Added Semantic Cache Example with BedrockChat using Bedrock Embedding…

docs/docs/integrations/chat/bedrock.ipynb

@@ -137,6 +137,77 @@
     "for chunk in chat.stream(messages):\n",
     "    print(chunk.content, end=\"\", flush=True)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c36575b3",
+   "metadata": {},
+   "source": [
+    "### LLM Caching with OpenSearch Semantic Cache\n",
+    "\n",
+    "Use OpenSearch as a semantic cache to cache prompts and responses and evaluate hits based on semantic similarity.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "375d4e56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.globals import set_llm_cache\n",
+    "from langchain_aws import BedrockEmbeddings, ChatBedrock\n",
+    "from langchain_community.cache import OpenSearchSemanticCache\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "bedrock_embeddings = BedrockEmbeddings(\n",
+    "    model_id=\"amazon.titan-embed-text-v1\", region_name=\"us-east-1\"\n",
+    ")\n",
+    "\n",
+    "chat = ChatBedrock(\n",
+    "    model_id=\"anthropic.claude-3-haiku-20240307-v1:0\", model_kwargs={\"temperature\": 0.5}\n",
+    ")\n",
+    "\n",
+    "# Enable LLM cache. Make sure OpenSearch is set up and running. Update URL accordingly.\n",
+    "set_llm_cache(\n",
+    "    OpenSearchSemanticCache(\n",
+    "        opensearch_url=\"http://localhost:9200\", embedding=bedrock_embeddings\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb5d25bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "messages = [HumanMessage(content=\"tell me about Amazon Bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
+    "\n",
+    "print(response_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cfb3086",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "# The second time, while not a direct hit, the question is semantically similar to the original question,\n",
+    "# so it uses the cached result!\n",
+    "\n",
+    "messages = [HumanMessage(content=\"what is amazon bedrock\")]\n",
+    "response_text = chat.invoke(messages)\n",
+    "\n",
+    "print(response_text)"
+   ]
   }
  ],
  "metadata": {