diff --git a/docs/docs/integrations/llm_caching.ipynb b/docs/docs/integrations/llm_caching.ipynb
index 4ac832199e6..72d058e2960 100644
--- a/docs/docs/integrations/llm_caching.ipynb
+++ b/docs/docs/integrations/llm_caching.ipynb
@@ -334,6 +334,121 @@
     "llm.invoke(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b29dd776",
+   "metadata": {},
+   "source": [
+    "### Semantic Cache\n",
+    "Use [Upstash Vector](https://upstash.com/docs/vector/overall/whatisvector) to do a semantic similarity search and cache the most similar response in the database. The vectorization is automatically done by the selected embedding model while creating Upstash Vector database. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37fb3c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install upstash-semantic-cache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "8470eedc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.globals import set_llm_cache\n",
+    "from upstash_semantic_cache import SemanticCache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "16b9fb03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "UPSTASH_VECTOR_REST_URL = \"<UPSTASH_VECTOR_REST_URL>\"\n",
+    "UPSTASH_VECTOR_REST_TOKEN = \"<UPSTASH_VECTOR_REST_TOKEN>\"\n",
+    "\n",
+    "cache = SemanticCache(\n",
+    "    url=UPSTASH_VECTOR_REST_URL, token=UPSTASH_VECTOR_REST_TOKEN, min_proximity=0.7\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "8d37104b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "set_llm_cache(cache)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "926a08b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 28.4 ms, sys: 3.93 ms, total: 32.3 ms\n",
+      "Wall time: 1.89 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nNew York City is the most crowded city in the USA.'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm.invoke(\"Which city is the most crowded city in the USA?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "0ce37d57",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3.22 ms, sys: 940 μs, total: 4.16 ms\n",
+      "Wall time: 97.7 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nNew York City is the most crowded city in the USA.'"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm.invoke(\"Which city has the highest population in the USA?\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "278ad7ae",
@@ -2684,7 +2799,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.12.3"
   }
  },
  "nbformat": 4,