a\u4efb\u52a1\u5b66\u4e60\u670d\u52a1\n\n\u4e00\u4e2a\u90e8\u7f72[Bert\u591a\u4efb\u52a1\u5b66\u4e60](https://github.com/JayYip/bert-multitask-learning)\u7684\u670d\u52a1\n\n## \u5b89\u88c5\n\n```bash\npip install bert-multitask-server\npip install bert-multitask-client\n```\n\n## \u5f00\u59cb\u4f7f\u7528\n\n1. \u8bad\u7ec3\u6a21\u578b\u5e76\u5bfc\u51fa\u6a21\u578b.\n\n \u5bfc\u51fa\u540e\u7684\u6a21\u578b\u76ee\u5f55\u5e94\u8be5\u6709\u4ee5\u4e0b\u6587\u4ef6\n\n ```text\n bert_serving_ckpt/\n \u251c\u2500\u2500 *_label_encoder.pkl\n \u251c\u2500\u2500 bert_config.json\n \u251c\u2500\u2500 export_model\n \u251c\u2500\u2500 params.json\n \u2514\u2500\u2500 vocab.txt\n ```\n\n2. \u7528CLI\u542f\u52a8\u670d\u52a1\n\n ```bash\n bert-multitask-serving-start -model_dir models/ -num_worker=4 -problem \"fake_problem\"\n ```\n\n3. \u7528\u5ba2\u6237\u7aef\u83b7\u53d6\u9884\u6d4b\u7ed3\u679c\n\n ```python\n from bert_serving.client import BertClient\n bc = BertClient()\n bc.encode(['\u6211\u7231\u5317\u4eac\u5929\u5b89\u95e8'])\n ```\n\n\n", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/JayYip/bert-multitask-service", "keywords": "bert nlp tensorflow machine learning sentence encoding embedding serving", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "bert-multitask-client", "package_url": "https://pypi.org/project/bert-multitask-client/", "platform": "", "project_url": "https://pypi.org/project/bert-multitask-client/", "project_urls": { "Homepage": "https://github.com/JayYip/bert-multitask-service" }, "release_url": "https://pypi.org/project/bert-multitask-client/0.1.1/", "requires_dist": [ "numpy", "setuptools (==40.5.0)", "pyzmq (==17.1.2)" ], "requires_python": "", "summary": "A service to serve bert_multitask_learning models(Client)", "version": "0.1.1" }, "last_serial": 5385192, "releases": { "0.1.0": [ { "comment_text": "", "digests": { "md5": "6e80fdc39f161c8cf6f25e920f80604f", "sha256": "5983098c0cc336a231cb948c5c4d981227cf481e9454b972eedd13ec4c216420" }, "downloads": -1, "filename": "bert_multitask_client-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "6e80fdc39f161c8cf6f25e920f80604f", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6766, "upload_time": "2019-06-11T07:38:20", "url": "https://files.pythonhosted.org/packages/c5/77/a3132aeabfa4d40f2e596929037ad17717936b51698368b0644613440e78/bert_multitask_client-0.1.0-py3-none-any.whl" } ], "0.1.1": [ { "comment_text": "", "digests": { "md5": "730a10d09c49662a4266d83336fc2e03", "sha256": "dcc22717a9c1c406393147eaa96c231781a5f4443954133ea03ce40caeb26831" }, "downloads": -1, "filename": "bert_multitask_client-0.1.1-py3-none-any.whl", "has_sig": false, "md5_digest": "730a10d09c49662a4266d83336fc2e03", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6767, "upload_time": "2019-06-11T07:48:06", "url": "https://files.pythonhosted.org/packages/ee/5b/3f1fbc12bfd18c32d653694c7894b9293cc4ad74018c024458fd91027483/bert_multitask_client-0.1.1-py3-none-any.whl" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "730a10d09c49662a4266d83336fc2e03", "sha256": "dcc22717a9c1c406393147eaa96c231781a5f4443954133ea03ce40caeb26831" }, "downloads": -1, "filename": "bert_multitask_client-0.1.1-py3-none-any.whl", "has_sig": false, "md5_digest": "730a10d09c49662a4266d83336fc2e03", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6767, "upload_time": "2019-06-11T07:48:06", "url": "https://files.pythonhosted.org/packages/ee/5b/3f1fbc12bfd18c32d653694c7894b9293cc4ad74018c024458fd91027483/bert_multitask_client-0.1.1-py3-none-any.whl" } ] }