Harrison/redis cache (#3766)

Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>

docs/modules/models/llms/examples/llm_caching.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "f69f6283",
    "metadata": {},
    "outputs": [],
@@ -52,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "64005d1f",
    "metadata": {},
    "outputs": [
@@ -60,8 +60,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 14.2 ms, sys: 4.9 ms, total: 19.1 ms\n",
-      "Wall time: 1.1 s\n"
+      "CPU times: user 26.1 ms, sys: 21.5 ms, total: 47.6 ms\n",
+      "Wall time: 1.68 s\n"
      ]
     },
     {
@@ -70,7 +70,7 @@
        "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -83,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "c8a1cb2b",
    "metadata": {},
    "outputs": [
@@ -91,8 +91,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 162 µs, sys: 7 µs, total: 169 µs\n",
-      "Wall time: 175 µs\n"
+      "CPU times: user 238 µs, sys: 143 µs, total: 381 µs\n",
+      "Wall time: 1.76 ms\n"
      ]
     },
     {
@@ -101,7 +101,7 @@
        "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -214,9 +214,18 @@
     "## Redis Cache"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "c5c9a4d5",
+   "metadata": {},
+   "source": [
+    "### Standard Cache\n",
+    "Use [Redis](../../../../ecosystem/redis.md) to cache prompts and responses."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "39f6eb0b",
    "metadata": {},
    "outputs": [],
@@ -225,15 +234,35 @@
     "# (make sure your local Redis instance is running first before running this example)\n",
     "from redis import Redis\n",
     "from langchain.cache import RedisCache\n",
+    "\n",
     "langchain.llm_cache = RedisCache(redis_=Redis())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "28920749",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 6.88 ms, sys: 8.75 ms, total: 15.6 ms\n",
+      "Wall time: 1.04 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "%%time\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
@@ -242,16 +271,124 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "94bf9415",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1.59 ms, sys: 610 µs, total: 2.2 ms\n",
+      "Wall time: 5.58 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "%%time\n",
     "# The second time it is, so it goes faster\n",
     "llm(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "82be23f6",
+   "metadata": {},
+   "source": [
+    "### Semantic Cache\n",
+    "Use [Redis](../../../../ecosystem/redis.md) to cache prompts and responses and evaluate hits based on semantic similarity."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "64df3099",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.cache import RedisSemanticCache\n",
+    "\n",
+    "\n",
+    "langchain.llm_cache = RedisSemanticCache(\n",
+    "    redis_url=\"redis://localhost:6379\",\n",
+    "    embedding=OpenAIEmbeddings()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "8e91d3ac",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 351 ms, sys: 156 ms, total: 507 ms\n",
+      "Wall time: 3.37 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy don't scientists trust atoms?\\nBecause they make up everything.\""
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "df856948",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 6.25 ms, sys: 2.72 ms, total: 8.97 ms\n",
+      "Wall time: 262 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy don't scientists trust atoms?\\nBecause they make up everything.\""
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "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",
+    "llm(\"Tell me one joke\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "684eab55",