burmesegpt 0.1.2

BurmeseGPT is a Burmese-first AI ecosystem package, including Padauk, an agentic small language model built for tool use, function calling, and local deployment.

BurmeseGPT

BurmeseGPT is an open Burmese-first AI ecosystem created by Dr. Wai Yan Nyein Naing. This Python package is the main package for BurmeseGPT projects, including Padauk, a practical agentic small language model built for Burmese language understanding, tool use, function calling, and local or edge deployment.

Why BurmeseGPT

Burmese is still a low-resource language in AI, and practical Burmese AI tooling remains limited for many real developer workflows. BurmeseGPT focuses on useful, production-minded, and developer-friendly Burmese AI systems that can run locally and integrate with modern agent and API patterns.

Related projects

• Padauk - Burmese-first agentic language model.
• Burmese-Coder - Burmese coding and technical AI direction.
• Future tools and integrations under the BurmeseGPT ecosystem.

Installation

# Core package (download + info)
pip install burmesegpt

# Local OpenAI-compatible server runtime
pip install "burmesegpt[server]"

# OpenAI Python SDK integration helpers
pip install "burmesegpt[openai]"

# Full install (recommended)
pip install "burmesegpt[full]"

download and info work with core install. serve and run (without --base-url) require burmesegpt[server]. smoke-test --client openai requires burmesegpt[openai].

Real model run (recommended)

pip install "burmesegpt[full]"
burmesegpt download --quant q8_0
burmesegpt serve --quant q8_0 --host 127.0.0.1 --port 8000

Developer/CI smoke test (no model download)

burmesegpt serve --test-mode --port 8000
burmesegpt smoke-test --base-url http://127.0.0.1:8000/v1 --model padauk-agent
burmesegpt smoke-test --client openai --base-url http://127.0.0.1:8000/v1 --model padauk-agent

OpenAI-compatible Python usage

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="sk-no-key-required")
response = client.chat.completions.create(
    model="padauk-agent",
    messages=[{"role": "user", "content": "မင်္ဂလာပါ"}],
)
print(response.choices[0].message.content)

OpenAI Agents SDK usage

pip install openai-agents

import asyncio

from openai import AsyncOpenAI
from agents import Agent, Runner, set_default_openai_api, set_default_openai_client, set_tracing_disabled

set_tracing_disabled(True)
set_default_openai_api("chat_completions")
set_default_openai_client(
    AsyncOpenAI(base_url="http://127.0.0.1:8000/v1", api_key="sk-no-key-required")
)

padauk = Agent(
    name="Padauk Assistant",
    model="padauk-agent",
    instructions="You are Padauk, a Burmese-first assistant. Reply in Burmese by default.",
)

async def main() -> None:
    result = await Runner.run(padauk, input="မင်္ဂလာပါ")
    print(result.final_output)

asyncio.run(main())

Padauk system prompt note

model/Modelfile includes a Burmese custom SYSTEM prompt for Padauk, but this package currently serves GGUF directly with llama_cpp.server and does not automatically inject that SYSTEM block. If you need strict persona behavior, provide a system message (or Agent.instructions) from your client.

CLI commands

• burmesegpt download - Download and checksum-verify a quantized GGUF artifact.
• burmesegpt serve - Start a local OpenAI-compatible API server.
• burmesegpt run - Interactive chat (boots local server or uses --base-url).
• burmesegpt smoke-test - Validate /models and /chat/completions.
• burmesegpt info - Print package/model configuration as JSON.

Useful options:

• --quant: q4_k_m (default), q5_k_m, q8_0
• --repo-id, --revision, --cache-dir, --hf-token (or HF_TOKEN)
• Shared options work both before and after subcommands.

Links

• Website: https://www.waiyannyeinnaing.com/
• Padauk: https://www.waiyannyeinnaing.com/projects/padauk
• Source: https://github.com/WaiYanNyeinNaing/burmese-gpt-pypi-api
• Hugging Face: https://huggingface.co/WYNN747/padauk-burmese-agentic-llm