{ "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "from openai import OpenAI\n", "client = OpenAI(api_key=\"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\")\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# load the list of genres we will use to generate artists\n", "# we will ask gpt to generate a list of 100 artists for each genre\n", "# this will enable us to create a master list of artists that we know have produced \"quality\" music" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# you list 100 of the top artists in the genre of cool jazz try not to repeat artists, return the list formatted with each artist on a new line in code format, do not include numbers, just the artist names" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "system_prompt = \"\"\"You are a music expert and have diverse knowledge of music. You are given a musical genre and you are to provide a list of around 100 representative artists in that genre. \n", "If this is a subgenre, try to find artists that are representative of the subgenre and not the parent genre.\n", "You are to return the list formatted with each artist on a new line in code format. Do not include numbers, just the artist names. Do not repeat artists or include additional text in your response.\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "genre_list_path = \"/home/christian/code/christian/metadata/genre_list.txt\"\n", "genre_list = open(genre_list_path, \"r\").read().split(\"\\n\")\n", "print(len(genre_list))\n", "\n", "# remove empty strings\n", "genre_list = [genre for genre in genre_list if genre]\n", "print(len(genre_list))\n", "\n", "# remove duplicates\n", "genre_list = list(set(genre_list))\n", "print(len(genre_list))" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 0/902 [00:00