feat: add movie dataset

Author: solygambas

playground/12-gpt-4-ai-spotify-playlist-generator.ipynb renamed to playground/11-gpt-4-ai-spotify-playlist-generator.ipynb

@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import dotenv_values\n",
+    "config = dotenv_values(\".env\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai.api_key = config[\"OPENAI_API_KEY\"]"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generating a single embedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = openai.Embedding.create(\n",
+    "    model=\"text-embedding-ada-002\",\n",
+    "    input=\"candy canes\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response[\"data\"][0][\"embedding\"]"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Movies plotting with Atlas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset_path = \"./datasets/movie_plots.csv\"\n",
+    "df = pd.read_csv(dataset_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "movies = df[df[\"Origin/Ethnicity\"] == \"American\"].sort_values(\"Release Year\", ascending=False).head(500)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.5"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

playground/12-embeddings.ipynb

@@ -77,6 +77,18 @@ You need to create a `.env` file with your `OPENAI_API_KEY`.
 
 - writing the playlist generating prompt.
 
-[Check the notebook](12-gpt-4-ai-spotify-playlist-generator.ipynb)
+[Check the notebook](11-gpt-4-ai-spotify-playlist-generator.ipynb)
+
+## Embeddings
+
+- generating a single embedding.
+- creating a movie embedding visualization with Atlas.
+- getting our movie data.
+- getting our movie data ready.
+- generating embeddings for 5000 movies.
+- visualizing our embeddings with atlas.
+- recommending movies using our embeddings.
+
+[Check the notebook](12-embeddings.ipynb)
 
 Based on [Mastering OpenAI Python APIs: Unleash the Power of GPT4](https://www.udemy.com/course/mastering-openai/) by Colt Steele (2023).