# x-langsmith

**Repository Path**: chain-engine/x-langsmith

## Basic Information

- **Project Name**: x-langsmith
- **Description**: 一个完整的 LangSmith（可观测性平台） 学习与实践项目
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-02-24
- **Last Updated**: 2026-02-24

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# x-langsmith

## Project Positioning
`x-langsmith` is a comprehensive LangSmith (observability platform) learning and practice project, designed to help developers quickly master LangSmith's core features and best practices, and build observable, debuggable, and optimizable large language model applications.

## What is LangSmith
LangSmith is an observability platform specifically designed for LLM applications, developed and maintained by the LangChain team. It provides a complete toolchain for tracing, evaluating, monitoring, and optimizing applications based on large language models.

### Relationship between LangSmith and LangChain
- **Same Ecosystem**: Both LangSmith and LangChain belong to the LangChain ecosystem and are developed by the same team
- **Complementary Functions**: LangChain provides the framework and tools for building LLM applications, while LangSmith provides the ability to observe, evaluate, and monitor these applications
- **Seamless Integration**: LangSmith can be seamlessly integrated with LangChain applications, automatically capturing and analyzing application runtime data
- **Independent Use**: Although deeply integrated with LangChain, LangSmith can also be used independently to monitor LLM applications not built with LangChain

## Software Architecture
The project adopts a modular architecture design, mainly including the following components:
- **Core Examples**: Sample code demonstrating various LangSmith features
- **Configuration Module**: LangSmith connection and configuration management
- **Toolset**: Utility tools for auxiliary development and testing

## Project Structure
The project directory structure is as follows:
```
x-langsmith/
├── .gitee/            # Gitee configuration files
├── examples/          # LangSmith example code
│   └── basic_tracing.py  # Basic tracing functionality example
├── .gitignore         # Git ignore file configuration
├── .python-version    # Python version specification
├── LICENSE            # MIT license file
├── README.en.md       # English README document
├── README.md          # Chinese README document
├── pyproject.toml     # Project configuration and dependency management
└── uv.lock            # Dependency version lock file
```

## Installation

1. **Environment Requirements**: Python 3.9 or higher
2. **Install Dependencies**: Use uv to manage project dependencies
   ```bash
   uv install
   ```
3. **Configure LangSmith**: Set environment variables
   ```bash
   export LANGSMITH_TRACING=true
   export LANGSMITH_API_KEY=your_api_key
   ```

## Usage

1. **Clone the project**:
   ```bash
   git clone https://gitee.com/chain-engine/x-langsmith.git
   cd x-langsmith
   ```
2. **Run Examples**:
   ```bash
   python examples/basic_tracing.py
   ```
3. **View Tracing Data**: Access the LangSmith console to view application runtime data
4. **Evaluate Application**: Use LangSmith's evaluation tools to assess application performance

## Contribution

1. Fork the repository
2. Create Feat_xxx branch
3. Commit your code
4. Create Pull Request

## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.