ai-python-lab 0.1.0

Simple and easy-to-use Python client for OpenRouter API that provides access to various AI models.

AI Python Lab - OpenRouter Client

A simple and easy-to-use Python client for the OpenRouter API that provides access to various AI models.

Installation

pip install ai-python-lab

Quick Start

Environment Setup

Set your OpenRouter API key as an environment variable:

export OPENROUTER_API_KEY="your-api-key-here"

Basic Usage

from ai_python_lab import OpenRouterClient

# Initialize client
client = OpenRouterClient()

# Simple chat
response = client.simple_chat("What is the meaning of life?")
print(response)

# Chat with conversation history
messages = [
    {"role": "user", "content": "Hello, how are you?"},
    {"role": "assistant", "content": "I'm doing well, thank you! How can I help you today?"},
    {"role": "user", "content": "Can you explain quantum computing?"}
]

response = client.chat(messages)
print(response)

Using Different Models

# Use a specific model
response = client.simple_chat(
    "Explain machine learning in simple terms",
    model="anthropic/claude-3-haiku"
)

# Set default model for the client
client = OpenRouterClient(default_model="openai/gpt-4")

Quick Functions

For simple one-off requests:

from ai_python_lab import quick_chat, ask_ai

# Quick chat function
response = quick_chat("Tell me a joke")
print(response)

# Even simpler alias
response = ask_ai("What's the weather like?")
print(response)

Advanced Configuration

client = OpenRouterClient(
    api_key="your-api-key",
    site_url="https://your-site.com",
    site_name="Your Site Name",
    default_model="openrouter/cypher-alpha:free"
)

# Chat with custom parameters
response = client.chat(
    messages=[{"role": "user", "content": "Write a poem"}],
    temperature=0.8,
    max_tokens=200,
    top_p=0.9
)

Error Handling

from ai_python_lab import OpenRouterClient
from ai_python_lab.exceptions import AuthenticationError, APIError, RateLimitError

try:
    client = OpenRouterClient(api_key="invalid-key")
    response = client.simple_chat("Hello")
except AuthenticationError as e:
    print(f"Authentication failed: {e}")
except RateLimitError as e:
    print(f"Rate limit exceeded: {e}")
except APIError as e:
    print(f"API error: {e}")

Getting Available Models

# Get list of available models
models = client.get_models()
for model in models:
    print(f"Model: {model['id']}")

API Reference

OpenRouterClient

Main client class for interacting with OpenRouter API.

Constructor

OpenRouterClient(
    api_key: Optional[str] = None,
    base_url: str = "https://openrouter.ai/api/v1",
    site_url: Optional[str] = None,
    site_name: Optional[str] = None,
    default_model: str = "openrouter/cypher-alpha:free"
)

Methods

• chat(messages, model=None, **kwargs) - Send chat completion request
• simple_chat(message, model=None, **kwargs) - Send simple message
• get_models() - Get available models

Parameters

• messages: List of message dictionaries with 'role' and 'content'
• model: Model to use (optional, uses default if not specified)
• temperature: Sampling temperature (0.0 to 2.0)
• max_tokens: Maximum tokens to generate
• top_p: Nucleus sampling parameter
• frequency_penalty: Frequency penalty (-2.0 to 2.0)
• presence_penalty: Presence penalty (-2.0 to 2.0)
• stop: Stop sequences

Quick Functions

• quick_chat(message, api_key=None, model="openrouter/cypher-alpha:free", **kwargs)
• ask_ai(message, **kwargs) - Alias for quick_chat

Exceptions

• OpenRouterError - Base exception
• APIError - API-related errors
• AuthenticationError - Authentication failures
• RateLimitError - Rate limit exceeded

Examples

Basic Chat Bot

from ai_python_lab import OpenRouterClient

client = OpenRouterClient()

while True:
    user_input = input("You: ")
    if user_input.lower() in ['quit', 'exit']:
        break
    
    response = client.simple_chat(user_input)
    print(f"AI: {response}")

Multi-turn Conversation

from ai_python_lab import OpenRouterClient

client = OpenRouterClient()
conversation = []

while True:
    user_input = input("You: ")
    if user_input.lower() in ['quit', 'exit']:
        break
    
    # Add user message to conversation
    conversation.append({"role": "user", "content": user_input})
    
    # Get AI response
    response = client.chat(conversation)
    print(f"AI: {response}")
    
    # Add AI response to conversation
    conversation.append({"role": "assistant", "content": response})

Using with Different Models

from ai_python_lab import OpenRouterClient

client = OpenRouterClient()

# Try different models
models = [
    "openrouter/cypher-alpha:free",
    "anthropic/claude-3-haiku",
    "openai/gpt-3.5-turbo"
]

question = "What is artificial intelligence?"

for model in models:
    try:
        response = client.simple_chat(question, model=model)
        print(f"\n{model}:")
        print(response)
    except Exception as e:
        print(f"Error with {model}: {e}")

Requirements

• Python 3.7+
• openai >= 1.0.0
• requests >= 2.25.1

License

MIT License

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

If you encounter any issues or have questions, please open an issue on GitHub.