Cortiqa AI Python SDK

Official Python client library for Cortiqa AI and Falin Foundation Models. Built for enterprise scalability, agentic workflows, and ultra-fast inference.

⚡ Installation

pip install cortiqa

Or install with development dependencies:

pip install "cortiqa[dev]"

🚀 Quickstart

Set your API key as an environment variable:

export CORTIQA_API_KEY="sk-cortiqa-your-api-key"

Then create your first completion:

from cortiqa import Cortiqa

client = Cortiqa()

response = client.chat.completions.create(
    model="falin-01",
    messages=[
        {"role": "system", "content": "You are a helpful assistant by Cortiqa."},
        {"role": "user", "content": "Explain quantum computing in two sentences."}
    ],
    temperature=0.7,
)

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

🌊 Real-Time Streaming

Stream tokens in real-time as they are generated by the model:

from cortiqa import Cortiqa
import sys

client = Cortiqa()

stream = client.chat.completions.create(
    model="falin-01",
    messages=[
        {"role": "user", "content": "Write a short poem about sunrise in the Himalayas."}
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        sys.stdout.write(chunk.choices[0].delta.content)
        sys.stdout.flush()

⚡ Asynchronous Support

High-concurrency async client using AsyncCortiqa:

import asyncio
from cortiqa import AsyncCortiqa

async def main():
    async with AsyncCortiqa() as client:
        response = await client.chat.completions.create(
            model="falin-pro",
            messages=[
                {"role": "user", "content": "Write a fast Go concurrent worker pool."}
            ]
        )
        print(response.choices[0].message.content)

asyncio.run(main())

🧠 Available Cortiqa Models

To query live models directly:

models = client.models.list()
for m in models:
    print(m.id, "-", m.description)

⚙️ Configuration & Options

client = Cortiqa(
    api_key="sk-cortiqa-...",                # Default: CORTIQA_API_KEY
    base_url="https://api.cortiqa.co",       # Default: https://api.cortiqa.co
    timeout=60.0,                            # Request timeout in seconds
    max_retries=2,                           # Auto-retries on transient failuress
)

🛡️ Error Handling

The SDK provides typed exceptions for predictable error handling:

from cortiqa import Cortiqa
from cortiqa.exceptions import AuthenticationError, RateLimitError, APIError

client = Cortiqa()

try:
    response = client.chat.completions.create(
        model="falin-01",
        messages=[{"role": "user", "content": "Hello!"}]
    )
except AuthenticationError:
    print("Invalid API Key! Check your sk-cortiqa key.")
except RateLimitError:
    print("Rate limit reached! Please slow down requests.")
except APIError as e:
    print(f"API failed with status {e.status_code}: {e.message}")

📄 License

MIT © Cortiqa AI