Update elastic search cookbook to use latest API (openai#1899)

Author: imran-binhasan

examples/vector_databases/elasticsearch/elasticsearch-semantic-search.ipynb

@@ -37,14 +37,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "8c304b93",
    "metadata": {},
    "outputs": [],
    "source": [
     "# install packages\n",
     "\n",
-    "!python3 -m pip install -qU openai pandas wget elasticsearch\n",
+    "! python3 -m pip install -qU openai pandas wget elasticsearch\n",
     "\n",
     "# import modules\n",
     "\n",
@@ -54,7 +54,7 @@
     "import zipfile\n",
     "import pandas as pd\n",
     "import json\n",
-    "import openai"
+    "from openai import OpenAI"
    ]
   },
   {
@@ -321,25 +321,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "57385c69",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Get OpenAI API key\n",
-    "OPENAI_API_KEY = getpass(\"Enter OpenAI API key\")\n",
-    "\n",
-    "# Set API key\n",
-    "openai.api_key = OPENAI_API_KEY\n",
-    "\n",
-    "# Define model\n",
-    "EMBEDDING_MODEL = \"text-embedding-3-small\"\n",
+    "# Create OpenAI client\n",
+    "openai_client = OpenAI()\n",
     "\n",
     "# Define question\n",
     "question = 'Is the Atlantic the biggest ocean in the world?'\n",
     "\n",
-    "# Create embedding\n",
-    "question_embedding = openai.Embedding.create(input=question, model=EMBEDDING_MODEL)\n"
+    "question_embedding = openai_client.embeddings.create(\n",
+    "    input=question,\n",
+    "    model=\"text-embedding-3-small\"\n",
+    ")"
    ]
   },
   {
@@ -383,7 +379,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "fc834fdd",
    "metadata": {},
    "outputs": [
@@ -764,7 +760,7 @@
     "  index = \"wikipedia_vector_index\",\n",
     "  knn={\n",
     "      \"field\": \"content_vector\",\n",
-    "      \"query_vector\":  question_embedding[\"data\"][0][\"embedding\"],\n",
+    "      \"query_vector\":  question_embedding.data[0].embedding,\n",
     "      \"k\": 10,\n",
     "      \"num_candidates\": 100\n",
     "    }\n",

registry.yaml

@@ -866,7 +866,6 @@
     - leemthompo
   tags:
     - embeddings
-    - completions
 
 - title: Using Hologres as a vector database for OpenAI embeddings
   path: >-