laiwenai 0.0.8

A lightweight OpenAI-compatible LLM client wrapper with defaults, retries, logging, and manual JSON mode.

LaiwenAI

LaiwenAI is a lightweight Python wrapper for OpenAI-compatible LLM endpoints. It keeps the familiar OpenAI SDK style while adding project-local .env defaults, retries, optional logging, and a small laiw command line helper.

PyPI: https://pypi.org/project/laiwenai/

Install

pip install laiwenai

Initialize

Run this in your project directory:

laiw init

laiw init checks only the current working directory. It creates or completes .env.example and .env, asks for LAIWEN_API_KEY, lets other values use defaults, then runs laiw test.

Default .env values:

LAIWEN_API_KEY=your_api_key_here
LAIWEN_BASE_URL=http://111.228.11.28:3000/v1
LAIWEN_MODEL=DeepSeek-V4-Flash
LAIWEN_EMBED_MODEL=text-embedding-3-small
LAIWEN_TEMP=0
LAIWEN_TIMEOUT=30.0
LAIWEN_RETRIES=1
LAIWEN_LOG_CONSOLE=False
LAIWEN_LOG_FILE=False
LAIWEN_LOG_DIR=logs

CLI

laiw test

laiw test checks the current directory .env and loads config from that file; values in the current .env override same-name system environment variables. It first prints the resolved environment config with LAIWEN_API_KEY masked, then runs a chat smoke test.

Example output:

Environment config:
  LAIWEN_API_KEY=your_a...here
  LAIWEN_BASE_URL=http://111.228.11.28:3000/v1
  LAIWEN_MODEL=DeepSeek-V4-Flash
  LAIWEN_EMBED_MODEL=text-embedding-3-small
  LAIWEN_TEMP=0.0
  LAIWEN_TIMEOUT=30.0
  LAIWEN_RETRIES=1
  LAIWEN_LOG_CONSOLE=False
  LAIWEN_LOG_FILE=False
  LAIWEN_LOG_DIR=logs

To test JSON-mode output:

laiw test --json

To test chat and embeddings:

laiw test --embedding

To run all smoke tests:

laiw test --all

Python Usage

from laiwenai import LaiwenAI

client = LaiwenAI()

response = client.chat.completions.create(
    messages=[
        {"role": "user", "content": "What model are you? Reply briefly as: I am the XXX model."}
    ]
)

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

You can still pass OpenAI SDK parameters:

response = client.chat.completions.create(
    model=None,
    messages=[{"role": "user", "content": "Hello"}],
    temperature=None,
    timeout=None,
    response_format={"type": "json_object"},
)

Embeddings:

embedding = client.embeddings.create(input="Hello")
print(len(embedding.data[0].embedding))

OpenAI-Compatible Endpoints

When you pass a custom base_url, you must also pass api_key explicitly. This prevents accidentally sending the default key to another provider.

from laiwenai import LaiwenAI

client = LaiwenAI(
    api_key="your-provider-key",
    base_url="http://111.228.11.28:3000/v1",
    model="DeepSeek-V4-Flash",
)

Configuration

Key	Description
LAIWEN_API_KEY	Default API key. Required unless passed explicitly.
LAIWEN_BASE_URL	Default OpenAI-compatible base URL.
LAIWEN_MODEL	Default chat/responses model.
LAIWEN_EMBED_MODEL	Default embedding model.
LAIWEN_TEMP	Default temperature when omitted or None.
LAIWEN_TIMEOUT	Default timeout when omitted or None.
LAIWEN_RETRIES	Retry attempts around API calls.
LAIWEN_LOG_CONSOLE	Enable structured console logs.
LAIWEN_LOG_FILE	Enable structured file logs.
LAIWEN_LOG_DIR	Directory for laiwenai.log.

Notes

LaiwenAI() loads .env only from the current working directory. If .env is missing, initialization fails with a clear error.

License

MIT