<p align="center">
<a target="_blank" href="https://phoenix.arize.com" style="background:none">
<img alt="凤凰横幅" src="https://yellow-cdn.veclightyear.com/835a84d5/4cae59d9-c9ea-4241-bb39-17518bab8915.jpg?raw=true" width="auto" height="auto"></img>
</a>
<br/>
<br/>
<a href="https://docs.arize.com/phoenix/">
<img src="https://img.shields.io/static/v1?message=文档&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAIAAAACACAYAAADDPmHLAAAG4ElEQVR4nO2d4XHjNhCFcTf+b3ZgdWCmgmMqOKUC0xXYrsBOBVEqsFRB7ApCVRCygrMriFQBM7h5mNlwKBECARLg7jeDscamSQj7sFgsQfBL27ZK4MtXsT1vRADMEQEwRwTAHBEAc0QAzBEBMEcEwBwRAHNEAMwRATBnjAByFGE+MqVUMcYOY24GVUqpb/h8VErVKAf87QNFcEcbd4WSw+D6803njHscO5sATmGEURGBiCj6yUlv1uX2gv91FsDViArbcA2RUKF8QhAV8RQc0b15DcOt0VaTE1oAfWj3dYdCBfGGsmSM0XX5HsP3nEMAXbqCeCdiOERQPx9og5exGJ0S4zRQN9KrUupfpdQWjZciure/YIj7K0bjqwTyAHdovA805iqCOg2xgnB1nZ97IvaoSCURdIPG/IHGjTH/YAz/A8KdJai7lBQzgbpx/0Hg6DT18UzWMXxSjMkDrElPNEmKfAbl6znwI3IMU/OCa0/1nfckwWaSbvWYYDnEsvCMJDNckhqu7GCMKWYOBXp9yPGd5kvqUAKf6rkAk7M2SY9QDXdEr9wEOr9x96EiejMFnixBNteDISsyNw7hHRqc22evWcP4vt39O85bzZH30AKg4+eo8cQRI4bHAJ7hyYM3CNHrG9RrimSXuZmUkZjN/O6nAPpcwCcJNmipAle2QM/1GU3vITCXhvY91u9geN/jOY27VuTnYL1PCeAcRhwh7/Bl8Ai+IuxPiOCShtfX/sPDtY8w+sZjby86dw6dBeoigD7obd/Ko6fI4BF8DA9HnGdrcU0fLt+n4dfE6H5jpjYcVdu2L23b5lpjHoo+18FDbcszddF1rUee/4C6ZiO+80rHZmjDoIQUQLdRtm3brkcKIUPjjqVPBIUHgW1GGN4YfawAL2IqAVB8iEE31tvIelARlCPPVaFOLoIupzY6xVcM4MoRUyHXyHhslH6PaPl5RP1Lh4UsOeKR2e8dzC0Aiuvc2Nx3fwhfxf/hknouUYbWUk5GTAIwmOh5e+H0cor8vEL91hfOdEqINLq1AV+RKImJ6869f9tFIBVc6y7gd3lHfWyNX0LEr7EuDElhRdAlQjig0e/RU31xxDltM4pF7IY3pLIgxAhhgzF/iC2M0Hi4dkOGlyGMd/g7dsMbUlsR9ICe9WhxbA3DjRkSdjiHzQzlBSKNJsCzIcUlYdfI0dcWS8LMkPDkcJ0n/O+Qyy/IAtDkSPnp4Fu4WpthQR/zm2VcoI/51fI28iYld9/HEh4Pf7D0Bm845pwIPnHMUJSf45pT5x68s5T9AW6INzhHDeP1BYcNMew5SghkinWOwVnaBhHGG5ybMn70zBDe8buh8X6DqV0Sa/5tWOIOIbcWQ8KBiGBnMb/P0OuTd/lddCrY5jn/VLm3nL+fY4X4YREuv8vS9wh6HSkAExMs0viKySZRd44iyOH2FzPe98Fll7A7GNMmjay4GF9BAKGXesfCN0sRsDG+YrhP4O2ACFgZXzHdKPL2RMJoxc34ivFOod3AMMNUj5XxFfOtYrUIXvB5MandS+G+V/AzZ+MrEcBPlpoFtUIEwBwRAG+OIgDe1CIA5ogAmCMCYI4IgDkiAOaIAJgjAmCOCIA5IgDmiACYIwJgjgiAOSIA5ogAmCMCYI4IgDkiAOaIAJgjAmCOCIA5IgDmiACYIwJgjgiAOSIA5ogAmCMCYI4IgDkiAOaIAJgjAmDOVYBXvwvxQV8NWJOd0esvJ94babZaz7B5ovldxnlDpYhp0JFr/KTlLKcEMMQKpcDPXIQxGXsYmhZnXAXQh/EWBQrr3bc80mATyyrEvs4+BdBHgbdxFOIhrDkSg1/6Iu2LCS0AyoqI4ftUF00EY/Q3h1fRj2JKAVCMGErmnsH1lfnemEsAlByvgl0z2qx5B8OPCuB8EIMADBlEEOV79j1whNE3c/X2PmISAGUNr7CEmUSUhjfEKgBDAY+QohCiNrwhdgEYzPv7UxkadvBg0RrekMrNoAozh3vLN4DPhc7S/WL52vkoSO1u4BZC+DOCulC0KJ/gqWaP7C8hlSGgjxyCmDuPsEePT/KuasrrAcyr4H+f6fq01yd7Sz1lD0CZ2hs06PVJufs+lrIiyLwufjfBtXYpjvWnWIoHoJSYe4dIK/t4HX1ULFEACkPCm8e8wXFJvZ6y1EWhJkDcWxw7RINzLc74auGrgg8e4oIm9Sh/CA7LwkvHqaIJ9pLI6Lmy1BigDy2EV8tjdzh+8XB6MGSLKH4INsZXDJ8MGhIBK+Mrpo+GnRIBO+MrZjFAFxoTNBwCvj6u4qvSZJiM3iNX4yvmHoA9Sh4PF0QAzBEBMEcEwBwRAHNEAMwRAXBGKfUfr5hKvglRfO4AAAAASUVORK5CYII=&labelColor=grey&color=blue&logoColor=white&label=%20"/>
</a>
<a target="_blank" href="https://join.slack.com/t/arize-ai/shared_invite/zt-1px8dcmlf-fmThhDFD_V_48oU7ALan4Q">
<img src="https://img.shields.io/static/v1?message=社区&logo=slack&labelColor=grey&color=blue&logoColor=white&label=%20"/>
</a>
<a target="_blank" href="https://twitter.com/ArizePhoenix">
<img src="https://yellow-cdn.veclightyear.com/835a84d5/9ff06128-3623-4fda-beac-e0df64ca5057.svg?color=blue&labelColor=gray&logo=twitter">
</a>
<a target="_blank" href="https://pypi.org/project/arize-phoenix/">
<img src="https://img.shields.io/pypi/v/arize-phoenix?color=blue">
</a>
<a target="_blank" href="https://anaconda.org/conda-forge/arize-phoenix">
<img src="https://yellow-cdn.veclightyear.com/835a84d5/427905d1-c542-4a33-998a-130d4b215112.svg?color=blue">
</a>
<a target="_blank" href="https://pypi.org/project/arize-phoenix/">
<img src="https://img.shields.io/pypi/pyversions/arize-phoenix">
</a>
<a target="_blank" href="https://hub.docker.com/r/arizephoenix/phoenix/tags">
<img src="https://img.shields.io/docker/v/arizephoenix/phoenix?sort=semver&logo=docker&label=镜像&color=blue">
</a>
</p>
Phoenix是一个开源的AI可观察性平台，专为实验、评估和故障排除而设计。它提供以下功能：
- 跟踪 - 使用基于OpenTelemetry的工具跟踪LLM应用程序的运行时。
- 评估 - 利用LLM对应用程序的性能进行基准测试，使用响应和检索评估。
- 数据集 - 创建版本化的示例数据集，用于实验、评估和微调。
- 实验 - 跟踪和评估提示、LLM和检索的变化。
- 推理分析 - 使用降维和聚类可视化推理和嵌入，以识别漂移和性能下降。
Phoenix与供应商和语言无关，为流行框架（🦙LlamaIndex、🦜⛓LangChain、🧩DSPy）和LLM提供商（OpenAI、Bedrock等）提供开箱即用的支持。有关自动化工具的详细信息，请查看OpenInference项目。
Phoenix几乎可以在任何地方运行，包括Jupyter笔记本、本地机器、容器化部署或云端。
安装
通过pip或conda安装Phoenix，并附带运行评估所需的额外依赖项：
pip install 'arize-phoenix[evals]'
Phoenix容器镜像可通过Docker Hub获得，可使用Docker或Kubernetes部署。
社区
加入我们的社区，与数千名AI构建者联系。
致谢
重大变更
请参阅迁移指南了解重大变更列表。
版权、专利和许可
版权所有 2023 Arize AI, Inc. 保留所有权利。
本代码的部分内容受一项或多项美国专利保护。参见IP_NOTICE。
本软件根据Elastic License 2.0（ELv2）的条款授权。参见LICENSE。
