gseai

A Python client and command-line tool for the GSE AI LocalAI server.

The GSEAIServer class wraps LocalAI’s OpenAI-compatible /v1/ endpoints and the Anthropic-compatible /v1/messages endpoint. The gseai CLI exposes the same functionality without writing any Python.

Installation

To add gseai as a dependency of a Python project:

uv add gseai

To install the gseai CLI as a system-wide tool:

uv tool install gseai

Quick start — Python

from gseai import GSEAIServer

with GSEAIServer("your-api-token") as server:
    # List available models
    models = server.list_models()

    # Simple single-turn chat
    response = server.chat("model-id", "What is machine learning?")

    # Multi-turn chat using the OpenAI-compatible API
    response = server.chat_completions(
        "model-id",
        messages=[{"role": "user", "content": "What is machine learning?"}],
    )

Quick start — CLI

export GSEAI_API_TOKEN=your-api-token

gseai models
gseai chat gemma-4-e2b-it "What is machine learning?"
gseai audio transcribe whisper-1 lecture.mp3
gseai images generate stable-diffusion "a red barn in a snowy field"

Queue jobs

Large models can take longer than the server’s HTTP timeout to respond. The job queue lets you submit a request and collect the result later — no open connection required. See Queue jobs for the full guide.

from gseai import GSEAIServer

with GSEAIServer("your-api-token") as server:
    # Submit and walk away
    job = server.submit_job("my-job", "qwen2.5-coder", "Explain transformers.")

    # Come back later
    result = server.wait_for_job(job["job_id"])
    print(result["result"])

gseai queue submit qwen2.5-coder "Explain transformers." -n my-job
# a3f1c7d2-...

# Come back later
gseai queue wait a3f1c7d2-...

Indices