{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hybrid Router\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `HybridRouter` in the Semantic Router library can improve making performance particularly for niche use-cases that contain specific terminology, such as finance or medical.\n",
    "\n",
    "It helps us provide more importance to making based on the keywords contained in our utterances and user queries."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting Started\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We start by installing the library:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install -qU semantic-router==0.1.0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We start by defining a dictionary mapping s to example phrases that should trigger those s.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/jamesbriggs/Library/Caches/pypoetry/virtualenvs/semantic-router-C1zr4a78-py3.12/lib/python3.12/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.route 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:\n"
   ]
  },
  {
   "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 models, we use a dense encoder from [OpenAI](https://platform.openai.com/) and a sparse encoder from [Aurelio](https://platform.aurelio.ai/). The `AurelioSparseEncoder` we use here provides a remote sparse encoder that can significantly improve routing accuracy when combined with dense embeddings.\n",
    "\n",
    "Semantic Router supports other _local_ sparse encoders like `TfidfEncoder` or `BM25Encoder`. Compared to these, the `AurelioSparseEncoder`:\n",
    "\n",
    "1. Doesn't require local fitting (training) on your dataset\n",
    "2. Handles out-of-vocabulary words better\n",
    "3. Works better with asymmetric retrieval (different encoding for queries vs. documents)\n",
    "\n",
    "We initialize both like so:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from semantic_router.encoders import OpenAIEncoder, AurelioSparseEncoder\n",
    "from getpass import getpass\n",
    "\n",
    "# get OpenAI API key from https://platform.openai.com/\n",
    "os.environ[\"OPENAI_API_KEY\"] = os.getenv(\"OPENAI_API_KEY\") or getpass(\n",
    "    \"Enter OpenAI API Key: \"\n",
    ")\n",
    "\n",
    "dense_encoder = OpenAIEncoder(name=\"text-embedding-3-small\", score_threshold=0.3)\n",
    "\n",
    "# get Aurelio API key from https://platform.aurelio.ai\n",
    "# use \"SRHYBRIDROUTER\" for free credits\n",
    "os.environ[\"AURELIO_API_KEY\"] = os.getenv(\"AURELIO_API_KEY\") or getpass(\n",
    "    \"Enter Aurelio API Key: \"\n",
    ")\n",
    "\n",
    "# Using Aurelio's BM25 sparse encoder\n",
    "sparse_encoder = AurelioSparseEncoder(name=\"bm25\")"
   ]
  },
  {
   "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`.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m2024-11-24 00:37:14 INFO semantic_router.utils.logger Downloading and initializing default sBM25 model parameters.\u001b[0m\n",
      "\u001b[32m2024-11-24 00:37:22 INFO semantic_router.utils.logger Encoding route politics\u001b[0m\n",
      "\u001b[32m2024-11-24 00:37:23 INFO semantic_router.utils.logger Encoding route chitchat\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from semantic_router.routers import HybridRouter\n",
    "\n",
    "router = HybridRouter(\n",
    "    encoder=dense_encoder,\n",
    "    sparse_encoder=sparse_encoder,\n",
    "    routes=routes,\n",
    "    alpha=0.5,  # Balance between dense (0) and sparse (1) embeddings\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RouteChoice(name='politics', function_call=None, similarity_score=1.1909239963848142)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "router(\"don't you love politics?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RouteChoice(name='chitchat', function_call=None, similarity_score=2.0)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "router(\"how's the weather today?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n"
   ]
  }
 ],
 "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}