```
如果您在非无服务器环境中使用 LangChain.js 和 LangSmith，我们还建议显式设置以下变量以减少延迟：
`export LANGCHAIN_CALLBACKS_BACKGROUND=true`
如果您在无服务器环境中，建议设置相反的值，以便在函数结束前完成追踪：
`export LANGCHAIN_CALLBACKS_BACKGROUND=false`
更多信息请参阅 [此 LangChain.js 指南](https://js.langchain.com/docs/how_to/callbacks_serverless)。
### 3. 记录追踪
设置好环境后，[包装或装饰您想要追踪的自定义函数/SDK](/langsmith/annotate-code#use-traceable--traceable)。LangSmith 随后将推断出正确的追踪配置：
```python Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import json
import openai
import operator
from langsmith import traceable
from langsmith.wrappers import wrap_openai
from typing import Annotated, Literal, TypedDict
from langgraph.graph import StateGraph
class State(TypedDict):
messages: Annotated[list, operator.add]
tool_schema = {
"type": "function",
"function": {
"name": "search",
"description": "调用以浏览网页。",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}},
"required": ["query"],
},
},
}
# 装饰工具函数将自动使用正确的上下文进行追踪
@traceable(run_type="tool", name="Search Tool")
def search(query: str):
"""调用以浏览网页。"""
if "sf" in query.lower() or "san francisco" in query.lower():
return "天气是 60 华氏度，有雾。"
return "天气是 90 华氏度，晴朗。"
tools = [search]
def call_tools(state):
function_name_to_function = {"search": search}
messages = state["messages"]
tool_call = messages[-1]["tool_calls"][0]
function_name = tool_call["function"]["name"]
function_arguments = tool_call["function"]["arguments"]
arguments = json.loads(function_arguments)
function_response = function_name_to_function[function_name](**arguments)
tool_message = {
"tool_call_id": tool_call["id"],
"role": "tool",
"name": function_name,
"content": function_response,
}
return {"messages": [tool_message]}
wrapped_client = wrap_openai(openai.Client())
def should_continue(state: State) -> Literal["tools", "__end__"]:
messages = state["messages"]
last_message = messages[-1]
if last_message["tool_calls"]:
return "tools"
return "__end__"
def call_model(state: State):
messages = state["messages"]
# 调用包装后的客户端将自动推断正确的追踪上下文
response = wrapped_client.chat.completions.create(
messages=messages, model="gpt-4.1-mini", tools=[tool_schema]
)
raw_tool_calls = response.choices[0].message.tool_calls
tool_calls = [tool_call.to_dict() for tool_call in raw_tool_calls] if raw_tool_calls else []
response_message = {
"role": "assistant",
"content": response.choices[0].message.content,
"tool_calls": tool_calls,
}
return {"messages": [response_message]}
workflow = StateGraph(State)
workflow.add_node("agent", call_model)
workflow.add_node("tools", call_tools)
workflow.add_edge("__start__", "agent")
workflow.add_conditional_edges(
"agent",
should_continue,
)
workflow.add_edge("tools", 'agent')
app = workflow.compile()
final_state = app.invoke(
{"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)
final_state["messages"][-1]["content"]
```
```typescript TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
**注意：** 以下示例需要 `langsmith>=0.1.39` 和 `@langchain/langgraph>=0.0.31`
import OpenAI from "openai";
import { StateGraph } from "@langchain/langgraph";
import { wrapOpenAI } from "langsmith/wrappers/openai";
import { traceable } from "langsmith/traceable";
type GraphState = {
messages: OpenAI.ChatCompletionMessageParam[];
};
const wrappedClient = wrapOpenAI(new OpenAI({}));
const toolSchema: OpenAI.ChatCompletionTool = {
type: "function",
function: {
name: "search",
description: "使用此工具查询网页。",
parameters: {
type: "object",
properties: {
query: {
type: "string",
},
},
required: ["query"],
}
}
};
// 包装工具函数将自动使用正确的上下文进行追踪
const search = traceable(async ({ query }: { query: string }) => {
if (
query.toLowerCase().includes("sf") ||
query.toLowerCase().includes("san francisco")
) {
return "天气是 60 华氏度，有雾。";
}
return "天气是 90 华氏度，晴朗。";
}, { run_type: "tool", name: "Search Tool" });
const callTools = async ({ messages }: GraphState) => {
const mostRecentMessage = messages[messages.length - 1];
const toolCalls = (mostRecentMessage as OpenAI.ChatCompletionAssistantMessageParam).tool_calls;
if (toolCalls === undefined || toolCalls.length === 0) {
throw new Error("没有工具调用传递给节点。");
}
const toolNameMap = {
search,
};
const functionName = toolCalls[0].function.name;
const functionArguments = JSON.parse(toolCalls[0].function.arguments);
const response = await toolNameMap[functionName](functionArguments);
const toolMessage = {
tool_call_id: toolCalls[0].id,
role: "tool",
name: functionName,
content: response,
}
return { messages: [toolMessage] };
};
const callModel = async ({ messages }: GraphState) => {
// 调用包装后的客户端将自动推断正确的追踪上下文
const response = await wrappedClient.chat.completions.create({
messages,
model: "gpt-4.1-mini",
tools: [toolSchema],
});
const responseMessage = {
role: "assistant",
content: response.choices[0].message.content,
tool_calls: response.choices[0].message.tool_calls ?? [],
};
return { messages: [responseMessage] };
};
const shouldContinue = ({ messages }: GraphState) => {
const lastMessage =
messages[messages.length - 1] as OpenAI.ChatCompletionAssistantMessageParam;
if (
lastMessage?.tool_calls !== undefined &&
lastMessage?.tool_calls.length > 0
) {
return "tools";
}
return "__end__";
}
const workflow = new StateGraph({
channels: {
messages: {
reducer: (a: any, b: any) => a.concat(b),
}
}
});
const graph = workflow
.addNode("model", callModel)
.addNode("tools", callTools)
.addEdge("__start__", "model")
.addConditionalEdges("model", shouldContinue, {
tools: "tools",
__end__: "__end__",
})
.addEdge("tools", "model")
.compile();
await graph.invoke({
messages: [{ role: "user", content: "what is the weather in sf" }]
});
```
### 查看追踪
**详细信息视图**
点击追踪，并在右上角切换到 **详细信息** 视图。您在 LangSmith 中的追踪应 [看起来像这样](https://smith.langchain.com/public/c3d128fa-c618-4b0e-b9d0-ccbb619440d8/r)。
**消息视图**
LangSmith UI 中的 **消息** 视图显示了用户与智能体之间的简化对话历史。此视图从顶层追踪（包括用户的初始请求、工具调用和智能体的最终响应）中提取消息，并以类似聊天的格式呈现。
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\langsmith\trace-with-langgraph.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.