{"id":13409222,"url":"https://github.com/langfuse/langfuse","last_synced_at":"2026-03-13T10:08:46.520Z","repository":{"id":169369787,"uuid":"642497346","full_name":"langfuse/langfuse","owner":"langfuse","description":"🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ","archived":false,"fork":false,"pushed_at":"2025-05-06T17:13:09.000Z","size":21092,"stargazers_count":11141,"open_issues_count":295,"forks_count":1000,"subscribers_count":33,"default_branch":"main","last_synced_at":"2025-05-06T17:13:42.663Z","etag":null,"topics":["analytics","autogen","evaluation","langchain","large-language-models","llama-index","llm","llm-evaluation","llm-observability","llmops","monitoring","observability","open-source","openai","playground","prompt-engineering","prompt-management","self-hosted","ycombinator"],"latest_commit_sha":null,"homepage":"https://langfuse.com/docs","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/langfuse.png","metadata":{"files":{"readme":"README.cn.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-05-18T17:47:09.000Z","updated_at":"2025-05-06T16:26:59.000Z","dependencies_parsed_at":"2023-09-25T02:45:57.786Z","dependency_job_id":"41ec8624-5521-4952-a683-8ebbca562b69","html_url":"https://github.com/langfuse/langfuse","commit_stats":{"total_commits":2683,"total_committers":49,"mean_commits":"54.755102040816325","dds":0.5475214312336936,"last_synced_commit":"6c7faf61f8139cac2b63af87c480603c3941bdf8"},"previous_names":["langfuse/langfuse"],"tags_count":386,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langfuse%2Flangfuse","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langfuse%2Flangfuse/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langfuse%2Flangfuse/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langfuse%2Flangfuse/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/langfuse","download_url":"https://codeload.github.com/langfuse/langfuse/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254000826,"owners_count":21997441,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["analytics","autogen","evaluation","langchain","large-language-models","llama-index","llm","llm-evaluation","llm-observability","llmops","monitoring","observability","open-source","openai","playground","prompt-engineering","prompt-management","self-hosted","ycombinator"],"created_at":"2024-07-30T20:00:58.985Z","updated_at":"2026-03-13T10:08:46.504Z","avatar_url":"https://github.com/langfuse.png","language":"TypeScript","readme":"![Langfuse GitHub Banner](https://langfuse.com/images/docs/github-readme/github-banner.png)\n\n\u003cdiv align=\"center\"\u003e\n  \u003cdiv\u003e\n    \u003ch3\u003e\n    \u003ca href=\"https://langfuse.com/cn\"\u003e\n        \u003cstrong\u003e🇨🇳 🤝 🪢\u003c/strong\u003e\n      \u003c/a\u003e · \n      \u003ca href=\"https://cloud.langfuse.com\"\u003e\n        \u003cstrong\u003eLangfuse Cloud\u003c/strong\u003e\n      \u003c/a\u003e · \n      \u003ca href=\"https://langfuse.com/docs/deployment/self-host\"\u003e\n        \u003cstrong\u003e自托管\u003c/strong\u003e\n      \u003c/a\u003e · \n      \u003ca href=\"https://langfuse.com/demo\"\u003e\n        \u003cstrong\u003e演示\u003c/strong\u003e\n      \u003c/a\u003e\n    \u003c/h3\u003e\n  \u003c/div\u003e\n\n  \u003cdiv\u003e\n    \u003ca href=\"https://langfuse.com/docs\"\u003e\u003cstrong\u003e文档\u003c/strong\u003e\u003c/a\u003e ·\n    \u003ca href=\"https://langfuse.com/issues\"\u003e\u003cstrong\u003e报告问题\u003c/strong\u003e\u003c/a\u003e ·\n    \u003ca href=\"https://langfuse.com/ideas\"\u003e\u003cstrong\u003e功能请求\u003c/strong\u003e\u003c/a\u003e ·\n    \u003ca href=\"https://langfuse.com/changelog\"\u003e\u003cstrong\u003e更新日志\u003c/strong\u003e\u003c/a\u003e ·\n    \u003ca href=\"https://langfuse.com/roadmap\"\u003e\u003cstrong\u003e路线图\u003c/strong\u003e\u003c/a\u003e ·\n  \u003c/div\u003e\n  \u003cbr/\u003e\n  \u003cspan\u003eLangfuse 使用 \u003ca href=\"https://github.com/orgs/langfuse/discussions\"\u003e\u003cstrong\u003eGitHub Discussions\u003c/strong\u003e\u003c/a\u003e 作为支持和功能请求的平台。\u003c/span\u003e\n  \u003cbr/\u003e\n  \u003cspan\u003e\u003cb\u003e我们正在招聘。\u003c/b\u003e \u003ca href=\"https://langfuse.com/careers\"\u003e\u003cstrong\u003e加入我们\u003c/strong\u003e\u003c/a\u003e，从事产品工程和技术市场职位。\u003c/span\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003cdiv\u003e\n  \u003c/div\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/langfuse/langfuse/blob/main/LICENSE\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-MIT-E11311.svg\" alt=\"MIT License\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://www.ycombinator.com/companies/langfuse\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Y%20Combinator-W23-orange\" alt=\"Y Combinator W23\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://hub.docker.com/u/langfuse\" target=\"_blank\"\u003e\n    \u003cimg alt=\"Docker Pulls\" src=\"https://img.shields.io/docker/pulls/langfuse/langfuse?labelColor=%20%23FDB062\u0026logo=Docker\u0026labelColor=%20%23528bff\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypi.python.org/pypi/langfuse\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/dm/langfuse?logo=python\u0026logoColor=white\u0026label=pypi%20langfuse\u0026color=blue\" alt=\"langfuse Python package on PyPi\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://www.npmjs.com/package/langfuse\"\u003e\n    \u003cimg src=\"https://img.shields.io/npm/dm/langfuse?logo=npm\u0026logoColor=white\u0026label=npm%20langfuse\u0026color=blue\" alt=\"langfuse npm package\"\u003e\n  \u003c/a\u003e\n  \u003cbr/\u003e\n  \u003ca href=\"https://discord.com/invite/7NXusRtqYU\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/discord/1111061815649124414?logo=discord\u0026labelColor=%20%235462eb\u0026logoColor=%20%23f5f5f5\u0026color=%20%235462eb\"\n         alt=\"在 Discord 上聊天\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://twitter.com/intent/follow?screen_name=langfuse\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/twitter/follow/langfuse?logo=X\u0026color=%20%23f5f5f5\"\n         alt=\"在 X (Twitter) 上关注\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://www.linkedin.com/company/langfuse/\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white\u0026logoColor=fff\"\n         alt=\"在 LinkedIn 上关注\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/langfuse/langfuse/graphs/commit-activity\" target=\"_blank\"\u003e\n    \u003cimg alt=\"过去一个月的提交\" src=\"https://img.shields.io/github/commit-activity/m/langfuse/langfuse?labelColor=%20%2332b583\u0026color=%20%2312b76a\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/langfuse/langfuse/\" target=\"_blank\"\u003e\n    \u003cimg alt=\"已关闭的问题\" src=\"https://img.shields.io/github/issues-search?query=repo%3Alangfuse%2Flangfuse%20is%3Aclosed\u0026label=issues%20closed\u0026labelColor=%20%237d89b0\u0026color=%20%235d6b98\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/langfuse/langfuse/discussions/\" target=\"_blank\"\u003e\n    \u003cimg alt=\"讨论帖数量\" src=\"https://img.shields.io/github/discussions/langfuse/langfuse?labelColor=%20%239b8afb\u0026color=%20%237a5af8\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"./README.md\"\u003e\u003cimg alt=\"README in English\" src=\"https://img.shields.io/badge/English-d9d9d9\"\u003e\u003c/a\u003e\n  \u003ca href=\"./README.cn.md\"\u003e\u003cimg alt=\"简体中文版自述文件\" src=\"https://img.shields.io/badge/简体中文-d9d9d9\"\u003e\u003c/a\u003e\n  \u003ca href=\"./README.ja.md\"\u003e\u003cimg alt=\"日本語のREADME\" src=\"https://img.shields.io/badge/日本語-d9d9d9\"\u003e\u003c/a\u003e\n  \u003ca href=\"./README.kr.md\"\u003e\u003cimg alt=\"README in Korean\" src=\"https://img.shields.io/badge/한국어-d9d9d9\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nLangfuse 是一个 **开源 LLM 工程** 平台。它帮助团队协作 **开发、监控、评估** 以及 **调试** AI 应用。Langfuse 可在几分钟内 **自托管**，并且经过 **实战考验**。\n\n[![Langfuse 概览视频](https://github.com/user-attachments/assets/3926b288-ff61-4b95-8aa1-45d041c70866)](https://langfuse.com/watch-demo)\n\n## ✨ 核心特性\n\n![Langfuse 概览](https://langfuse.com/images/docs/github-readme/github-feature-overview.png)\n\n- [LLM 应用可观察性](https://langfuse.com/docs/tracing)：为你的应用插入仪表代码，并开始将追踪数据传送到 Langfuse，从而追踪 LLM 调用及应用中其他相关逻辑（如检索、嵌入或代理操作）。检查并调试复杂日志及用户会话。试试互动的 [演示](https://langfuse.com/docs/demo) 看看效果。\n- [提示管理](https://langfuse.com/docs/prompt-management/get-started) 帮助你集中管理、版本控制并协作迭代提示。得益于服务器和客户端的高效缓存，你可以在不增加延迟的情况下反复迭代提示。\n\n- [评估](https://langfuse.com/docs/evaluation/overview) 是 LLM 应用开发流程的关键组成部分，Langfuse 能够满足你的多样需求。它支持 LLM 作为\"裁判\"、用户反馈收集、手动标注以及通过 API/SDK 实现自定义评估流程。\n\n- [数据集](https://langfuse.com/docs/evaluation/dataset-runs/datasets) 为评估你的 LLM 应用提供测试集和基准。它们支持持续改进、部署前测试、结构化实验、灵活评估，并能与 LangChain、LlamaIndex 等框架无缝整合。\n\n- [LLM 试玩平台](https://langfuse.com/docs/playground) 是用于测试和迭代提示及模型配置的工具，缩短反馈周期，加速开发。当你在追踪中发现异常结果时，可以直接跳转至试玩平台进行调整。\n\n- [综合 API](https://langfuse.com/docs/api)：Langfuse 常用于驱动定制化的 LLMOps 工作流程，同时利用 Langfuse 提供的构建模块和 API。我们提供 OpenAPI 规格、Postman 集合以及针对 Python 和 JS/TS 的类型化 SDK。\n\n## 📦 部署 Langfuse\n\n![Langfuse 部署选项](https://langfuse.com/images/docs/github-readme/github-deployment-options.png)\n\n### Langfuse Cloud\n\n由 Langfuse 团队管理的部署，提供慷慨的免费额度（爱好者计划），无需信用卡。\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://cloud.langfuse.com\" target=\"_blank\"\u003e\n    \u003cimg alt=\"注册 Langfuse Cloud\" src=\"https://img.shields.io/badge/»%20Sign%20up%20for%20Langfuse%20Cloud-8A2BE2?\u0026color=orange\"\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n### 自托管 Langfuse\n\n在你自己的基础设施上运行 Langfuse：\n\n- [本地（docker compose）](https://langfuse.com/self-hosting/local)：使用 Docker Compose 在你的机器上于 5 分钟内运行 Langfuse。\n\n  ```bash:README.md/docker-compose\n  # 获取最新的 Langfuse 仓库副本\n  git clone https://github.com/langfuse/langfuse.git\n  cd langfuse\n\n  # 运行 Langfuse 的 docker compose\n  docker compose up\n  ```\n\n- [Kubernetes（Helm）](https://langfuse.com/self-hosting/kubernetes-helm)：使用 Helm 在 Kubernetes 集群上部署 Langfuse。这是推荐的生产环境部署方式。\n\n- [虚拟机](https://langfuse.com/self-hosting/docker-compose)：使用 Docker Compose 在单台虚拟机上部署 Langfuse。\n\n- Terraform 模板: [AWS](https://langfuse.com/self-hosting/aws)、[Azure](https://langfuse.com/self-hosting/azure)、[GCP](https://langfuse.com/self-hosting/gcp)\n\n请参阅 [自托管文档](https://langfuse.com/self-hosting) 了解更多关于架构和配置选项的信息。\n\n## 🔌 集成\n\n![Langfuse 集成](https://langfuse.com/images/docs/github-readme/github-integrations.png)\n\n### 主要集成：\n\n| 集成                                                                                 | 支持语言/平台          | 描述                                                                                                                             |\n| ------------------------------------------------------------------------------------ | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------- |\n| [SDK](https://langfuse.com/docs/sdk)                                                 | Python, JS/TS          | 使用 SDK 进行手动仪表化，实现全面灵活性。                                                                                        |\n| [OpenAI](https://langfuse.com/integrations/model-providers/openai-py)                | Python, JS/TS          | 通过直接替换 OpenAI SDK 实现自动仪表化。                                                                                         |\n| [Langchain](https://langfuse.com/docs/integrations/langchain)                        | Python, JS/TS          | 通过传入回调处理器至 Langchain 应用实现自动仪表化。                                                                              |\n| [LlamaIndex](https://langfuse.com/docs/integrations/llama-index/get-started)         | Python                 | 通过 LlamaIndex 回调系统实现自动仪表化。                                                                                         |\n| [Haystack](https://langfuse.com/docs/integrations/haystack)                          | Python                 | 通过 Haystack 内容追踪系统实现自动仪表化。                                                                                       |\n| [LiteLLM](https://langfuse.com/docs/integrations/litellm)                            | Python, JS/TS (仅代理) | 允许使用任何 LLM 替代 GPT。支持 Azure、OpenAI、Cohere、Anthropic、Ollama、VLLM、Sagemaker、HuggingFace、Replicate（100+ LLMs）。 |\n| [Vercel AI SDK](https://langfuse.com/docs/integrations/vercel-ai-sdk)                | JS/TS                  | 基于 TypeScript 的工具包，帮助开发者使用 React、Next.js、Vue、Svelte 和 Node.js 构建 AI 驱动的应用。                             |\n| [API](https://langfuse.com/docs/api)                                                 |                        | 直接调用公共 API。提供 OpenAPI 规格。                                                                                            |\n| [Google VertexAI 和 Gemini](https://langfuse.com/docs/integrations/google-vertex-ai) | 模型                   | 在 Google 上运行基础模型和微调模型。                                                                                             |\n\n### 与 Langfuse 集成的软件包：\n\n| 名称                                                                    | 类型          | 描述                                                                                    |\n| ----------------------------------------------------------------------- | ------------- | --------------------------------------------------------------------------------------- |\n| [Instructor](https://langfuse.com/docs/integrations/instructor)         | 库            | 用于获取结构化 LLM 输出（JSON、Pydantic）的库。                                         |\n| [DSPy](https://langfuse.com/docs/integrations/dspy)                     | 库            | 一个系统性优化语言模型提示和权重的框架。                                                |\n| [Amazon Bedrock](https://langfuse.com/docs/integrations/amazon-bedrock) | 模型          | 在 AWS 上运行基础模型和微调模型。                                                       |\n| [Mirascope](https://langfuse.com/docs/integrations/mirascope)           | 库            | 构建 LLM 应用的 Python 工具包。                                                         |\n| [Ollama](https://langfuse.com/docs/integrations/ollama)                 | 模型（本地）  | 在你的机器上轻松运行开源 LLM。                                                          |\n| [AutoGen](https://langfuse.com/docs/integrations/autogen)               | 代理框架      | 用于构建分布式代理的开源 LLM 平台。                                                     |\n| [Flowise](https://langfuse.com/docs/integrations/flowise)               | 聊天/代理界面 | 基于 JS/TS 的无代码构建器，用于定制化 LLM 流程。                                        |\n| [Langflow](https://langfuse.com/docs/integrations/langflow)             | 聊天/代理界面 | 基于 Python 的 LangChain 用户界面，采用 react-flow 设计，提供便捷的实验与原型构建体验。 |\n| [Dify](https://langfuse.com/docs/integrations/dify)                     | 聊天/代理界面 | 带有无代码构建器的开源 LLM 应用开发平台。                                               |\n| [OpenWebUI](https://langfuse.com/docs/integrations/openwebui)           | 聊天/代理界面 | 自托管的 LLM 聊天网页界面，支持包括自托管和本地模型在内的多种 LLM 运行器。              |\n| [Promptfoo](https://langfuse.com/docs/integrations/promptfoo)           | 工具          | 开源 LLM 测试平台。                                                                     |\n| [LobeChat](https://langfuse.com/docs/integrations/lobechat)             | 聊天/代理界面 | 开源聊天机器人平台。                                                                    |\n| [Vapi](https://langfuse.com/docs/integrations/vapi)                     | 平台          | 开源语音 AI 平台。                                                                      |\n| [Inferable](https://langfuse.com/docs/integrations/other/inferable)     | 代理          | 构建分布式代理的开源 LLM 平台。                                                         |\n| [Gradio](https://langfuse.com/docs/integrations/other/gradio)           | 聊天/代理界面 | 开源 Python 库，可用于构建类似聊天 UI 的网页界面。                                      |\n| [Goose](https://langfuse.com/docs/integrations/goose)                   | 代理          | 构建分布式代理的开源 LLM 平台。                                                         |\n| [smolagents](https://langfuse.com/docs/integrations/smolagents)         | 代理          | 开源 AI 代理框架。                                                                      |\n| [CrewAI](https://langfuse.com/docs/integrations/crewai)                 | 代理          | 多代理框架，用于实现代理之间的协作与工具调用。                                          |\n\n## 🚀 快速入门\n\n为你的应用增加仪表代码，并开始将追踪数据上传到 Langfuse，从而记录 LLM 调用及应用中其他相关逻辑（如检索、嵌入或代理操作）。\n\n### 1️⃣ 创建新项目\n\n1. [创建 Langfuse 账户](https://cloud.langfuse.com/auth/sign-up) 或 [自托管](https://langfuse.com/self-hosting)\n2. 创建一个新项目\n3. 在项目设置中创建新的 API 凭证\n\n### 2️⃣ 记录你的第一个 LLM 调用\n\n使用 [\u003ccode\u003e@observe()\u003c/code\u003e 装饰器](https://langfuse.com/docs/sdk/python/decorators) 可轻松跟踪任何 Python LLM 应用。在本快速入门中，我们还使用了 Langfuse 的 [OpenAI 集成](https://langfuse.com/integrations/model-providers/openai-py) 来自动捕获所有模型参数。\n\n\u003e [!提示]\n\u003e 不使用 OpenAI？请访问 [我们的文档](https://langfuse.com/docs/get-started#log-your-first-llm-call-to-langfuse) 了解如何记录其他模型和框架。\n\n安装依赖：\n\n```bash\npip install langfuse openai\n```\n\n配置环境变量（创建名为 **.env** 的文件）：\n\n```bash:.env\nLANGFUSE_SECRET_KEY=\"sk-lf-...\"\nLANGFUSE_PUBLIC_KEY=\"pk-lf-...\"\nLANGFUSE_BASE_URL=\"https://cloud.langfuse.com\" # 🇪🇺 欧盟区域\n# LANGFUSE_BASE_URL=\"https://us.cloud.langfuse.com\" # 🇺🇸 美洲区域\n```\n\n创建示例代码（文件名：**main.py**）：\n\n```python:main.py\nfrom langfuse import observe\nfrom langfuse.openai import openai  # OpenAI 集成\n\n@observe()\ndef story():\n    return openai.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[{\"role\": \"user\", \"content\": \"What is Langfuse?\"}],\n    ).choices[0].message.content\n\n@observe()\ndef main():\n    return story()\n\nmain()\n```\n\n### 3️⃣ 在 Langfuse 中查看追踪记录\n\n在 Langfuse 中查看你的语言模型调用及其他应用逻辑。\n\n![示例追踪记录](https://langfuse.com/images/docs/github-readme/github-example-trace.png)\n\n_[Langfuse 中的公共示例追踪](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/2cec01e3-3dc2-472f-afcf-3b968cf0c1f4?timestamp=2025-02-10T14%3A27%3A30.275Z\u0026observation=cb5ff844-07ef-41e6-b8e2-6c64344bc13b)_\n\n\u003e [!提示]\n\u003e\n\u003e [了解更多](https://langfuse.com/docs/tracing) 关于 Langfuse 中的追踪，或试试 [互动演示](https://langfuse.com/docs/demo)。\n\n## ⭐️ 给我们加星\n\n![star-langfuse-on-github](https://github.com/user-attachments/assets/79a1d816-d229-4526-aecc-097d4a19f1ad)\n\n## 💭 支持\n\n查找问题答案：\n\n- 我们的 [文档](https://langfuse.com/docs) 是查找答案的最佳起点。内容全面，我们投入大量时间进行维护。你也可以通过 GitHub 提出文档修改建议。\n- [Langfuse 常见问题](https://langfuse.com/faq) 解答了最常见的问题。\n- 使用 \"Ask AI\" 立即获取问题答案。\n\n支持渠道：\n\n- **在 GitHub Discussions 的 [公共问答](https://github.com/orgs/langfuse/discussions/categories/support) 中提出任何问题。** 请尽量提供详细信息（如代码片段、截图、背景信息）以帮助我们理解你的问题。\n- 在 GitHub Discussions 中 [提出功能请求](https://github.com/orgs/langfuse/discussions/categories/ideas)。\n- 在 GitHub Issues 中 [报告 Bug](https://github.com/langfuse/langfuse/issues)。\n- 对于时效性较强的问题，请通过应用内聊天小部件联系我们。\n\n## 🤝 贡献\n\n欢迎你的贡献！\n\n- 在 GitHub Discussions 中为 [想法](https://github.com/orgs/langfuse/discussions/categories/ideas)投票。\n- 提出并评论 [问题](https://github.com/langfuse/langfuse/issues)。\n- 提交 PR —— 详情请参见 [CONTRIBUTING.md](CONTRIBUTING.md)，了解如何搭建开发环境。\n\n## 🥇 许可证\n\n除 `ee` 文件夹外，本仓库采用 MIT 许可证。详情请参见 [LICENSE](LICENSE) 以及 [文档](https://langfuse.com/docs/open-source)。\n\n## ⭐️ 星标历史\n\n\u003ca href=\"https://star-history.com/#langfuse/langfuse\u0026Date\"\u003e\n  \u003cpicture\u003e\n    \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://api.star-history.com/svg?repos=langfuse/langfuse\u0026type=Date\u0026theme=dark\" /\u003e\n    \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://api.star-history.com/svg?repos=langfuse/langfuse\u0026type=Date\" /\u003e\n    \u003cimg alt=\"星标历史图表\" src=\"https://api.star-history.com/svg?repos=langfuse/langfuse\u0026type=Date\" style=\"border-radius: 15px;\" /\u003e\n  \u003c/picture\u003e\n\u003c/a\u003e\n\n## ❤️ 使用 Langfuse 的开源项目\n\n以下是使用 Langfuse 的顶级开源 Python 项目，按星标数排名（[来源](https://github.com/langfuse/langfuse-docs/blob/main/components-mdx/dependents)）：\n\n| 仓库                                                                                                                                                                                                                                                                |  星数 |\n| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----: |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/127165244?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [langgenius](https://github.com/langgenius) / [dify](https://github.com/langgenius/dify)                                            | 54865 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/158137808?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [open-webui](https://github.com/open-webui) / [open-webui](https://github.com/open-webui/open-webui)                                | 51531 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/131470832?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [lobehub](https://github.com/lobehub) / [lobe-chat](https://github.com/lobehub/lobe-chat)                                           | 49003 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/85702467?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [langflow-ai](https://github.com/langflow-ai) / [langflow](https://github.com/langflow-ai/langflow)                                  | 39093 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/130722866?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [run-llama](https://github.com/run-llama) / [llama_index](https://github.com/run-llama/llama_index)                                 | 37368 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/169401942?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [danny-avila](https://github.com/danny-avila) / [LibreChat](https://github.com/danny-avila/LibreChat)                               | 33142 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/139558948?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [chatchat-space](https://github.com/chatchat-space) / [Langchain-Chatchat](https://github.com/chatchat-space/Langchain-Chatchat)    | 32486 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/128289781?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [FlowiseAI](https://github.com/FlowiseAI) / [Flowise](https://github.com/FlowiseAI/Flowise)                                         | 32448 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/31035808?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [mindsdb](https://github.com/mindsdb) / [mindsdb](https://github.com/mindsdb/mindsdb)                                                | 26931 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/119600397?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [twentyhq](https://github.com/twentyhq) / [twenty](https://github.com/twentyhq/twenty)                                              | 24195 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/60330232?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [PostHog](https://github.com/PostHog) / [posthog](https://github.com/PostHog/posthog)                                                | 22618 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/121462774?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [BerriAI](https://github.com/BerriAI) / [litellm](https://github.com/BerriAI/litellm)                                               | 15151 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/179202840?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [mediar-ai](https://github.com/mediar-ai) / [screenpipe](https://github.com/mediar-ai/screenpipe)                                   | 11037 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/105877416?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [formbricks](https://github.com/formbricks) / [formbricks](https://github.com/formbricks/formbricks)                                |  9386 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/76263028?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [anthropics](https://github.com/anthropics) / [courses](https://github.com/anthropics/courses)                                       |  8385 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/78410652?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [GreyDGL](https://github.com/GreyDGL) / [PentestGPT](https://github.com/GreyDGL/PentestGPT)                                          |  7374 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/152537519?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [superagent-ai](https://github.com/superagent-ai) / [superagent](https://github.com/superagent-ai/superagent)                       |  5391 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/137907881?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [promptfoo](https://github.com/promptfoo) / [promptfoo](https://github.com/promptfoo/promptfoo)                                     |  4976 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/157326433?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [onlook-dev](https://github.com/onlook-dev) / [onlook](https://github.com/onlook-dev/onlook)                                        |  4141 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/7250217?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [Canner](https://github.com/Canner) / [WrenAI](https://github.com/Canner/WrenAI)                                                      |  2526 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/11855343?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [pingcap](https://github.com/pingcap) / [autoflow](https://github.com/pingcap/autoflow)                                              |  2061 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/85268109?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [MLSysOps](https://github.com/MLSysOps) / [MLE-agent](https://github.com/MLSysOps/MLE-agent)                                         |  1161 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/158137808?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [open-webui](https://github.com/open-webui) / [pipelines](https://github.com/open-webui/pipelines)                                  |  1100 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/18422723?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [alishobeiri](https://github.com/alishobeiri) / [thread](https://github.com/alishobeiri/thread)                                      |  1074 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/125468716?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [topoteretes](https://github.com/topoteretes) / [cognee](https://github.com/topoteretes/cognee)                                     |   971 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/188657705?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [bRAGAI](https://github.com/bRAGAI) / [bRAG-langchain](https://github.com/bRAGAI/bRAG-langchain)                                    |   823 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/169500408?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [opslane](https://github.com/opslane) / [opslane](https://github.com/opslane/opslane)                                               |   677 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/151867818?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [dynamiq-ai](https://github.com/dynamiq-ai) / [dynamiq](https://github.com/dynamiq-ai/dynamiq)                                      |   639 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/48585267?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [theopenconversationkit](https://github.com/theopenconversationkit) / [tock](https://github.com/theopenconversationkit/tock)         |   514 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/20493493?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [andysingal](https://github.com/andysingal) / [llm-course](https://github.com/andysingal/llm-course)                                 |   394 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/132396805?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [phospho-app](https://github.com/phospho-app) / [phospho](https://github.com/phospho-app/phospho)                                   |   384 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/178644984?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [sentient-engineering](https://github.com/sentient-engineering) / [agent-q](https://github.com/sentient-engineering/agent-q)        |   370 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/168552753?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [sql-agi](https://github.com/sql-agi) / [DB-GPT](https://github.com/sql-agi/DB-GPT)                                                 |   324 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/60330232?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [PostHog](https://github.com/PostHog) / [posthog-foss](https://github.com/PostHog/posthog-foss)                                      |   305 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/154247157?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [vespperhq](https://github.com/vespperhq) / [vespper](https://github.com/vespperhq/vespper)                                         |   304 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/185116535?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [block](https://github.com/block) / [goose](https://github.com/block/goose)                                                         |   295 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/609489?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [aorwall](https://github.com/aorwall) / [moatless-tools](https://github.com/aorwall/moatless-tools)                                    |   291 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/2357342?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [dmayboroda](https://github.com/dmayboroda) / [minima](https://github.com/dmayboroda/minima)                                          |   221 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/66303003?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [RobotecAI](https://github.com/RobotecAI) / [rai](https://github.com/RobotecAI/rai)                                                  |   172 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/148684274?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [i-am-alice](https://github.com/i-am-alice) / [3rd-devs](https://github.com/i-am-alice/3rd-devs)                                    |   148 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/171735272?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [8090-inc](https://github.com/8090-inc) / [xrx-sample-apps](https://github.com/8090-inc/xrx-sample-apps)                            |   138 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/104478511?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [babelcloud](https://github.com/babelcloud) / [LLM-RGB](https://github.com/babelcloud/LLM-RGB)                                      |   135 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/15125613?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [souzatharsis](https://github.com/souzatharsis) / [tamingLLMs](https://github.com/souzatharsis/tamingLLMs)                           |   129 |\n| \u003cimg class=\"avatar mr-2\" src=\"https://avatars.githubusercontent.com/u/51827949?s=40\u0026v=4\" width=\"20\" height=\"20\" alt=\"\"\u003e \u0026nbsp; [deepset-ai](https://github.com/deepset-ai) / [haystack-core-integrations](https://github.com/deepset-ai/haystack-core-integrations) |   126 |\n\n## 🔒 安全与隐私\n\n我们非常重视数据安全和隐私。更多信息请参阅我们的 [安全与隐私](https://langfuse.com/security) 页面。\n\n### 遥测\n\n默认情况下，Langfuse 会自动将自托管实例的基础使用统计数据上传至集中服务器（PostHog）。\n\n这有助于我们：\n\n1. 了解 Langfuse 的使用情况，并改进最关键的功能。\n2. 跟踪整体使用数据，以便内部及外部（例如筹款）报告。\n\n所有数据均不会与第三方共享，也不包含任何敏感信息。我们对这一过程保持高度透明，你可以在 [此处](/web/src/features/telemetry/index.ts) 查看我们收集的具体数据。\n\n你可以通过设置 `TELEMETRY_ENABLED=false` 来选择退出。\n\n```\n\n```\n","funding_links":[],"categories":["Models and Tools","TypeScript","👁️ Observability \u0026 Tracing","[Langfuse](https://langfuse.com/)","🧺 Curated catalog","LLMOps","By Industry","LLM Engineering Platform","\u003cimg src=\"./assets/satellite.svg\" width=\"16\" height=\"16\" style=\"vertical-align: middle;\"\u003e Satellites","LLM Testing / Monitoring","Evaluation and Monitoring","A01_文本生成_文本对话","LLM Deployment","Tooling \u0026 Dev Experience","Agent","Observability","Prompts","开源工具","Monitoring and Observability","\u003ca id=\"tools\"\u003e\u003c/a\u003e🛠️ Tools","📊 Metrics","Tools","🔍 Observability and Evaluation","LLM Applications","Building","analytics","Repos","Tools \u0026 Platforms","Built with TypeScript","Observability and Monitoring","📋 Contents","Agent Integration \u0026 Deployment Tools","Platforms","Orchestration","Tools and Code","Agent Observability and Testing","Agent Infrastructure","Vendor Examples","10. LLM \u0026 AI Observability"],"sub_categories":["LLM Deployment","3. The Enterprise / High-Scale Stack (The 1%)","Links","Observability","Blockchain","大语言对话模型及数据","Development Tools","可观测性","Bleeding Edge ⚗️","Response Evaluation Metrics","LLM Evaluations and Benchmarks","Tracing and Monitoring","Prompt Engineering","Open Source Frameworks","Web","📊 8. MLOps / LLMOps \u0026 Production","LLM Framework Tools","Open Source Platforms","Application Framework","Application Frameworks","LLM Evaluation Tools","Benchmark Reality Check (real-world tool use)","Monitoring \u0026 Observability","Testing, Evaluation and Observability","Other Tools","Platforms"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flangfuse%2Flangfuse","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flangfuse%2Flangfuse","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flangfuse%2Flangfuse/lists"}