【完全無料】WindowsでOpen Interpreter～みんなのPCにAI導入！事務用PCにOpen Interpreterは導入できるのか？～【Llama2】

AIアシスタント
2023.09.18

はじめに

AI技術の発展により、日常的にPCでAIを活用することが増えてきました。今回は、一般的な事務用PCに「Open Interpreter」というAI技術を導入する方法を解説します。

解説動画

今回使用するPCのスペック

  • メーカー: HP
  • 型式: HP Spectre x360
  • OS: Windows 11
  • CPU: Intel Core i7 (4コア)
  • メモリ: 16GB
HP Spectre x360 14-ef 製品詳細 - ノートパソコン | 日本HP
女性でも持ち運びやすい薄型軽量ボディ鞄にも入りやすく女性でも持ち運び楽々。外出先での仕事が多いビジネスマンから、行動範囲が広い大学生にもぴったり！HP Spectre x360 14-ef をご紹介します。14-ef0051TU,14-ef0013TU,14-ef0055TU,14-ef0014TU
jp.ext.hp.com

インストールの手順

リポジトリのダウンロード

まず、指定されたリポジトリから「ダウンロードZIP」をクリックして、ZIPファイルをダウンロードします。ダウンロードが完了したら、ZIPを解凍します。

GitHub - Sunwood-ai-labs/open-interpreter-docker
Contribute to Sunwood-ai-labs/open-interpreter-docker development by creating an account on GitHub.
github.com

コマンドプロンプトを起動

以下の手順でコマンドプロンプトを開きます：

  1. Windowsの検索ボックスに「cmd」と入力
  2. 検索結果から「コマンドプロンプト」をクリックして起動

解凍したフォルダへ移動

以下のコマンドを入力して、ダウンロードしたリポジトリのフォルダ内へ移動します。


cd C:\Prj\open-interpreter-docker

Dockerの起動

次に、Dockerを使ってOpen Interpreterを動作させます。Docker Composeを使用して、以下のコマンドでバックグラウンドでDockerコンテナを起動します。


docker-compose up -d

コンテナ内に入る

次のコマンドでコンテナ内にアクセスします：


docker-compose exec open-interpreter /bin/bash

Open Interpreterの起動

コンテナ内で以下のコマンドを入力し、Open Interpreterを起動します。


interpreter

ここで、OpenAIのAPIキーは使用せず、Open Sourceのバージョンを利用します。使用するモデルは「7b Medium」とし、GPUは使用しません。

簡単なデータ分析


root@465aaa3eb215:~# interpreter

●

Welcome to Open Interpreter.

─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
▌ OpenAI API key not found

To use GPT-4 (recommended) please provide an OpenAI API key.

To use Code-Llama (free but less capable) press enter.

─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
OpenAI API key:

▌ Switching to Code-Llama...

Tip: Run interpreter --local to automatically use Code-Llama.

─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Open Interpreter will use Code Llama for local execution. Use your arrow keys to set up the model.

[?] Parameter count (smaller is faster, larger is more capable): 7B
 > 7B
   13B
   34B

[?] Quality (smaller is faster, larger is more capable): Medium | Size: 3.8 GB, Estimated RAM usage: 6.3 GB
   Small | Size: 2.6 GB, Estimated RAM usage: 5.1 GB
 > Medium | Size: 3.8 GB, Estimated RAM usage: 6.3 GB
   Large | Size: 6.7 GB, Estimated RAM usage: 9.2 GB
   See More

[?] Use GPU? (Large models might crash on GPU, but will run more quickly) (Y/n): Y

Model found at /root/.local/share/Open Interpreter/models/codellama-7b-instruct.Q4_K_M.gguf

▌ Model set to TheBloke/CodeLlama-7B-Instruct-GGUF

Open Interpreter will require approval before running code. Use interpreter -y to bypass this.

Press CTRL-C to exit.

> `from sklearn.datasets import fetch_california_housing`これを用いてカリフォルニア住宅価格のデータセットを用いて住宅価格の回帰予測をstep-by-stepで行って

  from sklearn.datasets import fetch_california_housing

  Would you like to run this code? (y/n)

  y

  from sklearn.datasets import fetch_california_housing

  I will now proceed to load the California Housing dataset using the fetch_california_housing function from scikit-learn.

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()

  Would you like to run this code? (y/n)

  y

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()

  I will now proceed to explore the California Housing dataset.

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)

  Would you like to run this code? (y/n)

  y

  from sklearn.datasets import fetch_california_housing

  from sklearn.datasets import fetch_california_housing

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group
  - HouseAge      median house age in block group

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group
  - HouseAge      median house age in block group

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)█

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group
  - HouseAge      median house age in block group

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group
  - HouseAge      median house age in block group

  from sklearn.datasets import fetch_california_housing
  housing = fetch_california_housing()
  print(housing.DESCR)

  .. _california_housing_dataset:
  California Housing dataset
  --------------------------
  **Data Set Characteristics:**
  :Number of Instances: 20640
  :Number of Attributes: 8 numeric, predictive attributes and the target
  :Attribute Information:
  - MedInc        median income in block group
  - HouseAge      median house age in block group
  - AveRooms      average number of rooms per household
  - AveBedrms     average number of bedrooms per household
  - Population    block group population
  - AveOccup      average number of household members
  - Latitude      block group latitude
  - Longitude     block group longitude
  :Missing Attribute Values: None
  This dataset was obtained from the StatLib repository.
  https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html
  The target variable is the median house value for California districts,
  expressed in hundreds of thousands of dollars ($100,000).
  This dataset was derived from the 1990 U.S. census, using one row per census
  block group. A block group is the smallest geographical unit for which the U.S.
  Census Bureau publishes sample data (a block group typically has a population
  of 600 to 3,000 people).
  A household is a group of people residing within a home. Since the average
  number of rooms and bedrooms in this dataset are provided per household, these
  columns may take surprisingly large values for block groups with few households
  and many empty houses, such as vacation resorts.
  It can be downloaded/loaded using the
  :func:`sklearn.datasets.fetch_california_housing` function.
  .. topic:: References
  - Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,
  Statistics and Probability Letters, 33 (1997) 291-297

  it appears that the California Housing dataset is a collection of features and target variable for predicting median house value in
  California districts. The dataset contains 8 numeric attributes and one target variable, which is the median house value expressed in
  hundreds of thousands of dollars ($100,000).

  I will now proceed to explore the California Housing dataset further by visualizing the distribution of the target variable.

  import matplotlib.pyplot as plt
  plt.hist(housing.target)
  plt.xlabel('Median House Value')
  plt.ylabel('Frequency')
  plt.title('Distribution of Median House Value')
  plt.show()

  Would you like to run this code? (y/n)

> y

  import matplotlib.pyplot as plt
  plt.hist(housing.target)
  plt.xlabel('Median House Value')
  plt.ylabel('Frequency')
  plt.title('Distribution of Median House Value')
  plt.show()

  Would you like to run this code? (y/n)

  y

  import matplotlib.pyplot as plt
  plt.hist(housing.target)
  plt.xlabel('Median House Value')
  plt.ylabel('Frequency')
  plt.title('Distribution of Median House Value')
  plt.show()

  (array([ 877., 3612., 4099., 3771., 2799., 1769., 1239.,  752.,  479.,
  1243.]), array([0.14999 , 0.634992, 1.119994, 1.604996, 2.089998, 2.575   ,
  3.060002, 3.545004, 4.030006, 4.515008, 5.00001 ]), <BarContainer object of 10 artists>)
  Text(0.5, 0, 'Median House Value')
  Text(0, 0.5, 'Frequency')
  Text(0.5, 1.0, 'Distribution of Median House Value')

  it appears that the median house value in California districts is distributed as follows:

   • The lowest value is $877
   • The highest value is $5000
   • There are approximately 1243 values between these two extremes

  I will now proceed to explore the distribution of the other attributes in the dataset.

  import matplotlib.pyplot as plt
  plt.hist(housing.data[:, 1:])
  plt.xlabel('Attribute')
  plt.ylabel('Frequency')
  plt.title('Distribution of Attributes')
  plt.show()

  Would you like to run this code? (y/n)

  y

  import matplotlib.pyplot as plt
  plt.hist(housing.data[:, 1:])
  plt.xlabel('Attribute')
  plt.ylabel('Frequency')
  plt.title('Distribution of Attributes')
  plt.show()

  (array([[2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00],
  [2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00],
  [2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00],
  [1.9726e+04, 7.9600e+02, 1.0000e+02, 1.2000e+01, 4.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 1.0000e+00, 1.0000e+00],
  [2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00],
  [2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00],
  [2.0640e+04, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,
  0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00]]), array([ -124.35 ,  3456.285,  7036.92 , 10617.555, 14198.19 ,
  17778.825,
  21359.46 , 24940.095, 28520.73 , 32101.365, 35682.   ]), <a list of 7 BarContainer objects>)
  Text(0.5, 0, 'Attribute')
  Text(0, 0.5, 'Frequency')
  Text(0.5, 1.0, 'Distribution of Attributes')

  it appears that there are 7 attributes in the dataset and their frequencies are distributed as follows:

   • The lowest value is -124.35
   • The highest value is 35682.0
   • There are approximately 1243 values between these two extremes

  I will now proceed to explore the distribution of the other attributes in the dataset.

  import matplotlib.pyplot as plt
  plt.hist(housing.data[:, 2:])
  plt.xlabel('Attribute')
  plt.ylabel('Frequency')
  plt.title('Distribution of Attributes')
  plt.show()

  Would you like to run this code? (y/n)

途中でループしてしまい予測までは到達できず。

メモリの確認

このPCでは、メモリが16GBありますが、すでに8GBが他のプロセスで使用されている可能性があります。残りの8GB未満をOpen Interpreterが使用します。このため、「7b Medium」モデルはこのPCのメモリ容量でギリギリ動作すると考えられます。

まとめ

以上で、HPの事務用PCにOpen Interpreterの7B Mediumモデルを導入する手順を解説しました。Open Interpreterを実際に活用する際は、メモリ使用量などに注意しながら使用してください。また、今回はデータの回帰予測までの手順は省略しましたが、必要に応じて追加の手順や命令を学ぶことができます。

それでは、次回の解説もお楽しみに！

Open Interpreter関連

【完全無料】WindowsでOpen Interpreter～みんなのPCにAI導入！Open Interpreterとおしゃべりしながら、プログラミングをしよう～【Llama2】
はじめにこんにちは、未来のPC操作を体験しませんか？今回は、AI技術「Open Interpreter」を利用して、PCとおしゃべりしながらプログラムを書く方法をご紹介します。初心者の方でも手軽に始められるよう、手順を丁寧に解説いたします。...
hamaruki.com
2023.09.14

コメント

タイトルとURLをコピーしました