用户追踪

Users 视图提供了所有用户的概览，也支持深入查看单个用户。把 Litefuse 中的数据映射到具体用户非常简单，只需将 userId 属性在 observation 之间传播即可。它可以是用户名、邮箱或任何其他唯一标识。userId 是可选的，但使用它能让你从 Litefuse 中获得更多价值，例如按 userId 聚合 LLM 用量与成本等指标。详情请参见集成文档。

使用 @observe() 装饰器时：

from langfuse import observe, propagate_attributes
 
@observe()
def process_user_request(user_query):
    # Propagate user_id to all child observations
    with propagate_attributes(user_id="user_12345"):
        # All nested observations automatically inherit user_id
        result = process_query(user_query)
        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-user-request"
) as root_span:
    # Propagate user_id to all child observations
    with propagate_attributes(user_id="user_12345"):
        # All observations created here automatically have user_id
        with root_span.start_as_current_observation(
            as_type="generation",
            name="generate-response",
            model="gpt-4o"
        ) as gen:
            # This observation automatically has user_id
            pass

使用 context manager 时：

import { startActiveObservation, propagateAttributes } from "@langfuse/tracing";
 
await startActiveObservation("context-manager", async (span) => {
  span.update({
    input: { query: "What is the capital of France?" },
  });
 
  // Propagate userId to all child observations
  await propagateAttributes(
    {
      userId: "user-123",
    },
    async () => {
      // All observations created here automatically have userId
      // ... your logic ...
    }
  );
});

使用 observe wrapper 时：

import { observe, propagateAttributes } from "@langfuse/tracing";
 
// An existing function
const processUserRequest = observe(
  async (userQuery: string) => {
    // Propagate userId to all child observations
    return await propagateAttributes({ userId: "user-123" }, async () => {
      // All nested observations automatically inherit userId
      const result = await processQuery(userQuery);
      return result;
    });
  },
  { name: "process-user-request" }
);
 
const result = await processUserRequest("some query");

更多细节请参阅 JS/TS SDK 文档。

from langfuse import get_client, propagate_attributes
from langfuse.openai import openai
 
langfuse = get_client()
 
with langfuse.start_as_current_observation(as_type="span", name="openai-call"):
    # Propagate user_id to all observations including OpenAI generation
    with propagate_attributes(user_id="user_12345"):
        completion = openai.chat.completions.create(
            name="test-chat",
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "You are a calculator."},
                {"role": "user", "content": "1 + 1 = "}
            ],
            temperature=0,
        )

将 propagate_attributes() 与 CallbackHandler 配合使用：

from langfuse import get_client, propagate_attributes
from langfuse.langchain import CallbackHandler
 
langfuse = get_client()
handler = CallbackHandler()
 
with langfuse.start_as_current_observation(as_type="span", name="langchain-call"):
    # Propagate user_id to all observations
    with propagate_attributes(user_id="user_12345"):
        # Pass handler to the chain invocation
        chain.invoke(
            {"animal": "dog"},
            config={"callbacks": [handler]},
        )

将 propagateAttributes() 与 CallbackHandler 配合使用：

import { startActiveObservation, propagateAttributes } from "@langfuse/tracing";
import { CallbackHandler } from "langfuse-langchain";
 
const langfuseHandler = new CallbackHandler();
 
await startActiveObservation("langchain-call", async () => {
  // Propagate userId to all observations
  await propagateAttributes(
    {
      userId: "user-123",
    },
    async () => {
      // Pass handler to the chain invocation
      await chain.invoke(
        { input: "<user_input>" },
        { callbacks: [langfuseHandler] }
      );
    }
  );
});

Note on Attribute Propagation

We use Attribute Propagation to propagate `userId` across all observations of a trace. We will use all observations with `userId` to create `userId`-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

查看所有用户

用户列表给出了 Litefuse 已追踪到的所有用户的概览。可以方便地按整体 token 用量、trace 数和用户反馈进行细分。

用户列表

单个用户视图

单个用户视图提供了对单个用户的深入查看。你可以浏览聚合指标，或查看该用户的所有 trace 和反馈。

用户详情视图

你可以通过以下 URL 格式深链接到该视图：https://<hostname>/project/{projectId}/users/{userId}

用户追踪

查看所有用户

单个用户视图

相关资源