Making Your First Request

This guide walks you through making your first LLM request using AiCore.

Prerequisites

• Completed installation
• Valid API key for your chosen provider
• Basic Python knowledge

Basic Usage

1. First, import the required modules:

from aicore.llm import Llm
from aicore.llm.config import LlmConfig

2. Configure your LLM provider (example using OpenAI):

config = LlmConfig(
    provider="openai",
    api_key="your_api_key_here",
    model="gpt-4o"
)

3. Initialize the LLM client:

llm = Llm(config=config)

4. Make your first request:

response = llm.complete("Hello world!")
print(response)

Async Usage

For asynchronous applications:

import asyncio
from aicore.llm import Llm
from aicore.llm.config import LlmConfig

async def main():
    config = LlmConfig(
        provider="openai",
        api_key="your_api_key_here",
        model="gpt-4o"
    )
    llm = Llm(config=config)
    
    response = await llm.acomplete("Hello async world!")
    print(response)

asyncio.run(main())

Configuration Options

You can customize your requests with:

• temperature: Controls randomness (0-1)
• max_tokens: Limits response length
• stream: Enables streaming responses

Example with custom settings:

response = llm.complete(
    "Explain quantum computing",
    temperature=0.7,
    max_tokens=500,
    stream=True
)

Next Steps

• Learn about advanced configuration
• Explore provider-specific features
• Check out usage tracking for cost monitoring
• Try the examples for more complex scenarios