From 884b4b3b84ca9e63547d37241cf5b870b42f58a3 Mon Sep 17 00:00:00 2001
From: James Briggs <james.briggs@hotmail.com>
Date: Thu, 13 Jun 2024 16:32:44 +0800
Subject: [PATCH] feat: pinecone openai async example
---
docs/indexes/pinecone_async.ipynb | 574 ++++++++++++++++++++++++++++++
1 file changed, 574 insertions(+)
create mode 100644 docs/indexes/pinecone_async.ipynb
diff --git a/docs/indexes/pinecone_async.ipynb b/docs/indexes/pinecone_async.ipynb
new file mode 100644
index 00000000..9019db2f
--- /dev/null
+++ b/docs/indexes/pinecone_async.ipynb
@@ -0,0 +1,574 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -qU \"semantic-router[pinecone]==0.0.47\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from semantic_router import Route\n",
+ "\n",
+ "# we could use this as a guide for our chatbot to avoid political conversations\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\" \"don't you just hate the president\",\n",
+ " \"they're going to destroy this country!\",\n",
+ " \"they will save the country!\",\n",
+ " ],\n",
+ ")\n",
+ "\n",
+ "# this could be used as an indicator to our chatbot to switch to a more\n",
+ "# conversational prompt\n",
+ "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",
+ "# we place both of our decisions together into single list\n",
+ "routes = [politics, chitchat]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "As of 13 June 2024, two encoders support async functionality:\n",
+ "\n",
+ "* `AzureOpenAIEncoder`\n",
+ "* `OpenAIEncoder`\n",
+ "\n",
+ "To use either of these encoders in async mode we simply initialize them as we usually would. When we then include them within a `RouteLayer` and run `acall` the route layer will automatically run the encoders in async mode.\n",
+ "\n",
+ "**Azure OpenAI:**\n",
+ "\n",
+ "```python\n",
+ "from semantic_router.encoders import AzureOpenAIEncoder\n",
+ "\n",
+ "encoder = AzureOpenAIEncoder(\n",
+ " api_key=\"YOUR_AZURE_OPENAI_API_KEY\",\n",
+ " deployment_name=\"YOUR_DEPLOYMENT_NAME\",\n",
+ " azure_endpoint=\"YOUR_ENDPOINT\",\n",
+ " api_version=\"2024-02-01\",\n",
+ " model=\"text-embedding-3-small\",\n",
+ ")\n",
+ "```"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**OpenAI:**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from getpass import getpass\n",
+ "from semantic_router.encoders import OpenAIEncoder\n",
+ "\n",
+ "# get at platform.openai.com\n",
+ "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\") or getpass(\n",
+ " \"Enter OpenAI API key: \"\n",
+ ")\n",
+ "encoder = OpenAIEncoder(name=\"text-embedding-3-small\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We can see encoder details, including default `score_threshold` like so:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "OpenAIEncoder(name='text-embedding-3-small', score_threshold=0.3, type='openai', client=<openai.OpenAI object at 0x117d35e50>, async_client=<openai.AsyncOpenAI object at 0x117d47ad0>, dimensions=NOT_GIVEN, token_limit=8192)"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "encoder"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We can create embeddings asynchronously via our encoder using the `encoder.acall` method:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[[-0.009877119213342667,\n",
+ " 0.0015331337926909328,\n",
+ " 0.015642808750271797,\n",
+ " -0.05476367473602295,\n",
+ " -0.006405937951058149,\n",
+ " ...],\n",
+ " [0.012598802335560322,\n",
+ " -0.0037690235767513514,\n",
+ " 0.025685198605060577,\n",
+ " -0.08883649855852127,\n",
+ " 0.0013644769787788391,\n",
+ " ...]]"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "await encoder.acall(docs=[\"test\", \"test 2\"])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "For our `PineconeIndex` we do the exact same thing, ie we initialize as usual:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "from semantic_router.index.pinecone import PineconeIndex\n",
+ "\n",
+ "# get at app.pinecone.io\n",
+ "os.environ[\"PINECONE_API_KEY\"] = os.environ.get(\"PINECONE_API_KEY\") or getpass(\n",
+ " \"Enter Pinecone API key: \"\n",
+ ")\n",
+ "pc_index = PineconeIndex(dimensions=1536)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There are several async methods we can call directly:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'indexes': []}"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "await pc_index._async_list_indexes()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "But unless we're using the index directly, we don't need to use these. As with the encoder, once we pass the `PineconeIndex` to our route layer, the route layer will call all async methods automatically when we hit the `acall` method."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Async RouteLayer"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The `RouteLayer` class supports both sync and async operations by default, so we initialize as usual:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from semantic_router.layer import RouteLayer\n",
+ "\n",
+ "rl = RouteLayer(encoder=encoder, routes=routes, index=pc_index)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We can check our route layer and index information as usual:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['politics', 'chitchat']"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl.list_route_names()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "10"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(rl.index)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We can also view all of the records for a given route:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['politics#64069085d9d6e98e5a80915f69fabe82bac6c742f801bc305c5001dce88f0d19',\n",
+ " 'politics#af8b76111f260cf44fb34f04fcf82927dcbe08e8f47c30f4d571379c1512fac8',\n",
+ " 'politics#d1bb40236c3d95b9c695bfa86b314b6da4eb87e136699563fccae47fccea23e2',\n",
+ " 'politics#ed0f3dd7bd5dea12e55b1953bcd2c562a5ab19f501f6d5ff8c8927652c3904b8',\n",
+ " 'politics#fc6d15f9e6075e6de82b3fbef6722b64353e4eadc8d663b7312a4ed60c43e6f6']"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl.index._get_route_ids(route_name=\"politics\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "And now for async vs. sync usage! To call in synchronous mode we simply hit `rl(...)`, to switch to async mode we hit `rl.acall(...)`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'politics'"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl(\"don't you love politics\").name # SYNC mode"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'politics'"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out = await rl.acall(\"don't you love politics?\") # ASYNC mode\n",
+ "out.name"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let's try a few more sync and async requests:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'chitchat'"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl(\"how's the weather today?\").name"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'chitchat'"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out = await rl.acall(\"how's the weather today?\")\n",
+ "out.name"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "rl(\"I'm interested in learning about llama 2\").name"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "out = await rl.acall(\"I'm interested in learning about llama 2\")\n",
+ "out.name"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We can delete or update routes using the usual synchronous methods:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "10"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(rl.index)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "5"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import time\n",
+ "\n",
+ "rl.delete(route_name=\"chitchat\")\n",
+ "time.sleep(3)\n",
+ "len(rl.index)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "out = await rl.acall(\"how's the weather today?\")\n",
+ "out.name"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('politics', \"why don't you tell me about your political opinions\"),\n",
+ " ('politics',\n",
+ " \"don't you just love the presidentdon't you just hate the president\"),\n",
+ " ('politics', \"isn't politics the best thing ever\"),\n",
+ " ('politics', \"they're going to destroy this country!\"),\n",
+ " ('politics', 'they will save the country!')]"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl.index.get_routes()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'type': 'pinecone', 'dimensions': 1536, 'vectors': 5}"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rl.index.describe()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "semantic_router_1",
+ "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
+}
--
GitLab