Skip to main content

mlx_augllm

MLX(Apple Silicon向け機械学習フレームワーク)を用いた、 ローカルで動作する LLM / VLM のための統一インターフェースライブラリです。

本ライブラリは以下を目的としています。

  • ローカルLLM/VLMを簡単かつ一貫したAPIで扱える
  • Tool Use(関数呼び出し)に対応
  • 会話履歴の管理を自動化
  • Apple Siliconに最適化

インストール

pip install -U mlx_augllm
  • Apple Silicon必須

サンプル

from mlx_augllm import MlxAugmentedLLM, MlxLLMInterface, PromptBuilder 

def run_test():

    # モデルの準備
    model_path = "mlx-community/gemma-3-27b-it-4bit"
    augmented_llm = MlxAugmentedLLM(
        llm_interface=MlxLLMInterface(
            model_path=model_path,
            use_vision=False,
            temp=0.7,
            top_k=50,
            top_p=0.9,
            min_p=0.05,
            max_tokens=8192
        ),
        prompt_builder=PromptBuilder(system_prompt_text="あなたは有能なアシスタントです。"),
    )

    # 実行テスト
    user_query = "トポロジー最適化について教えてください。"
    
    print(f"\nユーザーの問いかけ: {user_query}")
    print("-" * 50)
    print("AIの応答 (Streaming):")

    # respond の呼び出し (contextを渡す)
    response_generator = augmented_llm.respond(
        user_text=user_query,
        stream=True,
        temp=0.7
    )

    full_response = ""
    for chunk in response_generator:
        print(chunk, end="", flush=True)
        full_response += chunk
    
    print("\n" + "-" * 50)
    print("【内部レポート】")
    if augmented_llm.report_text:
        print(f"最終回答の文字数: {len(augmented_llm.report_text)}")

if __name__ == "__main__":
    run_test()

Release files for mlx-augllm 1.5.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mlx-augllm 1.5.2
File Size Uploaded
mlx_augllm-1.5.2.tar.gz 18.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for mlx-augllm 1.5.2
File Interpreter ABI Platform
mlx_augllm-1.5.2-py3-none-any.whl Python 3 none any Details

Total release size: 41.1 kB

Release files / mlx_augllm-1.5.2.tar.gz

Download URL mlx_augllm-1.5.2.tar.gz
Size 18.8 kB
Tags Source
SHA-256 checksum
How to use checksums
028736d49201f96274bb3d8aa6d2e43a88f6004f3ef4d506bd4a391e21346bbd
BLAKE2b-256 checksum
How to use checksums
80debe2a354c79d32e8918e4aaa7048f26541dd395802acf6a09208519ca64a3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Release files / mlx_augllm-1.5.2-py3-none-any.whl

Download URL mlx_augllm-1.5.2-py3-none-any.whl
Size 22.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0c914b43a176a0e83080b1951dea021e64d65b5f980b77667c883485a8364364
BLAKE2b-256 checksum
How to use checksums
3a87d95396bdae6c7068e33d79f3940a9b30475c92634908db49095d13fd1681
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Release history Release notifications | RSS feed

This release

1.5.2 This release

2 release files

1.5.1

2 release files

1.5

2 release files

1.4.1

2 release files

1.4

2 release files

1.3

2 release files

1.2

2 release files

1.1

2 release files

1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page