diff --git a/docs/encoders/fastembed.ipynb b/docs/encoders/fastembed.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..27bad545385bd76c7c8064f988e84b0b5c0f180e
--- /dev/null
+++ b/docs/encoders/fastembed.ipynb
@@ -0,0 +1,262 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "[](https://colab.research.google.com/github/aurelio-labs/semantic-router/blob/main/docs/encoders/fastembed.ipynb) [](https://nbviewer.org/github/aurelio-labs/semantic-router/blob/main/docs/encoders/fastembed.ipynb)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Using FastEmbedEncoder"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "FastEmbed is a _lightweight and fast_ embedding library built for generating embeddings. It can be run locally and supports many open source encoders.\n",
+ "\n",
+ "Beyond being a local, open source library, there are two key reasons we might want to run this library over other open source alternatives:\n",
+ "\n",
+ "* **Lightweight and Fast**: The library uses an ONNX runtime so there is no heavy PyTorch dependency, supports quantized model weights (smaller memory footprint), is developed for running on CPU, and uses data-parallelism for encoding large datasets.\n",
+ "\n",
+ "* **Open-weight models**: FastEmbed supports many open source and open-weight models, included some that outperform popular encoders like OpenAI's Ada-002."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Getting Started"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We start by installing semantic-router with the `[fastembed]` flag to include all necessary dependencies for `FastEmbedEncoder`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -qU \"semantic-router[fastembed]==0.0.15\""
+ ]
+ },
+ {
+ "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": [],
+ "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, you can find a list of [all available embedding models here](https://qdrant.github.io/fastembed/examples/Supported_Models/):"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from semantic_router.encoders import FastEmbedEncoder\n",
+ "\n",
+ "encoder = FastEmbedEncoder()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "_**âš ï¸ If you see an ImportError, you must install the FastEmbed library. You can do so by installing Semantic Router using `pip install -qU \"semantic-router[fastembed]\"`.**_"
+ ]
+ },
+ {
+ "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[32m2024-01-06 16:53:16 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": [
+ "Now we can test it:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name='politics', function_call=None)"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl(\"don't you love politics?\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name='chitchat', function_call=None)"
+ ]
+ },
+ "execution_count": 6,
+ "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": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name=None, function_call=None)"
+ ]
+ },
+ "execution_count": 7,
+ "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."
+ ]
+ }
+ ],
+ "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
+}
diff --git a/docs/encoders/huggingface.ipynb b/docs/encoders/huggingface.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..4e9c28cdd9d1cc4c65b84a30de2d896b77ef2049
--- /dev/null
+++ b/docs/encoders/huggingface.ipynb
@@ -0,0 +1,271 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "[](https://colab.research.google.com/github/aurelio-labs/semantic-router/blob/main/docs/encoders/huggingface.ipynb) [](https://nbviewer.org/github/aurelio-labs/semantic-router/blob/main/docs/encoders/huggingface.ipynb)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Using HuggingFaceEncoder"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "HuggingFace is a huge ecosystem of open source models. It can be run locally and supports the largest library of encoders."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Getting Started"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We start by installing semantic-router with the `[local]` flag to include all necessary dependencies for `HuggingFaceEncoder`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -qU \"semantic-router[local]==0.0.16\""
+ ]
+ },
+ {
+ "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": [],
+ "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": [
+ "_**âš ï¸ If you see an ImportError, you must install local dependencies. You can do so by installing Semantic Router using `pip install -qU \"semantic-router[local]\"`.**_"
+ ]
+ },
+ {
+ "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": [
+ {
+ "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",
+ "tokenizer_config.json: 100%|██████████| 350/350 [00:00<00:00, 1.06MB/s]\n",
+ "vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 1.05MB/s]\n",
+ "tokenizer.json: 100%|██████████| 466k/466k [00:00<00:00, 1.43MB/s]\n",
+ "special_tokens_map.json: 100%|██████████| 112/112 [00:00<00:00, 386kB/s]\n",
+ "config.json: 100%|██████████| 612/612 [00:00<00:00, 2.90MB/s]\n",
+ "pytorch_model.bin: 100%|██████████| 90.9M/90.9M [00:01<00:00, 63.2MB/s]\n"
+ ]
+ }
+ ],
+ "source": [
+ "from semantic_router.encoders import HuggingFaceEncoder\n",
+ "\n",
+ "encoder = HuggingFaceEncoder()"
+ ]
+ },
+ {
+ "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[32m2024-01-09 00:22:35 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": [
+ "Now we can test it:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name='politics', function_call=None)"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl(\"don't you love politics?\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name='chitchat', function_call=None)"
+ ]
+ },
+ "execution_count": 6,
+ "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": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RouteChoice(name=None, function_call=None)"
+ ]
+ },
+ "execution_count": 7,
+ "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."
+ ]
+ }
+ ],
+ "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
+}