aihuber 0.3.0

⚡ Python AI SDK - OpenAI, MistralAI, Anthropic, Google Gemini, XAI Grok, Hugging Face

AIHuber

aihuber is the easiest and quickest way to communicate with AI providers. Free and open-source.

✨ Features

aihuber is compatible with main AI providers :

Chat completion (Text generation)

AI Providers Comparison

AI Provider	Buffering sync & async	Streaming (sync & async)	Endpoint
OpenAI	✅	✅	https://api.openai.com/v1/chat/completions
Mistral AI	✅	✅	https://api.mistral.ai/v1/chat/completions
Anthropic	✅	✅	https://api.anthropic.com/v1/messages
Google (Gemini)	❌	❌	https://generativelanguage.googleapis.com/v1/models/{model}:generateContent
Cohere	✅	✅	https://api.cohere.com/v2/chat
Together AI	✅	✅	https://api.together.xyz/v1/chat/completions
Replicate	❌	❌	https://api.replicate.com/v1/predictions
Hugging Face	❌	❌	https://api-inference.huggingface.co/models/{model_id}
Azure OpenAI	❌	❌	https://{your-resource-name}.openai.azure.com/openai/deployments/{deployment-name}/chat/completions?api-version=2024-02-01
AWS Bedrock	❌	❌	https://bedrock-runtime.{region}.amazonaws.com/model/{model-id}/invoke
Perplexity	✅	✅	https://api.perplexity.ai/chat/completions
xAI (Grok)	❌	❌	https://api.x.ai/v1/chat/completions

Legend

• ✅ = Available
• ❌ = Not Available
• Text in parentheses = Specific service/model name

🚀 Quick Start

Installation

pip install aihuber

Or with uv:

uv add aihuber

Basic Usage

import asyncio
import os

from dotenv import load_dotenv

from aihuber import LLM, Message
from pydantic import SecretStr

load_dotenv()

MISTRAL_AI_TOKEN = SecretStr(os.getenv("MISTRAL_AI_TOKEN"))  # type: ignore


async def main():
    """Chat completion example with asynchronous"""
    llm = LLM(model="mistral:mistral-small-latest", api_key=MISTRAL_AI_TOKEN)

    messages = [
        Message(role="system", content="You are a helpful Python developer assistant."),
        Message(role="user", content="Give me 10 numbers from 0"),
    ]

    async_chat_completion = await llm.chat_completion_async(messages, stream=True)
    async for chunk in async_chat_completion:
        print(chunk)

if __name__ == "__main__":
    asyncio.run(main())

📄 License

MIT