Skip to main content

llm-toolforge

用于大模型工具调用的框架,同时提供 HTTP API(同步、流式、异步)和MCP Server两种接入方式。

安装

任选一种方式安装:

从 PyPI 安装(推荐)

pip install llm-toolforge

从源码安装(开发)

pip install -e .

验证

toolforge --help

使用

从零开始

  1. 创建项目
toolforge new project my-app   # 创建 ./my-app/ 并生成项目初始文件
# 或者
toolforge new project .        # 在当前目录初始化项目(目录已存在时使用)
  1. 创建工具
toolforge new tool <name> 

默认工具代码是获取当前时间,可以根据示例代码进行修改。详细说明见工具开发指南

  1. 编辑配置文件 配置文件位于项目根目录下的 config.yaml,默认配置即可运行。各字段含义见文件内注释。

  2. 启动 在项目根目录执行,可以在页面http://localhost:12345进行测试。

toolforge run 

使用示例工程

  1. 安装环境
cd examples
pip install -r requirements.txt
  1. 编辑 config.yaml,按注释填写配置

  2. 运行

toolforge run

打开页面http://localhost:12345进行测试。

部署

toolforge new project 会在项目目录下生成 Dockerfile

docker build -t llm-toolforge-example:v0.1.0 .

docker run --rm \
  -v "$(pwd)/config.yaml:/app/config.yaml" \
  -e SERVICE_NAME=llm-toolforge-example \
  -p 12345:12345 \
  -p 12346:12346 \ 
  llm-toolforge-example:v0.1.0

运行自动化测试

参与框架开发时,先在项目根目录安装源码及测试依赖:

python -m pip install -e ".[test]"

以后每次修改代码后,在项目根目录运行:

python -m pytest

环境变量

少量字段可由环境变量覆盖(优先级高于 config.yaml):

变量 覆盖字段
SERVICE_NAME service.name
SERVICE_VERSION service.version

K8s 多实例部署时推荐通过 Deployment 注入 SERVICE_NAME,避免镜像里写死。


Download files

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

Source Distribution

llm_toolforge-0.6.3.tar.gz (6.4 MB view details)

Uploaded Source

Built Distribution

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

llm_toolforge-0.6.3-py3-none-any.whl (6.4 MB view details)

Uploaded Python 3

File details

Details for the file llm_toolforge-0.6.3.tar.gz.

File metadata

  • Download URL: llm_toolforge-0.6.3.tar.gz
  • Upload date:
  • Size: 6.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for llm_toolforge-0.6.3.tar.gz
Algorithm Hash digest
SHA256 114a8f6256c0f7b643295811250ae680f80c82839650d988b43ec11910ab4680
MD5 5b6df2a1c4f44c7c0b2127165d2f14e5
BLAKE2b-256 5d7216ca4c2df3781bc491211a9c5d5ffada658b98c43f7b81f141c3966ca881

See more details on using hashes here.

File details

Details for the file llm_toolforge-0.6.3-py3-none-any.whl.

File metadata

  • Download URL: llm_toolforge-0.6.3-py3-none-any.whl
  • Upload date:
  • Size: 6.4 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for llm_toolforge-0.6.3-py3-none-any.whl
Algorithm Hash digest
SHA256 500ab2ef5202502a7ef99ed6d1d1a5034e20a9f3099c813b3e9828d0d8081885
MD5 968971f476f939fe56af381d3c0e613d
BLAKE2b-256 c146c5edb486119b7152bc3a11e458dff1e9824f2d70be1b619574ddf7347552

See more details on using hashes here.

Release history Release notifications | RSS feed

0.8.1

2 files

0.8.0

2 files

0.7.3

2 files

0.7.2

2 files

0.7.1

2 files

0.7.0

2 files

This release

0.6.3 This release

2 files

0.6.0

2 files

0.5.9

2 files

0.5.8

2 files

0.5.7

2 files

0.5.6

2 files

0.5.5

2 files

0.5.4

2 files

0.5.3

2 files

0.5.2

2 files

0.5.1

2 files

0.5.0

2 files

0.4.1

2 files

0.4.0

2 files

0.3.2

2 files

0.3.1

2 files

0.3.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page