warning

Legacy managed-runtime reference. Command examples below describe the older desktop/managed llama.cpp preview and are legacy, not the current BCCLI v0.4 command surface. Use BCCLI and Local AI for current instructions.

Python install

Source-only preview

bash

pip install botconnector-ai

The package is implemented in the accepted source tree but is not published on PyPI. Do not pin pip install botconnector-ai in deployment automation yet.

Requirements

Python 3.9+
A running BotConnector local server (botconnector server start) — the SDK is a client, not an engine.

What to use today

The local API speaks OpenAI's protocol, so openai (or any HTTP client) works now:

python

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:11435/v1", api_key="not-needed")

Endpoints: OpenAI-compatible API. Embeddings: POST /v1/embeddings.

Publication status

The source boundary is live-tested; PyPI publication, versioned wheels and a support policy are still pending. Watch the status page.