Review comment and format

Author: john0isaac

rag-azure-openai-cosmosdb-notebook.ipynb

@@ -59,16 +59,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "True"
+       "False"
       ]
      },
-     "execution_count": 1,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -105,9 +105,7 @@
     "\n",
     "# Vector search index parameters\n",
     "index_name = \"VectorSearchIndex\"\n",
-    "vector_dimensions = (\n",
-    "    1536  # text-embedding-ada-002 uses a 1536-dimensional embedding vector\n",
-    ")\n",
+    "vector_dimensions = 1536  # text-embedding-ada-002 uses a 1536-dimensional embedding vector\n",
     "num_lists = 1\n",
     "similarity = \"COS\"  # cosine distance"
    ]
@@ -141,16 +139,14 @@
     "from semantic_kernel.memory.memory_store_base import MemoryStoreBase\n",
     "\n",
     "\n",
-    "async def upsert_data_to_memory_store(\n",
-    "    memory: SemanticTextMemory, store: MemoryStoreBase, data_file_path: str\n",
-    ") -> None:\n",
+    "async def upsert_data_to_memory_store(memory: SemanticTextMemory, store: MemoryStoreBase, data_file_path: str) -> None:\n",
     "    \"\"\"\n",
     "    This asynchronous function takes two memory stores and a data file path as arguments.\n",
     "    It is designed to upsert (update or insert) data into the memory stores from the data file.\n",
     "\n",
     "    Args:\n",
-    "        kernel_memory_store (callable): A callable object that represents the kernel memory store where data will be upserted.\n",
-    "        memory_store (callable): A callable object that represents the memory store where data will be upserted.\n",
+    "        memory (callable): A callable object that represents the semantic kernel memory.\n",
+    "        store (callable): A callable object that represents the memory store where data will be upserted.\n",
     "        data_file_path (str): The path to the data file that contains the data to be upserted.\n",
     "\n",
     "    Returns:\n",
@@ -164,11 +160,7 @@
     "            # check if the item already exists in the memory store\n",
     "            # if the id doesn't exist, it throws an exception\n",
     "            try:\n",
-    "                already_created = bool(\n",
-    "                    await store.get(\n",
-    "                        collection_name, item[\"id\"], with_embedding=True\n",
-    "                    )\n",
-    "                )\n",
+    "                already_created = bool(await store.get(collection_name, item[\"id\"], with_embedding=True))\n",
     "            except Exception:\n",
     "                already_created = False\n",
     "            # if the record doesn't exist, we generate embeddings and save it to the database\n",
@@ -297,9 +289,7 @@
    ],
    "source": [
     "# adding azure openai text embedding service\n",
-    "embedding_model_deployment_name = os.environ.get(\n",
-    "    \"AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME\"\n",
-    ")\n",
+    "embedding_model_deployment_name = os.environ.get(\"AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME\")\n",
     "\n",
     "kernel.add_service(\n",
     "    AzureTextEmbedding(\n",
@@ -515,11 +505,7 @@
     "from semantic_kernel.connectors.ai.open_ai import OpenAITextPromptExecutionSettings\n",
     "\n",
     "execution_settings = OpenAITextPromptExecutionSettings(\n",
-    "    service_id=\"chat_completion\",\n",
-    "    ai_model_id=chat_model_deployment_name,\n",
-    "    max_tokens=500,\n",
-    "    temperature=0.0,\n",
-    "    top_p=0.5\n",
+    "    service_id=\"chat_completion\", ai_model_id=chat_model_deployment_name, max_tokens=500, temperature=0.0, top_p=0.5\n",
     ")"
    ]
   },
@@ -540,7 +526,7 @@
     "        InputVariable(name=\"db_record\", description=\"The database record\", is_required=True),\n",
     "        InputVariable(name=\"query_term\", description=\"The user input\", is_required=True),\n",
     "    ],\n",
-    "    execution_settings=execution_settings\n",
+    "    execution_settings=execution_settings,\n",
     ")"
    ]
   },
@@ -551,9 +537,7 @@
    "outputs": [],
    "source": [
     "chat_function = kernel.create_function_from_prompt(\n",
-    "    function_name= \"ChatGPTFunc\",\n",
-    "    plugin_name=\"chatGPTPlugin\",\n",
-    "    prompt_template_config=chat_prompt_template_config\n",
+    "    function_name=\"ChatGPTFunc\", plugin_name=\"chatGPTPlugin\", prompt_template_config=chat_prompt_template_config\n",
     ")"
    ]
   },
@@ -563,7 +547,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "completions_result = await kernel.invoke(chat_function, sk.KernelArguments(query_term=query_term, db_record=result[0].additional_metadata))"
+    "completions_result = await kernel.invoke(\n",
+    "    chat_function, sk.KernelArguments(query_term=query_term, db_record=result[0].additional_metadata)\n",
+    ")"
    ]
   },
   {
@@ -629,7 +615,9 @@
     "while query_term != \"exit\":\n",
     "    query_term = input(\"Enter a query: \")\n",
     "    result = await memory.search(collection_name, query_term)\n",
-    "    completions_result = kernel.invoke_stream(chat_function, sk.KernelArguments(query_term=query_term, db_record=result[0].additional_metadata))\n",
+    "    completions_result = kernel.invoke_stream(\n",
+    "        chat_function, sk.KernelArguments(query_term=query_term, db_record=result[0].additional_metadata)\n",
+    "    )\n",
     "    print(f\"Question:\\n{query_term}\\nResponse:\")\n",
     "    async for completion in completions_result:\n",
     "        print(str(completion[0]), end=\"\")\n",
@@ -654,7 +642,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,