版本与发布

你可以在 Litefuse 中追踪 LLM 应用的变更对各项指标的影响。这让你能够：

在生产环境中运行实验（A/B 测试），并衡量其对成本、延迟和质量的影响。
- 示例：“切换到新模型会带来什么影响？”
解释指标随时间的变化。
- 示例：“为什么这条 chain 的延迟变高了？“

Releases

release 用于追踪应用程序的整体版本。它通常被设置为应用的 semantic version 或 git commit hash。

SDK 按以下顺序查找 release：

SDK 初始化参数
环境变量
主流部署平台上自动设置的 release 标识符

初始化

Python SDK 允许你在初始化客户端时设置 release：

from langfuse import Langfuse
 
# Set the release when initializing the client
langfuse = Langfuse(release="v2.1.24")

JS/TS SDK 会查找 LANGFUSE_RELEASE 环境变量。你可以在 CI/CD 流水线中通过它来配置 release。

LANGFUSE_RELEASE = "<release_tag>" # <- github sha or other identifier

SDK 会查找 LANGFUSE_RELEASE 环境变量。你可以在 CI/CD 流水线中通过它来配置 release。

LANGFUSE_RELEASE = "<release_tag>" # <- github sha or other identifier

主流平台自动识别

如果没有设置其他 release，Langfuse SDK 会回退到一组已知的 release 环境变量。

支持的平台包括：Vercel、Heroku、Netlify。完整的环境变量列表可参见 JS/TS 和 Python。

Versions

version 参数可以添加到所有 observation 类型上（例如 span、generation、event 以及其他 observation 类型）。这样你就可以使用 Litefuse 分析来追踪某个特定 name 对象的新 version 对各项指标的影响。

在某个 context 内为所有 observation 设置 version：

from langfuse import observe, propagate_attributes
 
@observe()
def process_data():
    # Propagate version to all child observations
    with propagate_attributes(version="1.0"):
        # All nested operations automatically inherit version
        result = perform_processing()
 
        return result

直接创建 observation 时：

from langfuse import get_client, propagate_attributes
 
langfuse = get_client()
 
with langfuse.start_as_current_observation(as_type="span", name="process-data") as span:
    # Propagate version to all child observations
    with propagate_attributes(version="1.0"):
        # All observations created here automatically have version="1.0"
        with span.start_as_current_observation(
            as_type="generation",
            name="guess-countries",
            model="gpt-4o"
        ) as generation:
            # This generation automatically has version="1.0"
            pass

为某个具体 observation 设置 version：

from langfuse import get_client
 
langfuse = get_client()
 
with langfuse.start_as_current_observation(as_type="span", name="process-data", version="1.0") as span:
    # This span has version="1.0"
    pass

在某个 context 内将 version 传播到所有 observation：

import { startActiveObservation, propagateAttributes } from "@langfuse/tracing";
 
await startActiveObservation("process-data", async (span) => {
  // Propagate version to all child observations
  await propagateAttributes(
    {
      version: "1.0",
    },
    async () => {
      // All observations created here automatically have version="1.0"
      const generation = startObservation(
        "guess-countries",
        { model: "gpt-4" },
        { asType: "generation" }
      );
      // This generation automatically has version="1.0"
      generation.end();
    }
  );
});

为某个具体 observation 设置 version：

import { startObservation } from "@langfuse/tracing";
 
const generation = startObservation(
  "guess-countries",
  { model: "gpt-4" },
  { asType: "generation" }
);
generation.update({ version: "1.0" });
generation.end();

from langfuse.callback import CallbackHandler
 
handler = CallbackHandler(version="1.0")

import { CallbackHandler } from "langfuse-langchain";
 
const handler = new CallbackHandler({
  version: "1.0",
});

Note on Attribute Propagation

We use Attribute Propagation to propagate `version` across all observations of a trace. We will use all observations with `version` to create `version`-level metrics. Please consider the following when using Attribute Propagation:

Values must be strings ≤200 characters
Call early in your trace to ensure all observations are covered. This way you make sure that all Metrics in Litefuse are accurate.
Invalid values are dropped with a warning

Learn more: Python SDK | TypeScript SDK

Litefuse 界面中的 version 参数

单个 generation 上的 version

事件队列与批处理采样

这个页面对你有帮助吗？

支持