Technology Radar
Langfuse is an open-source LLM engineering platform covering observability, prompt management, evaluations and dataset management. The project has matured significantly since we last assessed it. The v3 architecture introduces ClickHouse, Redis and S3 as back-end components, making it more scalable but also more complex to self-host.
Both the Python and TypeScript SDKs are now built natively on OpenTelemetry, making Langfuse a natural fit for teams that already use OTEL-based observability. New capabilities such as the experiment runner SDK and structured output support for prompt experiments move Langfuse beyond pure tracing into systematic evaluation workflows. This makes it worth considering in an increasingly crowded space that includes Arize Phoenix, Helicone and LangSmith.
Teams building primarily on Pydantic AI may also consider Pydantic Logfire, which takes a broader approach as a full-stack OTEL observability platform rather than an LLM-specific tooling suite. Langfuse remains in Assess as it is a credible choice for teams that need integrated tracing, evaluations and prompt management in one self-hostable platform. However, teams should evaluate whether the infrastructure commitment is justified for their scale and whether a narrower tool like Helicone may suffice if the primary need is model-layer cost and latency visibility.
LLM（大型语言模型）像黑箱一样运作，非常难以确定它的行为。可观察性对于打开这个黑箱并理解 LLM 应用程序在生产环境中的运作至关重要。我们团队在使用 Langfuse 方面有过积极的体验，我们曾用它来观察、监控和评估基于 LLM 的应用程序。它的追踪、分析和评估能力使我们能够分析完成性能和准确性，管理成本和延迟，并理解生产使用模式，从而促进持续的数据驱动改进。仪器数据提供了请求-响应流和中间步骤的完整可追溯性，这可以作为测试数据，在部署新变更之前验证应用程序。我们已将 Langfuse 与 RAG（检索增强生成） 等 LLM 架构，以及 大语言模型驱动的自主代理 一起使用。 例如，在基于 RAG 的应用程序中，分析低评分的对话追踪有助于识别架构的哪个部分（如预检索、检索或生成）需要改进。当然，在这一领域，另一个值得考虑的选项是 Langsmith。
