latentkit 0.1.0

Python client for the LatentKit gateway (OpenAI-compatible /v1 HTTP API).

LatentKit Python SDK

Official Python client for the canonical LatentKit /v1 API.

Install

pip install latentkit

Requires Python 3.10+.

Quickstart

from latentkit import LatentKit, LatentKitAPIError

client = LatentKit(api_key="YOUR_RAW_KEY")
try:
    response = client.chat.create(
        messages=[{"role": "user", "content": "Say hello from LatentKit."}],
        max_tokens=100,
        response_profile="balanced",
    )
    print(response["content"])
except LatentKitAPIError as exc:
    print(exc.status_code, exc.body)
client.close()

Async

import asyncio

from latentkit import AsyncLatentKit


async def main() -> None:
    async with AsyncLatentKit(api_key="YOUR_RAW_KEY") as client:
        response = await client.completions.create(
            prompt="Write a short product description for LatentKit.",
            system="Respond in one sentence.",
        )
        print(response["content"])


asyncio.run(main())

Timeouts and custom clients

LatentKit(...) and AsyncLatentKit(...) create httpx clients with a default timeout of 120s.

If you inject your own http_client, configure timeouts on that client yourself:

import httpx
from latentkit import LatentKit

http_client = httpx.Client(timeout=30.0)
client = LatentKit(api_key="YOUR_RAW_KEY", http_client=http_client)

Streaming

from latentkit import LatentKit

with LatentKit(api_key="YOUR_RAW_KEY") as client:
    for event in client.chat.stream(
        messages=[{"role": "user", "content": "Count from one to five."}],
    ):
        if event.event == "error":
            raise RuntimeError(event.data)
        if event.is_done:
            break
        print(event.data["delta"], end="")

Response profiles

Pass response_profile to ask the assigned policy for a speed/depth tradeoff:

response = client.chat.create(
    messages=[{"role": "user", "content": "Give me the short version."}],
    response_profile="fast",
)

Allowed values are fast, balanced, and deep. The assigned policy controls whether request overrides are allowed and which routes are eligible for each profile.

Agent sessions

from latentkit import LatentKit

with LatentKit(api_key="YOUR_RAW_KEY") as client:
    session = client.agents.sessions.create(
        task="Inspect the repo and explain the auth flow",
        workspace_root="/workspace",
        permission_mode="workspace-write",
    )
    queued = client.agents.sessions.run(session["id"])
    print(queued)

See docs/latentkit-coder-api.md for the full agent session request/response model.

Modalities

with LatentKit(api_key="YOUR_RAW_KEY") as client:
    client.embeddings.create(input=["hello world"], dimensions=256)
    client.image.generate(prompt="A clean product icon", size="1024x1024")
    client.speech.create(input="Hello from LatentKit.", voice="alloy")
    client.transcription.create(audio={"base64": "..."}, language="en")
    client.translation.create(audio={"base64": "..."}, target_language="en")
    client.video.generate(prompt="A short product scene", duration_seconds=4)