kronoslabs 1.0.0

Official Python client for Kronos Labs API

Kronos Labs Python Client

Official Python client for the Kronos Labs API.

Installation

pip install kronoslabs

Quick Start

from kronoslabs import KronosLabs

# Initialize the client
client = KronosLabs(api_key="your-api-key-here")

# Non-streaming chat completion
response = client.chat.completions.create(
    prompt="Hello, how are you?",
    temperature=0.7,
    is_stream=False
)

print(response.choices[0].message.content)

# Streaming chat completion
stream = client.chat.completions.create(
    prompt="Tell me a story",
    temperature=0.7,
    is_stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Features

• Simple and intuitive API similar to OpenAI's ChatGPT client
• Support for both streaming and non-streaming responses
• Automatic handling of API authentication
• Comprehensive error handling
• Type hints for better IDE support

API Reference

Initialize Client

client = KronosLabs(api_key="your-api-key")

Chat Completions

response = client.chat.completions.create(
    messages=[],  # Optional: list of message dicts
    prompt="Your prompt here",  # Required: the prompt text
    temperature=0.7,  # Optional: controls randomness (0.0-2.0)
    is_stream=False,  # Optional: enable streaming
    tool=True  # Optional: enable tool usage
)

Parameters

• messages (list, optional): List of message dictionaries with 'role' and 'content' keys
• prompt (str, required): The prompt text to send to the model
• temperature (float, optional): Controls randomness in the response (0.0-2.0). Default: 0.7
• is_stream (bool, optional): Enable streaming responses. Default: False
• tool (bool, optional): Enable tool usage. Default: True

Response Format

Non-streaming response:

{
    "id": "chatcmpl_...",
    "object": "chat.completion",
    "created": 1234567890,
    "model": "hyperion-1.5b-chat",
    "choices": [{
        "index": 0,
        "message": {
            "role": "assistant",
            "content": "Response text"
        },
        "finish_reason": "stop"
    }],
    "usage": {
        "prompt_tokens": 10,
        "completion_tokens": 20,
        "total_tokens": 30
    }
}

Streaming response (yields chunks):

{
    "id": "chatcmpl_...",
    "object": "chat.completion.chunk",
    "created": 1234567890,
    "model": "hyperion-1.5b-chat",
    "choices": [{
        "index": 0,
        "delta": {
            "content": "token"
        },
        "finish_reason": null
    }]
}

Error Handling

from kronoslabs import KronosLabs, APIError, AuthenticationError

client = KronosLabs(api_key="your-api-key")

try:
    response = client.chat.completions.create(prompt="Hello")
except AuthenticationError as e:
    print(f"Authentication failed: {e}")
except APIError as e:
    print(f"API error: {e.message}, Status: {e.status_code}")

License

MIT License