LLM_Engineering_OLD/week8/day2.1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b577c1be-f7a4-4549-8d27-30cb35407225",
   "metadata": {},
   "source": [
    "# The Price is Right\n",
    "\n",
    "Today we build a more complex solution for estimating prices of goods.\n",
    "\n",
    "1. Day 2.0 notebook: create a RAG database with our 400,000 training data\n",
    "2. Day 2.1 notebook: visualize in 2D\n",
    "3. Day 2.2 notebook: visualize in 3D\n",
    "4. Day 2.3 notebook: build and test a RAG pipeline with GPT-4o-mini\n",
    "5. Day 2.4 notebook: (a) bring back our Random Forest pricer (b) Create a Ensemble pricer that allows contributions from all the pricers\n",
    "\n",
    "Phew! That's a lot to get through in one day!\n",
    "\n",
    "## PLEASE NOTE:\n",
    "\n",
    "We already have a very powerful product estimator with our proprietary, fine-tuned LLM. Most people would be very satisfied with that! The main reason we're adding these extra steps is to deepen your expertise with RAG and with Agentic workflows.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "993a2a24-1a58-42be-8034-6d116fb8d786",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import re\n",
    "import math\n",
    "import json\n",
    "from tqdm import tqdm\n",
    "import random\n",
    "from dotenv import load_dotenv\n",
    "from huggingface_hub import login\n",
    "import numpy as np\n",
    "import pickle\n",
    "from sentence_transformers import SentenceTransformer\n",
    "from datasets import load_dataset\n",
    "import chromadb\n",
    "from sklearn.manifold import TSNE\n",
    "import plotly.graph_objects as go"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1cc1fe53-612f-4228-aa02-8758f4c2098f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# It is very fun turning this up to 400_000 and seeing the full dataset visualized,\n",
    "# but it almost crashes my box every time so do that at your own risk!! 10_000 is safe!\n",
    "\n",
    "MAXIMUM_DATAPOINTS = 30_000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f4aab95e-d719-4476-b6e7-e248120df25a",
   "metadata": {},
   "outputs": [],
   "source": [
    "DB = \"products_vectorstore\"\n",
    "client = chromadb.PersistentClient(path=DB)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5f95dafd-ab80-464e-ba8a-dec7a2424780",
   "metadata": {},
   "outputs": [],
   "source": [
    "collection = client.get_or_create_collection('products')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "525fc313-8a16-4ac0-8c42-6a6d1ba1c9b8",
   "metadata": {},
   "outputs": [],
   "source": [
    "CATEGORIES = ['Appliances', 'Automotive', 'Cell_Phones_and_Accessories', 'Electronics','Musical_Instruments', 'Office_Products', 'Tools_and_Home_Improvement', 'Toys_and_Games']\n",
    "COLORS = ['red', 'blue', 'brown', 'orange', 'yellow', 'green' , 'purple', 'cyan']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4cf1c9a-1ced-48d4-974c-3c850905034e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prework\n",
    "result = collection.get(include=['embeddings', 'documents', 'metadatas'], limit=MAXIMUM_DATAPOINTS)\n",
    "vectors = np.array(result['embeddings'])\n",
    "documents = result['documents']\n",
    "categories = [metadata['category'] for metadata in result['metadatas']]\n",
    "colors = [COLORS[CATEGORIES.index(c)] for c in categories]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c54df150-c8d8-4bc3-8877-6759691eeb42",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's try a 2D chart\n",
    "\n",
    "tsne = TSNE(n_components=2, random_state=42, n_jobs=-1)\n",
    "reduced_vectors = tsne.fit_transform(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e8fb2a63-24c5-4dce-9e63-aa208272f82d",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Create the 2D scatter plot\n",
    "fig = go.Figure(data=[go.Scatter(\n",
    "    x=reduced_vectors[:, 0],\n",
    "    y=reduced_vectors[:, 1],\n",
    "    mode='markers',\n",
    "    marker=dict(size=3, color=colors, opacity=0.7),\n",
    ")])\n",
    "\n",
    "fig.update_layout(\n",
    "    title='2D Chroma Vectorstore Visualization',\n",
    "    scene=dict(xaxis_title='x', yaxis_title='y'),\n",
    "    width=1200,\n",
    "    height=800,\n",
    "    margin=dict(r=20, b=10, l=10, t=40)\n",
    ")\n",
    "\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5e4ae088-3d29-45d3-87a2-fea805fe2c65",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}