Skip to content

Commit

Permalink
Merge pull request #209 from aurelio-labs/zahid/filter
Browse files Browse the repository at this point in the history 
feat: Add route filtering to indexes
  • Loading branch information
@ashraq1455
ashraq1455 authored Apr 1, 2024
2 parents ca71efa + b88eb99 commit a91face
Show file tree
Hide file tree
Showing 9 changed files with 882 additions and 144 deletions.
324 changes: 324 additions & 0 deletions docs/09-route-filter.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,324 @@
{
"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/00-introduction.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/00-introduction.ipynb)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Semantic Router Filter"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The Semantic Router library can be used as a super fast route making layer on top of LLMs. That means rather than waiting on a slow agent to decide what to do, we can use the magic of semantic vector space to make routes. Cutting route making time down from seconds to milliseconds."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Getting Started"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We start by installing the library:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install -qU semantic-router==0.0.29\n"
]
},
{
"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/zahidsyed/anaconda3/envs/semantic_router/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:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from getpass import getpass\n",
"from semantic_router.encoders import CohereEncoder, OpenAIEncoder\n",
"os.environ[\"COHERE_API_KEY\"] = os.getenv(\"COHERE_API_KEY\") or getpass(\n",
" \"Enter Cohere API Key: \"\n",
")\n",
"# os.environ[\"OPENAI_API_KEY\"] = os.getenv(\"OPENAI_API_KEY\") or getpass(\n",
"# \"Enter OpenAI API Key: \"\n",
"# )\n",
"\n",
"encoder = CohereEncoder()\n",
"# encoder = OpenAIEncoder()"
]
},
{
"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[32m2024-03-28 14:24:37 INFO semantic_router.utils.logger local\u001b[0m\n"
]
}
],
"source": [
"from semantic_router.layer import RouteLayer\n",
"\n",
"rl = RouteLayer(encoder=encoder, routes=routes)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now we can test it:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RouteChoice(name='politics', function_call=None, similarity_score=None)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rl(\"don't you love politics?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"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": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RouteChoice(name=None, function_call=None, similarity_score=None)"
]
},
"execution_count": 6,
"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."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Demonstrating the Filter Feature\n",
"\n",
"Now, let's demonstrate the filter feature. We can specify a subset of routes to consider when making a classification. This can be useful if we want to restrict the scope of possible routes based on some context.\n",
"\n",
"For example, let's say we only want to consider the \"chitchat\" route for a particular query:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RouteChoice(name='chitchat', function_call=None, similarity_score=None)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rl(\"don't you love politics?\", route_filter=[\"chitchat\"])\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Even though the query might be more related to the \"politics\" route, it will be classified as \"chitchat\" because we've restricted the routes to consider.\n",
"\n",
"Similarly, we can restrict it to the \"politics\" route:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RouteChoice(name=None, function_call=None, similarity_score=None)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rl(\"how's the weather today?\", route_filter=[\"politics\"])\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In this case, it will return None because the query doesn't match the \"politics\" route well enough to pass the threshold.\n",
"\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": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading

0 comments on commit a91face

Please sign in to comment.