Skip to main content

LangChain/LangGraph-based agent utilities for CodeBaseX.

Project description

langchain_agentx

langchain_agentx 是一组基于 LangChain / LangGraph 的“代码智能体”工具函数,帮助你在自己的项目里快速集成:

  • OpenCode 风格的 LangGraph Agent(代码理解、重构、分析)
  • DeepAgent 兼容的 Agent 工厂
  • 上下文感知中间件、性能监控等基础设施

安装

发布到 PyPI 后,你可以直接通过 pip 安装:

pip install langchain-agentx

快速上手

from langchain_agentx import create_opencode_style_agent, create_opencode_style_deepagent

# 这里省略 LangChain / LangGraph 相关模型与工具配置
agent = create_opencode_style_agent(...)
deep_agent = create_opencode_style_deepagent(...)

具体的能力和使用方式可以参考源码中的 docstring 以及各模块下的 README.md

发布新版本流程(备忘)

以下命令默认在项目根目录(c:\git_code\langchain_agentx)并已激活 kw_venv

1. 准备代码与版本号

  • 修改版本号:编辑 pyproject.toml
    • [project] 里的 version = "0.x.y" 改成新版本(例如 0.2.0)。
  • 确认工作区干净
    • 运行 git status,确认只有本次要发版的变更。

2. 安装构建与发布工具

只需偶尔执行一次(环境更新或新机器时):

python -m pip install -U build twine

3. 本地构建分发包

在项目根目录执行:

python -m build

构建成功后会生成:

  • dist/langchain_agentx-<version>.tar.gz
  • dist/langchain_agentx-<version>-py3-none-any.whl

4. 上传到 TestPyPI(可选,推荐先试)

  1. 在浏览器里登录 https://test.pypi.org/,创建/获取 API token。
  2. 在本机用户目录创建/编辑 ~/.pypirc
[distutils]
index-servers =
    testpypi

[testpypi]
  username = __token__
  password = pypi-xxxxxxxxxxxxxxxxxxxx
  1. 运行上传命令:
python -m twine upload --repository testpypi dist/*
  1. 在一个干净的虚拟环境里测试安装:
python -m pip install -i https://test.pypi.org/simple/ langchain-agentx==<version>

5. 上传到正式 PyPI

  1. 在浏览器里登录 https://pypi.org/,创建/获取 API token。
  2. ~/.pypirc 中增加正式仓库配置(若尚未配置):
[distutils]
index-servers =
    pypi
    testpypi

[pypi]
  username = __token__
  password = pypi-xxxxxxxxxxxxxxxxxxxx

[testpypi]
  username = __token__
  password = pypi-xxxxxxxxxxxxxxxxxxxx
  1. 上传到 PyPI:
python -m twine upload dist/*

6. 打 Tag 并推送(可选但推荐)

git add .
git commit -m "release: langchain-agentx <version>"
git tag v<version>
git push
git push --tags

下次发布时按本节从上到下依次执行即可。***

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_agentx-0.1.1.tar.gz (109.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_agentx-0.1.1-py3-none-any.whl (131.6 kB view details)

Uploaded Python 3

File details

Details for the file langchain_agentx-0.1.1.tar.gz.

File metadata

  • Download URL: langchain_agentx-0.1.1.tar.gz
  • Upload date:
  • Size: 109.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for langchain_agentx-0.1.1.tar.gz
Algorithm Hash digest
SHA256 1778d165b2f0685188f8a44194dd185eb9b65e75806f7d13d279ddbea527f5e8
MD5 a5806dbb16f7581db3a1541c46ddfd34
BLAKE2b-256 775d62ba9509dfdad023acb3df1d976de608bc67395c706aeff3cffe3f3699e5

See more details on using hashes here.

File details

Details for the file langchain_agentx-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_agentx-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 5580a040ff2e0f50b9331d3db057d5ee39732a6081beae565a20946f7868b89c
MD5 fc2b544346cfdcc69c83b6c31617bed6
BLAKE2b-256 d032298f07467457e0c9c1e05a845f337f9aa55c1ef81d23e1ff093108c6846c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page