cosmosdbnosql: Added Cosmos DB NoSQL Semantic Cache Integration with tests and jupyter notebook (#24424)

* Added Cosmos DB NoSQL Semantic Cache Integration with tests and
jupyter notebook

---------

Co-authored-by: Aayush Kataria <aayushkataria3011@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>

docs/docs/integrations/llm_caching.ipynb

@@ -14,8 +14,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "88486f6f",
+   "execution_count": null,
+   "id": "f938e881",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -30,12 +30,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "10ad9224",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-04-12T02:05:57.319706Z",
-     "start_time": "2024-04-12T02:05:57.303868Z"
+     "end_time": "2024-12-06T00:54:06.474593Z",
+     "start_time": "2024-12-06T00:53:58.727138Z"
     }
    },
    "outputs": [],
@@ -1820,7 +1820,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": null,
    "id": "bc1570a2a77b58c8",
    "metadata": {
     "ExecuteTime": {
@@ -1848,12 +1848,155 @@
      "output_type": "execute_result"
     }
    ],
+   "source": [
+    "%%time\n",
+    "# The second time it is, so it goes faster\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "235ff73bf7143f13",
+   "metadata": {},
+   "source": [
+    "## Azure CosmosDB NoSql Semantic Cache\n",
+    "\n",
+    "You can use this integrated [vector database](https://learn.microsoft.com/en-us/azure/cosmos-db/vector-database) for caching."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41fea5aa7b2153ca",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-06T00:55:38.648972Z",
+     "start_time": "2024-12-06T00:55:38.290541Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from typing import Any, Dict\n",
+    "\n",
+    "from azure.cosmos import CosmosClient, PartitionKey\n",
+    "from langchain_community.cache import AzureCosmosDBNoSqlSemanticCache\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "HOST = \"COSMOS_DB_URI\"\n",
+    "KEY = \"COSMOS_DB_KEY\"\n",
+    "\n",
+    "cosmos_client = CosmosClient(HOST, KEY)\n",
+    "\n",
+    "\n",
+    "def get_vector_indexing_policy() -> dict:\n",
+    "    return {\n",
+    "        \"indexingMode\": \"consistent\",\n",
+    "        \"includedPaths\": [{\"path\": \"/*\"}],\n",
+    "        \"excludedPaths\": [{\"path\": '/\"_etag\"/?'}],\n",
+    "        \"vectorIndexes\": [{\"path\": \"/embedding\", \"type\": \"diskANN\"}],\n",
+    "    }\n",
+    "\n",
+    "\n",
+    "def get_vector_embedding_policy() -> dict:\n",
+    "    return {\n",
+    "        \"vectorEmbeddings\": [\n",
+    "            {\n",
+    "                \"path\": \"/embedding\",\n",
+    "                \"dataType\": \"float32\",\n",
+    "                \"dimensions\": 1536,\n",
+    "                \"distanceFunction\": \"cosine\",\n",
+    "            }\n",
+    "        ]\n",
+    "    }\n",
+    "\n",
+    "\n",
+    "cosmos_container_properties_test = {\"partition_key\": PartitionKey(path=\"/id\")}\n",
+    "cosmos_database_properties_test: Dict[str, Any] = {}\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    AzureCosmosDBNoSqlSemanticCache(\n",
+    "        cosmos_client=cosmos_client,\n",
+    "        embedding=OpenAIEmbeddings(),\n",
+    "        vector_embedding_policy=get_vector_embedding_policy(),\n",
+    "        indexing_policy=get_vector_indexing_policy(),\n",
+    "        cosmos_container_properties=cosmos_container_properties_test,\n",
+    "        cosmos_database_properties=cosmos_database_properties_test,\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1e1cd93819921bf6",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-06T00:55:44.513080Z",
+     "start_time": "2024-12-06T00:55:41.353843Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 374 ms, sys: 34.2 ms, total: 408 ms\n",
+      "Wall time: 3.15 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "%%time\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
     "llm.invoke(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "576ce24c1244812a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-06T00:55:50.925865Z",
+     "start_time": "2024-12-06T00:55:50.548520Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 17.7 ms, sys: 2.88 ms, total: 20.6 ms\n",
+      "Wall time: 373 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy couldn't the bicycle stand up by itself? Because it was two-tired!\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time it is, so it goes faster\n",
+    "llm.invoke(\"Tell me a joke\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "306ff47b",