docs/encoders/openai-embed-3.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/aurelio-labs/semantic-router/blob/main/docs/encoders/fastembed.ipynb) [![Open nbviewer](https://raw.githubusercontent.com/pinecone-io/examples/master/assets/nbviewer-shield.svg)](https://nbviewer.org/github/aurelio-labs/semantic-router/blob/main/docs/encoders/fastembed.ipynb)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Using OpenAI Embed 3 Models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The 3rd generation embedding models from OpenAI (`text-embedding-3-small` and `text-embedding-3-large`) can both be used with our `OpenAIEncoder` and usage is primarily the same as with the 2nd generation `text-embedding-ada-002`. However, there is a new `dimensions` parameter — which we will discuss below."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting Started"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We start by installing semantic-router. Support for the new `dimensions` parameter was added in `semantic-router==0.0.19` and `openai==1.10.0`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -qU semantic-router==0.0.20"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We start by defining a dictionary mapping routes to example phrases that should trigger those routes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/jamesbriggs/opt/anaconda3/envs/decision-layer/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from semantic_router import Route\n",
    "\n",
    "politics = Route(\n",
    "    name=\"politics\",\n",
    "    utterances=[\n",
    "        \"isn't politics the best thing ever\",\n",
    "        \"why don't you tell me about your political opinions\",\n",
    "        \"don't you just love the president\",\n",
    "        \"don't you just hate the president\",\n",
    "        \"they're going to destroy this country!\",\n",
    "        \"they will save the country!\",\n",
    "    ],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's define another for good measure:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "chitchat = Route(\n",
    "    name=\"chitchat\",\n",
    "    utterances=[\n",
    "        \"how's the weather today?\",\n",
    "        \"how are things going?\",\n",
    "        \"lovely weather today\",\n",
    "        \"the weather is horrendous\",\n",
    "        \"let's go to the chippy\",\n",
    "    ],\n",
    ")\n",
    "\n",
    "routes = [politics, chitchat]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we initialize our embedding model, we will use the `-3-large` model alongside a `dimensions` value of `256`. This will produce _tiny_ 256-dimensional vectors that — according to OpenAI — outperform the 1536-dimensional vectors produced by `text-embedding-ada-002`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from getpass import getpass\n",
    "from semantic_router.encoders import OpenAIEncoder\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = os.getenv(\"OPENAI_API_KEY\") or getpass(\n",
    "    \"Enter OpenAI API Key: \"\n",
    ")\n",
    "\n",
    "encoder = OpenAIEncoder(\n",
    "    name=\"text-embedding-3-large\", score_threshold=0.5, dimensions=256\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we define the `RouteLayer`. When called, the route layer will consume text (a query) and output the category (`Route`) it belongs to — to initialize a `RouteLayer` we need our `encoder` model and a list of `routes`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m2024-01-28 12:40:08 INFO semantic_router.utils.logger Initializing RouteLayer\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from semantic_router.layer import RouteLayer\n",
    "\n",
    "rl = RouteLayer(encoder=encoder, routes=routes)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can check the dimensionality of our vectors by looking at the `index` attribute of the `RouteLayer`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(11, 256)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rl.index.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We do have 256-dimensional vectors. Now let's test them:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RouteChoice(name='politics', function_call=None, similarity_score=None, trigger=None)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rl(\"don't you love politics?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RouteChoice(name='chitchat', function_call=None, similarity_score=None, trigger=None)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rl(\"how's the weather today?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Both are classified accurately, what if we send a query that is unrelated to our existing `Route` objects?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RouteChoice(name=None, function_call=None, similarity_score=None, trigger=None)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rl(\"I'm interested in learning about llama 2\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this case, we return `None` because no matches were identified. We always recommend optimizing your `RouteLayer` for optimal performance, you can see how in [this notebook](https://github.com/aurelio-labs/semantic-router/blob/main/docs/06-threshold-optimization.ipynb)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "decision-layer",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}