> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# LangSmith CLI

> 从终端查询和管理 LangSmith 项目、追踪、运行、数据集、评估器、实验和会话线程

LangSmith CLI 是一个快速、对智能体友好的命令行工具，可直接在终端中处理您的 LangSmith 数据和工作流。它专为人类和 AI 编码智能体设计，用于列出、筛选、检索和导出数据——默认提供可预测的 JSON 输出，并为人类提供美观的表格模式。

<Callout icon="terminal" color="#4F46E5" iconType="regular">
  专为智能体和脚本构建：默认输出 JSON，支持清晰的 stdout/stderr 分离，并提供 `--yes` 标志用于非交互式使用。
</Callout>

## 安装

使用以下方法之一进行安装：

<CodeGroup>
  ```bash 安装脚本（推荐） theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  curl -sSL https://raw.githubusercontent.com/langchain-ai/langsmith-cli/main/scripts/install.sh | sh
  ```

  ```bash 安装到自定义目录 theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  INSTALL_DIR=$HOME/.local/bin \
    curl -sSL https://raw.githubusercontent.com/langchain-ai/langsmith-cli/main/scripts/install.sh | sh
  ```

  ```bash GitHub Releases theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  # 为您的平台下载最新的二进制文件
  # https://github.com/langchain-ai/langsmith-cli/releases
  ```

  ```bash Go install theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  go install github.com/langchain-ai/langsmith-cli/cmd/langsmith@latest
  ```
</CodeGroup>

## 认证

将您的 [API 密钥](/langsmith/create-account-api-key) 设置为环境变量：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export LANGSMITH_API_KEY="lsv2_..."
```

可选默认设置：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export LANGSMITH_ENDPOINT="https://api.smith.langchain.com"  # 自托管/混合部署
export LANGSMITH_PROJECT="my-default-project"                 # 查询的默认项目
```

或者在运行命令时通过标志传递：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith --api-key lsv2_... trace list --project my-app
```

## 快速开始

以下命令涵盖了核心资源类型——项目、追踪、运行、数据集、实验和会话线程：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 列出追踪项目（会话）
langsmith project list

# 列出项目中的近期追踪
langsmith trace list --project my-app --limit 5

# 获取特定追踪的完整详情
langsmith trace get <trace-id> --project my-app --full

# 列出包含令牌计数的 LLM 运行
langsmith run list --project my-app --run-type llm --include-metadata

# 数据集和实验
langsmith dataset list
langsmith experiment list --dataset my-eval-set

# 项目中的会话线程
langsmith thread list --project my-chatbot
```

## 输出格式

* 默认：JSON 输出到 stdout，便于管道传输和脚本处理
* 美观表格：`--format pretty` 用于人类可读的表格和树状视图
* 写入文件：`-o <路径>`

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith trace list --project my-app                  # JSON 数组输出到 stdout
langsmith --format pretty trace list --project my-app  # 表格/树状视图
langsmith trace list --project my-app -o traces.json   # 将 JSON 写入文件
```

## 命令概览

CLI 按资源分组功能。每个命令都支持 `--limit`、`--last-n-minutes` 等筛选器。

### project—列出追踪项目

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith project list                    # 默认限制：20
langsmith project list --name-contains chatbot
langsmith --format pretty project list
```

### trace—查询和导出追踪

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith trace list --project my-app --limit 50 --last-n-minutes 60
langsmith trace list --project my-app --error --include-metadata
langsmith trace get <trace-id> --project my-app --full
langsmith trace export ./traces --project my-app --limit 20 --full
```

### run—查询单个运行

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith run list --project my-app --run-type llm
langsmith run list --project my-app --run-type tool --name search
langsmith run get <run-id> --full
langsmith run export llm_calls.jsonl --project my-app --run-type llm --full
```

### thread—查询会话线程

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith thread list --project my-chatbot --last-n-minutes 120
langsmith thread get <thread-id> --project my-chatbot --full
```

### dataset—管理评估数据集

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith dataset list --name-contains eval
langsmith dataset get my-dataset
langsmith dataset create --name my-eval-set --description "QA pairs for v2"
langsmith dataset export my-dataset ./data.json --limit 500
```

### evaluator—管理评估器

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith evaluator list
langsmith evaluator upload evals.py --name accuracy --function check_accuracy --dataset my-eval-set
langsmith evaluator delete accuracy --yes
```

### experiment—结果和摘要

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
langsmith experiment list --dataset my-eval-set
langsmith experiment get my-experiment-2024-01-15
```

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\langsmith\langsmith-cli.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>