Removed unnecessary code from quickstart-rag

Author: HeidiSteen

Quickstart-RAG/Quickstart-rag.ipynb

@@ -48,9 +48,9 @@
     "       }]},\n",
     "    ```\n",
     "\n",
-    "- On Azure AI Search, create a role assignment for the Azure OpenAI managed identity. Required roles: Search Index Data Reader, Search Service Contributor.\n",
+    "- On Azure AI Search, create a role assignment for the Azure OpenAI managed identity. Required roles: **Search Index Data Reader**, **Search Service Contributor**.\n",
     "\n",
-    "- On Azure OpenAI, create a role assigmnet for the user running the code: Required role: Cognitive Services OpenAI User."
+    "- On Azure OpenAI, create a role assigment for the user running the code: Required role: **Cognitive Services OpenAI User**."
    ]
   },
   {
@@ -84,7 +84,6 @@
    "outputs": [],
    "source": [
     "# Set query parameters for grounding the conversation on your search index\n",
-    "k=50\n",
     "search_type=\"text\"\n",
     "use_semantic_reranker=True\n",
     "sources_to_include=5"
@@ -100,12 +99,10 @@
     "from azure.core.credentials_async import AsyncTokenCredential\n",
     "from azure.identity.aio import get_bearer_token_provider\n",
     "from azure.search.documents.aio import SearchClient\n",
-    "from azure.search.documents.models import VectorizableTextQuery, HybridSearch\n",
     "from openai import AsyncAzureOpenAI\n",
     "from enum import Enum\n",
     "from typing import List, Optional\n",
     "\n",
-    "\n",
     "def create_openai_client(credential: AsyncTokenCredential) -> AsyncAzureOpenAI:\n",
     "    token_provider = get_bearer_token_provider(credential, \"https://cognitiveservices.azure.com/.default\")\n",
     "    return AsyncAzureOpenAI(\n",
@@ -128,7 +125,7 @@
     "    HYBRID = \"hybrid\"\n",
     "\n",
     "# This function retrieves the sselected fields from the search index\n",
-    "async def get_sources(search_client: SearchClient, query: str, search_type: SearchType, use_semantic_reranker: bool = True, sources_to_include: int = 5, k: int = 50) -> List[str]:\n",
+    "async def get_sources(search_client: SearchClient, query: str, search_type: SearchType, use_semantic_reranker: bool = True, sources_to_include: int = 5) -> List[str]:\n",
     "    search_type == SearchType.TEXT,\n",
     "    response = await search_client.search(\n",
     "        search_text=query,\n",
@@ -159,8 +156,8 @@
     "            \"content\": message\n",
     "        })\n",
     "\n",
-    "    async def append_grounded_message(self, search_client: SearchClient, query: str, search_type: SearchType, use_semantic_reranker: bool = True, sources_to_include: int = 5, k: int = 50):\n",
-    "        sources = await get_sources(search_client, query, search_type, use_semantic_reranker, sources_to_include, k)\n",
+    "    async def append_grounded_message(self, search_client: SearchClient, query: str, search_type: SearchType, use_semantic_reranker: bool = True, sources_to_include: int = 5):\n",
+    "        sources = await get_sources(search_client, query, search_type, use_semantic_reranker, sources_to_include)\n",
     "        sources_formatted = \"\\n\".join([f'{document[\"HotelName\"]}:{document[\"Description\"]}:{document[\"Tags\"]}' for document in sources])\n",
     "        self.append_message(role=\"user\", message=GROUNDED_PROMPT.format(query=query, sources=sources_formatted))\n",
     "        self.search_results.append(\n",