LangChain & LangGraph 学习项目
核心概念
LangChain
LangChain 是一个用于构建基于语言模型应用的框架,主要功能包括:
- 组件化架构:提供模块化组件(LLMs、记忆、索引等)
- 链式调用:将多个组件连接成工作流(Chains)
- 记忆功能:支持对话历史管理
- 数据增强:可与外部数据源集成(Retrieval-Augmented Generation)
- 工具集成:支持调用外部API和工具
LangGraph
LangGraph 是建立在LangChain之上的框架,专注于:
- 状态机模型:基于状态转换的流程控制
- 循环工作流:支持多轮对话和复杂流程
- 分布式执行:可扩展的分布式任务处理
- 可视化调试:提供流程可视化工具
API参考
langchain api https://python.langchain.com/api_reference/reference.html
langgraph api https://langchain-ai.github.io/langgraph/concepts/why-langgraph/
安装
uv build
技术栈
核心框架
- LangChain (v0.3.25+)
- LangGraph (v0.4.8+)
主要模块
-
语言模型集成:
- langchain-openai (OpenAI接口)
- langchain-google-genai (Google Gemini接口)
- langchain-deepseek (DeepSeek模型)
- langchain-nvidia-ai-endpoints (NVIDIA接口)
-
数据连接器:
- langchain-chroma (向量数据库)
- langchain-community (社区贡献连接器)
- psycopg2-binary (PostgreSQL连接)
-
工具扩展:
- yfinance (金融数据)
- arxiv (学术论文)
- Faker (测试数据生成)
-
部署与监控:
- Flask + Flask-SocketIO (Web服务)
- Gradio (快速UI构建)
- watchdog (文件监控)
- loguru (日志记录)
Metadata
Release files for tut-langgraph 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| tut_langgraph-0.1.1.tar.gz | 3.5 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tut_langgraph-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.2 MB
Release files / tut_langgraph-0.1.1.tar.gz
| Download URL | tut_langgraph-0.1.1.tar.gz |
|---|---|
| Size | 3.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0e7d25549450681bfa2a167abe64fe84c38db2624ab9e8b339a39ba93da6f43c
|
|
BLAKE2b-256 checksum How to use checksums |
e26fef81523d7cec141f5fdb4a2c0ab66645e50a756e0d0027ac7e04184721d7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Release files / tut_langgraph-0.1.1-py3-none-any.whl
| Download URL | tut_langgraph-0.1.1-py3-none-any.whl |
|---|---|
| Size | 4.7 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cb751c2ab95287a1d00ec7ae4946ce35674703aae3ec756db3805b23a5823466
|
|
BLAKE2b-256 checksum How to use checksums |
d18e9db163299ac541c41838a3d7d63b79e27c2f01173e2dbd74af371d715e2f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|