gracefox-llm-hub 0.2.0

统一的LLM调用库，支持多种LLM提供商

LLM Hub - Unified LLM Calling Library

A unified calling library supporting multiple LLM providers (International + Chinese AI), providing a consistent API interface.

✨ Features

• 🔌 Unified API - One interface for all LLM providers
• 🌍 Multi-Provider Support - OpenAI, DeepSeek, Kimi, Gemini, Claude, etc.
• 🇨🇳 Chinese AI Support - Qwen, GLM, ERNIE, MiniCPM
• 💻 Local Deployment - Ollama, llama.cpp
• 🤔 Reasoning Mode - Display thinking process (DeepSeek support)
• 📊 Accurate Token Counting - Official tokenizers for each provider
• 📡 Streaming Output - Real-time response generation
• 💾 Configuration Management - JSON/YAML config, profiles, environment variables
• 🔌 Plugin System - Support for third-party Provider extensions

📋 Supported Providers

Provider	Type	Token Counting	Reasoning Mode
OpenAI	Cloud	✅ tiktoken	❌
DeepSeek	Cloud	✅ deepseek-tokenizer	✅
Kimi	Cloud	✅ API	❌
Google Gemini	Cloud	⚠️ Estimation	❌
Anthropic Claude	Cloud	⚠️ Estimation	❌
Qwen	Cloud	✅ qwen-tokenizer	❌
GLM	Cloud	✅ transformers	❌
ERNIE	Cloud	✅ transformers	❌
MiniCPM	Cloud/Local	✅ transformers	❌
Ollama	Local	✅ API tokenize	❌
llama.cpp	Local	✅ Subprocess	❌

🚀 Quick Start

Installation

# Basic installation
pip install gracefox-llm-hub

# Install environment sensing support (system resource monitoring)
pip install gracefox-llm-hub[env]

# Install accurate token counting
pip install gracefox-llm-hub[tokenizers]

# Install secure encryption support
pip install gracefox-llm-hub[secure]

# Install YAML config support
pip install gracefox-llm-hub[yaml]

# Install all features
pip install gracefox-llm-hub[all]

Basic Usage

from llm_hub import LLMClient, LLMConfig, Provider

# Create DeepSeek client
client = LLMClient(LLMConfig(
    provider=Provider.DEEPSEEK,
    model="deepseek-chat",
    api_key="your-api-key"
))

# Single round conversation
response = client.chat("What is artificial intelligence?")
print(response.content)

📖 Complete API usage examples can be found in the docs/ directory

⚙️ Configuration

Configuration File Format

{
    "provider": "deepseek",
    "model": "deepseek-chat",
    "api_key": "your-api-key",
    "temperature": 0.7,
    "max_tokens": 2000,
    "reasoning": true,
    "stream": true
}

Environment Variables

export LLM_PROVIDER=deepseek
export LLM_MODEL=deepseek-chat
export LLM_API_KEY=your-key
export LLM_TEMPERATURE=0.7

Configuration Priority (Low to High)

1. Default configuration
2. Environment variables
3. Configuration profiles
4. Configuration files
5. JSON string
6. Code parameters

📦 Project Structure

llm-hub/
├── llm_hub/
│   ├── core/           # Core functionality
│   │   ├── client.py   # Main client
│   │   ├── enums.py    # Enum definitions
│   │   └── exceptions.py # Exception definitions
│   ├── config/         # Configuration management
│   │   ├── config.py   # Configuration class
│   │   ├── manager.py  # Configuration manager
│   │   └── security.py # Encryption and security
│   ├── models/         # Data models
│   │   ├── message.py  # Message and Conversation
│   │   └── response.py # Response models
│   ├── providers/      # Provider implementations
│   │   ├── base.py     # Base classes
│   │   ├── factory.py  # Factory and plugin system
│   │   ├── deepseek.py # DeepSeek
│   │   ├── qwen.py     # Qwen
│   │   ├── glm.py      # GLM
│   │   ├── ernie.py    # ERNIE
│   │   ├── minicpm.py  # MiniCPM
│   │   └── ...
│   ├── environment/    # Environment sensing (optional)
│   └── utils/          # Utility functions
│       ├── token_counter.py  # Token counting
│       ├── stream_handler.py # Stream handling
│       ├── rate_limiter.py   # Rate limiting
│       └── logger.py         # Logging system
├── docs/               # API documentation and examples
├── examples/           # Example code
├── pyproject.toml      # Project configuration
└── README.md           # This document

🔧 Development Guide

# Clone repository
git clone https://gitee.com/SteHub/llm-hub.git
cd llm-hub

# Development installation
pip install -e .[dev,all]

# Code formatting
black llm_hub/

# Code linting
ruff check llm_hub/

# Type checking
mypy llm_hub/

🔌 Plugin System

LLM Hub supports third-party Provider extensions through the entry points mechanism.

Developing Third-party Providers

# setup.py
from setuptools import setup

setup(
    name="my-llm-provider",
    entry_points={
        "llm_hub.providers": [
            "my_provider = my_package:MyProvider",
        ]
    }
)

After installation, it will be automatically discovered without modifying llm_hub code.

🤝 Contributing

Contributions are welcome! Please feel free to submit Pull Requests.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing)
5. Open a Pull Request

📄 License

GNU General Public License v3.0 - See LICENSE file for details

📧 Contact

• Author: GraceFox
• Email: [e-mail]
• Homepage: https://gitee.com/SteHub/llm-hub
• Issues: https://gitee.com/SteHub/llm-hub/issues

---

Quick Reference

Installation Options

Option	Description	Dependencies
[env]	Environment sensing	psutil
[tokenizers]	Accurate token counting	tiktoken, transformers
[secure]	Secure encryption	cryptography
[yaml]	YAML configuration	pyyaml
[all]	All features	All of the above

Supported Providers

Provider	Config Value	Example Model
OpenAI	openai	gpt-3.5-turbo
DeepSeek	deepseek	deepseek-chat
Kimi	kimi	moonshot-v1-8k
Qwen	qwen	qwen-turbo
GLM	glm	glm-4-flash
ERNIE	ernie	ernie-3.5-8k
MiniCPM	minicpm	minicpm
Ollama	ollama	llama2
llama.cpp	llama_cpp	llama-2-7b

API Key Acquisition

Provider	URL
OpenAI	https://platform.openai.com/api-keys
DeepSeek	https://platform.deepseek.com/api_keys
Kimi	https://platform.moonshot.cn/console/apiKey
Qwen	https://dashscope.console.aliyun.com/apiKey
GLM	https://open.bigmodel.cn/usercenter/apikeys
ERNIE	https://console.bce.baidu.com/ai_platform/

---

📖 Complete API usage examples, streaming output, reasoning mode, token counting, and more detailed documentation can be found in the docs/ directory

⭐ If you find this useful, please give it a Star on Gitee!