Quick Start: Creating Your First LLM Instance

Learn how to create and use an LLM instance with SimplerLLM in just a few lines of code.

Installation

First, install SimplerLLM using pip:

pip install simplerllm

Setting Up API Keys

Create a .env file in your project root and add your API keys:

# .env file
OPENAI_API_KEY=your_openai_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
GEMINI_API_KEY=your_gemini_api_key
# Add other provider keys as needed

Creating Your First LLM Instance

Here's how to create an LLM instance and generate your first response:

from SimplerLLM.language.llm import LLM, LLMProvider

# Create an LLM instance with OpenAI
llm = LLM.create(
    provider=LLMProvider.OPENAI,
    model_name="gpt-4o"
)

# Generate a response
response = llm.generate_response(
    prompt="Explain quantum computing in simple terms"
)

print(response)

Step-by-Step Explanation

from SimplerLLM.language.llm import LLM, LLMProvider

llm = LLM.create(
    provider=LLMProvider.OPENAI,
    model_name="gpt-4o"
)

response = llm.generate_response(
    prompt="Explain quantum computing in simple terms"
)

Trying Different Providers

SimplerLLM makes it easy to switch between providers. Here are examples for each supported provider:

OpenAI

llm = LLM.create(
    provider=LLMProvider.OPENAI,
    model_name="gpt-4o"
)

Anthropic Claude

llm = LLM.create(
    provider=LLMProvider.ANTHROPIC,
    model_name="claude-3-5-sonnet-20241022"
)

Google Gemini

llm = LLM.create(
    provider=LLMProvider.GEMINI,
    model_name="gemini-1.5-pro"
)

Cohere

llm = LLM.create(
    provider=LLMProvider.COHERE,
    model_name="command-r-plus"
)

DeepSeek

llm = LLM.create(
    provider=LLMProvider.DEEPSEEK,
    model_name="deepseek-chat"
)

OpenRouter (100+ Models)

llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="openai/gpt-4o"
)

Ollama (Local Models)

llm = LLM.create(
    provider=LLMProvider.OLLAMA,
    model_name="llama2"
)

Customizing Parameters

You can customize the LLM behavior with additional parameters:

llm = LLM.create(
    provider=LLMProvider.OPENAI,
    model_name="gpt-4o",
    temperature=0.7,      # Controls randomness (0.0 to 2.0)
    top_p=1.0,           # Controls diversity via nucleus sampling
    api_key="your_key"   # Optional: Override environment variable
)

Complete Example

Here's a complete working example you can run:

from SimplerLLM.language.llm import LLM, LLMProvider

def main():
    # Create LLM instance
    llm = LLM.create(
        provider=LLMProvider.OPENAI,
        model_name="gpt-4o",
        temperature=0.7
    )

    # Define your prompt
    prompt = """
    Write a short poem about artificial intelligence
    and its impact on humanity. Make it inspiring.
    """

    # Generate response
    print("Generating response...")
    response = llm.generate_response(prompt=prompt)

    # Display result
    print("\nResponse:")
    print(response)

if __name__ == "__main__":
    main()

Expected Output

When you run the example above, you'll get a response like:

Generating response...

Response:
In circuits bright and minds of steel,
A future dawns with dreams surreal.
Artificial thoughts that learn and grow,
Expanding all we'll ever know.

Through data streams and neural fire,
We build machines that never tire.
Not to replace the human heart,
But amplify our creative art...

What's Next?

Now that you know how to create an LLM instance, explore these advanced features: