LMITF - Large Model Interface
LMITF (Large Model Interface) 为与大型语言模型和视觉模型交互提供了一个灵活、简洁的Python接口。
✨ 特性
- 🚀 简单易用 - 直观的API设计,快速上手
- 🔧 灵活配置 - 支持多种API端点和环境配置
- 📊 内置定价 - 集成成本追踪和使用分析
- 🎯 模板系统 - 预构建模板和自定义提示管理
- 🖼️ 视觉模型 - 支持图像分析和多模态AI任务
- 📖 完整文档 - 详尽的使用指南和API参考
📚 文档
‼️(文档由claude code生成,不太准确,无误版请参考下方的 ## 📖 示例)
完整文档: https://colehank.github.io/AI-interface/
🚀 快速开始
安装
pip install lmitf
基本使用
from lmitf import BaseLLM
llm = BaseLLM()
response = llm.call("你好,请介绍一下人工智能")
print(response)
📋 项目简介
LMITF (Large Model Interface) 为与聚合API平台交互提供了一个灵活的接口,支持:
- 文本生成 - 基于BaseLLM的语言模型交互
- 图像理解 - 基于BaseLVM的视觉语言模型
- 模板系统 - TemplateLLM支持复用提示模板
- 成本管理 - 内置定价追踪和使用分析
🔧 环境配置
创建.env文件:
OPENAI_API_KEY=你的API密钥
OPENAI_BASE_URL=https://api.openai.com/v1
📖 示例
- LLM使用: example_llm.ipynb
- 视觉模型: example_lvm.ipynb
- 定价查询: example_price.ipynb
🤝 贡献
欢迎贡献代码!请查看贡献指南了解详情。
📄 许可证
本项目采用 MIT 许可证 - 查看 LICENSE 文件了解详情。
👨💻 作者
Guohao Zhang - guohao2045@gmail.com
🌟 如果这个项目对您有帮助,请给个星标支持!
Metadata
Release files for lmitf 0.1.24
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| lmitf-0.1.24.tar.gz | 30.6 MB | Without provenance | Details for lmitf-0.1.24.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| lmitf-0.1.24-py3-none-any.whl | Python 3 | none | any | Details for lmitf-0.1.24-py3-none-any.whl |
Total release size: 31.1 MB
Release files / lmitf-0.1.24.tar.gz
| Download URL | lmitf-0.1.24.tar.gz |
|---|---|
| Size | 30.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ac8fc336b5df1621c5058b39667c8e420a0a462ccfbb5aeefcaed8f038d46f20
|
|
BLAKE2b-256 checksum How to use checksums |
24449a186aa19e15122b2cd918f1f3e79017a5f49a96e9ca258d2e6f52530338
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-requests/2.32.4
|
Release files / lmitf-0.1.24-py3-none-any.whl
| Download URL | lmitf-0.1.24-py3-none-any.whl |
|---|---|
| Size | 507.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
926e1a5fe8432b759ba58c0e5e4f5f376bcfc3c295af4a5a7e66f726898ac92e
|
|
BLAKE2b-256 checksum How to use checksums |
f9a24f9d0482c72c2c8523c9458054b347e9ba4bccaa34aaab6abe473f4f3b7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-requests/2.32.4
|
Security for lmitf 0.1.24
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.