Fix RAG prompt to pass top hit as context (#39)

* Fix RAG prompt to pass top hit as context

* Update question

* Multiline for GH preview

Author: leemthompo

notebooks/integrations/openai/openai-KNN-RAG.ipynb

@@ -292,7 +292,7 @@
     "EMBEDDING_MODEL = \"text-embedding-ada-002\"\n",
     "\n",
     "# Define question\n",
-    "question = 'How wide is the Atlantic ocean?'\n",
+    "question = 'How big is the Atlantic ocean?'\n",
     "\n",
     "# Create embedding\n",
     "question_embedding = openai.Embedding.create(input=question, model=EMBEDDING_MODEL)\n"
@@ -353,16 +353,15 @@
     "      \"num_candidates\": 100\n",
     "    }\n",
     ")\n",
-    "pretty_response(response)"
+    "pretty_response(response)\n",
+    "top_hit_summary = response['hits']['hits'][0]['_source']['text'] # Store content of top hit for final step"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "276c1147",
    "metadata": {},
    "source": [
-    "## Next steps\n",
-    "\n",
     "Success! Now you know how to use Elasticsearch as a vector database to store embeddings, encode queries by calling the OpenAI [`embeddings`](https://platform.openai.com/docs/api-reference/embeddings) endpoint, and run semantic search using [kNN search](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html) to find the top results.\n",
     "\n",
     "Play around with different queries, and if you want to try with your own data, you can experiment with different embedding models.\n",
@@ -395,7 +394,10 @@
     "  model=\"gpt-3.5-turbo\",\n",
     "  messages=[\n",
     "        {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
-    "        {\"role\": \"user\", \"content\": \"Answer the following question:\" + question + \"by using the following text:\"},\n",
+    "        {\"role\": \"user\", \"content\": \"Answer the following question:\" \n",
+    "         + question \n",
+    "         + \"by using the following text:\" \n",
+    "         + top_hit_summary},\n",
     "    ]\n",
     ")\n",
     "\n",