Initial commit

examples/Get_embeddings.ipynb

@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get embeddings\n",
+    "\n",
+    "The function `get_embedding` will give us an embedding for an input text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "12288"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import openai\n",
+    "\n",
+    "embedding = openai.Embedding.create(input=\"Sample document text goes here\", engine=\"text-similarity-davinci-001\")['data'][0]['embedding']\n",
+    "len(embedding)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1024\n"
+     ]
+    }
+   ],
+   "source": [
+    "import openai\n",
+    "from tenacity import retry, wait_random_exponential, stop_after_attempt\n",
+    "\n",
+    "@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))\n",
+    "def get_embedding(text: str, engine=\"text-similarity-davinci-001\") -> List[float]:\n",
+    "\n",
+    "    # replace newlines, which can negatively affect performance.\n",
+    "    text = text.replace(\"\\n\", \" \")\n",
+    "\n",
+    "    return openai.Embedding.create(input=[text], engine=engine)[\"data\"][0][\"embedding\"]\n",
+    "\n",
+    "embedding = get_embedding(\"Sample query text goes here\", engine=\"text-search-ada-query-001\")\n",
+    "print(len(embedding))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1024\n"
+     ]
+    }
+   ],
+   "source": [
+    "embedding = get_embedding(\"Sample document text goes here\", engine=\"text-search-ada-doc-001\")\n",
+    "print(len(embedding))"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "be4b5d5b73a21c599de40d6deb1129796d12dc1cc33a738f7bac13269cfcafe8"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.7.3 64-bit ('base': conda)",
+   "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": "3.7.3"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}