{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "collapsed_sections": [ "CoofhZcDtp6R" ] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "Yk-K_mHMs7ns", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "6f0206db-0574-4596-984c-31769ab1a9b7" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m262.9/262.9 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m810.5/810.5 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m269.1/269.1 kB\u001b[0m \u001b[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.6/71.6 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.8/77.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.0/53.0 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.5/138.5 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h" ] } ], "source": [ "!pip install openai langchain tiktoken langchain-openai langchain-community -q" ] }, { "cell_type": "markdown", "source": [ "## Если используете ключ от OpenAI, запустите эту ячейку 👇\n" ], "metadata": { "id": "CoofhZcDtp6R" } }, { "cell_type": "code", "source": [ "from langchain_openai import ChatOpenAI\n", "import os\n", "from getpass import getpass\n", "\n", "\n", "# os.environ['OPENAI_API_KEY'] = \"Введите ваш OpenAI API ключ\"\n", "os.environ['OPENAI_API_KEY'] = getpass(prompt='Введите ваш OpenAI API ключ')\n", "\n", "# Инициализируем языковую модель\n", "llm = ChatOpenAI(temperature=0.0)" ], "metadata": { "id": "k48wWXnPtKa2" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "## Если используете ключ из курса, запустите эти ячейки 👇\n" ], "metadata": { "id": "DiQqMwQJt8rP" } }, { "cell_type": "code", "source": [ "!wget https://raw.githubusercontent.com/a-milenkin/LLM_practical_course/main/notebooks/utils.py" ], "metadata": { "id": "Keq0WAjLuPgJ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "from utils import ChatOpenAI\n", "from getpass import getpass\n", "\n", "#course_api_key= \"Введите ваш API ключ с курса\"\n", "course_api_key = getpass(prompt='Введите API ключ')\n", "\n", "# Инициализируем языковую модель\n", "llm = ChatOpenAI(temperature=0.0, course_api_key=course_api_key)" ], "metadata": { "id": "PCS_WedHtPRg" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "## Задание 2.1.8 LLM — сила 💪, ML — могила 🧟" ], "metadata": { "id": "Z9uleJTbu6Ui" } }, { "cell_type": "code", "source": [ "import pandas as pd\n", "from tqdm import tqdm" ], "metadata": { "id": "CDMOJZ-3f0bs" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "df = pd.read_csv('https://stepik.org/media/attachments/lesson/1084297/submission100lines.csv')" ], "metadata": { "id": "Avwkg164vHPH" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "df.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "1x3bbJoTvNzh", "outputId": "040b873c-3eff-4a8b-b9ee-ebce0af4a45c" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " amount text_id text\n", "0 2 14205200 Сниму жилье. 500-600 рублей сутки. Эконом клас...\n", "1 6 319097075 ищем жилье в центре недалеко от моря с 23.07-0...\n", "2 4 98881311 Ищем жилье на период с 18-28июля..на две семьи...\n", "3 4 44587027 2 семьи по 3 человека (2 взрослых и ребенок) с...\n", "4 3 352802829 Сниму недорогое жилье в лазаревском на 6 чел 3..." ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
amounttext_idtext
0214205200Сниму жилье. 500-600 рублей сутки. Эконом клас...
16319097075ищем жилье в центре недалеко от моря с 23.07-0...
2498881311Ищем жилье на период с 18-28июля..на две семьи...
34445870272 семьи по 3 человека (2 взрослых и ребенок) с...
43352802829Сниму недорогое жилье в лазаревском на 6 чел 3...
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "
\n", "
\n" ] }, "metadata": {}, "execution_count": 6 } ] }, { "cell_type": "code", "source": [ "# Напишите шаблон промпт, указав инструкцию, вопрос и выходной индикатор\n", "\n", "prompt_template = \"\"\"...\n", "\n", "Context: {text_input}\n", "\n", "Question: ...\n", "\n", "Answer: ...\n", "\"\"\"" ], "metadata": { "id": "KJliN54ynKi1" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "amount_list = [] # Список, где будем хранить ответы модели\n", "\n", "for text_input in tqdm(df['text']):\n", " prompt = prompt_template.format(text_input=text_input) # Добавляем сообщение в промпт\n", " amount = llm.invoke(prompt).content # Ответ модели\n", " amount_list.append(amount) # Добавляем ответ в список\n", " break # Для отладки. Уберите, когда убедитесь, что на одном примере работает" ], "metadata": { "id": "uRgoFuWUycRu" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "df['amount'] = amount_list # Создаём новый столбец из ответов модели" ], "metadata": { "id": "QflBn5-l-_10" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "df.to_csv('2_1_8_solution.csv', index=False) # Сохраняем файл, отправляем на Stepik, получаем баллы :)" ], "metadata": { "id": "Ki850BP0_H2A" }, "execution_count": null, "outputs": [] } ] }