alveare 0.1.0

Python SDK for the Alveare Private SLM Inference-as-a-Service platform

Alveare Python SDK

Python client for the Alveare Private SLM Inference-as-a-Service platform.

Installation

pip install alveare

Quick start

from alveare import Alveare

client = Alveare(api_key="alv_live_...")

# Native inference
result = client.infer(
    specialist="summarise",
    prompt="Summarise this quarterly report...",
    max_tokens=256,
)
print(result.text)

# OpenAI-compatible chat completions
completion = client.chat.completions.create(
    model="alveare-summarise",
    messages=[{"role": "user", "content": "Summarise this..."}],
    max_tokens=256,
)
print(completion.choices[0].message.content)

Async usage

import asyncio
from alveare import AsyncAlveare

async def main():
    async with AsyncAlveare(api_key="alv_live_...") as client:
        result = await client.infer(specialist="summarise", prompt="...")
        print(result.text)

asyncio.run(main())

Configuration

Parameter	Environment variable	Default
api_key	ALVEARE_API_KEY	required
base_url	ALVEARE_BASE_URL	https://api.alveare.ai
timeout	--	60.0
max_retries	--	3

Error handling

from alveare import Alveare, AuthenticationError, RateLimitError, APIError

client = Alveare(api_key="alv_live_...")

try:
    result = client.infer(specialist="summarise", prompt="...")
except AuthenticationError:
    print("Check your API key")
except RateLimitError as e:
    print(f"Rate limited. Retry after {e.retry_after}s")
except APIError as e:
    print(f"API error {e.status_code}: {e.message}")

Requirements

• Python 3.9+
• httpx (installed automatically)

License

MIT