diff --git a/python-recipes/RAG/01_redisvl.ipynb b/python-recipes/RAG/01_redisvl.ipynb
index fef526d3..b1d2d34c 100644
--- a/python-recipes/RAG/01_redisvl.ipynb
+++ b/python-recipes/RAG/01_redisvl.ipynb
@@ -35,40 +35,40 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 8,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T04:41:18.607703Z",
+     "start_time": "2025-04-24T04:41:11.664107Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "AJJ2UW6M1ui0",
-    "outputId": "0f5773b7-a292-4ee6-f4bd-20dc40ca2aba",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T04:41:18.607703Z",
-     "start_time": "2025-04-24T04:41:11.664107Z"
-    }
+    "outputId": "0f5773b7-a292-4ee6-f4bd-20dc40ca2aba"
    },
-   "source": [
-    "# NBVAL_SKIP\n",
-    "!git clone https://github.com/redis-developer/redis-ai-resources.git temp_repo\n",
-    "!mv temp_repo/python-recipes/RAG/resources .\n",
-    "!rm -rf temp_repo"
-   ],
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Cloning into 'temp_repo'...\r\n",
-      "remote: Enumerating objects: 679, done.\u001B[K\r\n",
-      "remote: Counting objects: 100% (330/330), done.\u001B[Kjects:  82% (271/330)\u001B[K\r\n",
-      "remote: Compressing objects: 100% (214/214), done.\u001B[K\r\n",
-      "remote: Total 679 (delta 227), reused 148 (delta 115), pack-reused 349 (from 2)\u001B[K\r\n",
+      "remote: Enumerating objects: 679, done.\u001b[K\r\n",
+      "remote: Counting objects: 100% (330/330), done.\u001b[Kjects:  82% (271/330)\u001b[K\r\n",
+      "remote: Compressing objects: 100% (214/214), done.\u001b[K\r\n",
+      "remote: Total 679 (delta 227), reused 148 (delta 115), pack-reused 349 (from 2)\u001b[K\r\n",
       "Receiving objects: 100% (679/679), 57.80 MiB | 11.09 MiB/s, done.\r\n",
       "Resolving deltas: 100% (295/295), done.\r\n",
       "mv: rename temp_repo/python-recipes/RAG/resources to ./resources: Directory not empty\r\n"
      ]
     }
    ],
-   "execution_count": 8
+   "source": [
+    "# NBVAL_SKIP\n",
+    "!git clone https://github.com/redis-developer/redis-ai-resources.git temp_repo\n",
+    "!mv temp_repo/python-recipes/RAG/resources .\n",
+    "!rm -rf temp_repo"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -81,33 +81,33 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 9,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T04:41:20.572419Z",
+     "start_time": "2025-04-24T04:41:18.616143Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "DgxBQFXQ1ui2",
-    "outputId": "c3c399d6-e294-4a3a-a0a3-82d818509991",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T04:41:20.572419Z",
-     "start_time": "2025-04-24T04:41:18.616143Z"
-    }
+    "outputId": "c3c399d6-e294-4a3a-a0a3-82d818509991"
    },
-   "source": [
-    "%pip install -q redis \"redisvl>=0.4.1\" langchain-community pypdf sentence-transformers langchain openai pandas"
-   ],
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "\r\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m24.0\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m25.0.1\u001B[0m\r\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\r\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.0.1\u001b[0m\r\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\r\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
    ],
-   "execution_count": 9
+   "source": [
+    "%pip install -q \"redisvl>=0.6.0\" langchain-community pypdf sentence-transformers langchain openai pandas"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -134,6 +134,7 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -141,6 +142,7 @@
     "id": "c0d5lfNxJkD8",
     "outputId": "f96e72fa-b9f3-476f-bc9e-328bd30d1344"
    },
+   "outputs": [],
    "source": [
     "# NBVAL_SKIP\n",
     "%%sh\n",
@@ -149,9 +151,7 @@
     "sudo apt-get update  > /dev/null 2>&1\n",
     "sudo apt-get install redis-stack-server  > /dev/null 2>&1\n",
     "redis-stack-server --daemonize yes"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -180,13 +180,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 3,
    "metadata": {
-    "id": "ggh5TzhkJkD9",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:46:45.583246Z",
      "start_time": "2025-04-24T16:46:45.581177Z"
-    }
+    },
+    "id": "ggh5TzhkJkD9"
    },
+   "outputs": [],
    "source": [
     "import os\n",
     "\n",
@@ -197,9 +199,7 @@
     "\n",
     "# If SSL is enabled on the endpoint, use rediss:// as the URL prefix\n",
     "REDIS_URL = f\"redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}\""
-   ],
-   "outputs": [],
-   "execution_count": 3
+   ]
   },
   {
    "cell_type": "markdown",
@@ -227,27 +227,18 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 4,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:46.043726Z",
+     "start_time": "2025-04-24T16:46:45.600472Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "uijl2qFH1ui3",
-    "outputId": "a99b3fcb-7cfd-4dbd-f258-57779cfcae3c",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:46.043726Z",
-     "start_time": "2025-04-24T16:46:45.600472Z"
-    }
+    "outputId": "a99b3fcb-7cfd-4dbd-f258-57779cfcae3c"
    },
-   "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_community.document_loaders import PyPDFLoader\n",
-    "\n",
-    "# Load list of pdfs from a folder\n",
-    "data_path = \"resources/\"\n",
-    "docs = [os.path.join(data_path, file) for file in os.listdir(data_path)]\n",
-    "\n",
-    "print(\"Listing available documents ...\", docs)"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -257,21 +248,40 @@
      ]
     }
    ],
-   "execution_count": 4
+   "source": [
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import PyPDFLoader\n",
+    "\n",
+    "# Load list of pdfs from a folder\n",
+    "data_path = \"resources/\"\n",
+    "docs = [os.path.join(data_path, file) for file in os.listdir(data_path)]\n",
+    "\n",
+    "print(\"Listing available documents ...\", docs)"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 5,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:50.509810Z",
+     "start_time": "2025-04-24T16:46:46.104219Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "anya8hVnT6K_",
-    "outputId": "a8430acc-2e6d-45fd-fc8b-601fbbd8289b",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:50.509810Z",
-     "start_time": "2025-04-24T16:46:46.104219Z"
-    }
+    "outputId": "a8430acc-2e6d-45fd-fc8b-601fbbd8289b"
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Done preprocessing. Created 211 chunks of the original pdf resources/nke-10k-2023.pdf\n"
+     ]
+    }
+   ],
    "source": [
     "# pick out the Nike doc for this exercise\n",
     "doc = [doc for doc in docs if \"nke\" in doc][0]\n",
@@ -286,17 +296,7 @@
     "chunks = loader.load_and_split(text_splitter)\n",
     "\n",
     "print(\"Done preprocessing. Created\", len(chunks), \"chunks of the original pdf\", doc)"
-   ],
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Done preprocessing. Created 211 chunks of the original pdf resources/nke-10k-2023.pdf\n"
-     ]
-    }
-   ],
-   "execution_count": 5
+   ]
   },
   {
    "cell_type": "markdown",
@@ -310,7 +310,12 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 6,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:55.588165Z",
+     "start_time": "2025-04-24T16:46:50.528240Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 661,
@@ -461,41 +466,44 @@
      ]
     },
     "id": "N3iQ2aLEJkD9",
-    "outputId": "b0f0d2c1-41dc-4932-990b-53d2912af19e",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:55.588165Z",
-     "start_time": "2025-04-24T16:46:50.528240Z"
-    }
+    "outputId": "b0f0d2c1-41dc-4932-990b-53d2912af19e"
    },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import warnings\n",
     "import pandas as pd\n",
     "from redisvl.utils.vectorize import HFTextVectorizer, BaseVectorizer\n",
+    "from redisvl.extensions.cache.embeddings import EmbeddingsCache\n",
     "\n",
     "warnings.filterwarnings(\"ignore\")\n",
-    "\n",
-    "hf = HFTextVectorizer(\"sentence-transformers/all-MiniLM-L6-v2\")\n",
     "os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
     "\n",
+    "hf = HFTextVectorizer(\n",
+    "    model=\"sentence-transformers/all-MiniLM-L6-v2\",\n",
+    "    cache=EmbeddingsCache(\n",
+    "        name=\"embedcache\",\n",
+    "        ttl=600,\n",
+    "        redis_url=REDIS_URL,\n",
+    "    )\n",
+    ")\n",
+    "\n",
     "# Embed each chunk content\n",
     "embeddings = hf.embed_many([chunk.page_content for chunk in chunks])\n",
     "\n",
     "# Check to make sure we've created enough embeddings, 1 per document chunk\n",
     "len(embeddings) == len(chunks)"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "True"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 6
+   ]
   },
   {
    "cell_type": "markdown",
@@ -510,20 +518,21 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 7,
    "metadata": {
-    "id": "zB1EW_9n1ui-",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:46:55.611260Z",
      "start_time": "2025-04-24T16:46:55.598846Z"
-    }
+    },
+    "id": "zB1EW_9n1ui-"
    },
+   "outputs": [],
    "source": [
     "from redisvl.index import SearchIndex\n",
     "\n",
     "\n",
     "index_name = \"redisvl\"\n",
     "\n",
-    "\n",
     "schema = {\n",
     "  \"index\": {\n",
     "    \"name\": index_name,\n",
@@ -553,24 +562,18 @@
     "    }\n",
     "  ]\n",
     "}"
-   ],
-   "outputs": [],
-   "execution_count": 7
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 8,
    "metadata": {
-    "id": "LKuQku2CJkD9",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:46:55.630056Z",
      "start_time": "2025-04-24T16:46:55.620207Z"
-    }
+    },
+    "id": "LKuQku2CJkD9"
    },
-   "source": [
-    "# create an index from schema and the client\n",
-    "index = SearchIndex.from_dict(schema, redis_url=REDIS_URL)\n",
-    "index.create(overwrite=True, drop=True)"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -580,10 +583,15 @@
      ]
     }
    ],
-   "execution_count": 8
+   "source": [
+    "# create an index from schema and the client\n",
+    "index = SearchIndex.from_dict(schema, redis_url=REDIS_URL)\n",
+    "index.create(overwrite=True, drop=True)"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -591,30 +599,26 @@
     "id": "L6GOqmeN1ui_",
     "outputId": "91a199e3-d087-4b15-9544-d59efa6033c5"
    },
+   "outputs": [],
    "source": [
     "# use the RedisVL CLI tool to list all indices\n",
     "!rvl index listall"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 10,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:56.828176Z",
+     "start_time": "2025-04-24T16:46:56.283831Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "C70C-UWj1ujA",
-    "outputId": "1fb7a2d6-ae6d-4536-b4b7-702620efd128",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:56.828176Z",
-     "start_time": "2025-04-24T16:46:56.283831Z"
-    }
+    "outputId": "1fb7a2d6-ae6d-4536-b4b7-702620efd128"
    },
-   "source": [
-    "# get info about the index\n",
-    "!rvl index info -i redisvl"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -639,7 +643,10 @@
      ]
     }
    ],
-   "execution_count": 10
+   "source": [
+    "# get info about the index\n",
+    "!rvl index info -i redisvl"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -653,13 +660,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 11,
    "metadata": {
-    "id": "Zsg09Keg1ujA",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:46:56.895623Z",
      "start_time": "2025-04-24T16:46:56.836700Z"
-    }
+    },
+    "id": "Zsg09Keg1ujA"
    },
+   "outputs": [],
    "source": [
     "# load expects an iterable of dictionaries\n",
     "from redisvl.redis.utils import array_to_buffer\n",
@@ -675,9 +684,7 @@
     "\n",
     "# RedisVL handles batching automatically\n",
     "keys = index.load(data, id_field=\"chunk_id\")"
-   ],
-   "outputs": [],
-   "execution_count": 11
+   ]
   },
   {
    "cell_type": "markdown",
@@ -691,7 +698,12 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 12,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:56.991529Z",
+     "start_time": "2025-04-24T16:46:56.903370Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 85,
@@ -710,12 +722,20 @@
      ]
     },
     "id": "BkFv-_iC1ujB",
-    "outputId": "c398d356-6bb7-43a9-ca95-cb7f167d1f38",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:56.991529Z",
-     "start_time": "2025-04-24T16:46:56.903370Z"
-    }
+    "outputId": "c398d356-6bb7-43a9-ca95-cb7f167d1f38"
    },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'*=>[KNN 3 @text_embedding $vector AS vector_distance] RETURN 3 chunk_id content vector_distance SORTBY vector_distance ASC DIALECT 2 LIMIT 0 3'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from redisvl.query import VectorQuery\n",
     "\n",
@@ -733,56 +753,26 @@
     "\n",
     "# show the raw redis query\n",
     "str(vector_query)"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'*=>[KNN 3 @text_embedding $vector AS vector_distance] RETURN 3 chunk_id content vector_distance SORTBY vector_distance ASC DIALECT 2 LIMIT 0 3'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 12
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 13,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.008139Z",
+     "start_time": "2025-04-24T16:46:56.999381Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 143
     },
     "id": "5reL5qTW1ujC",
-    "outputId": "dd58f191-54f5-4226-c4e1-70207d58f2dc",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.008139Z",
-     "start_time": "2025-04-24T16:46:56.999381Z"
-    }
+    "outputId": "dd58f191-54f5-4226-c4e1-70207d58f2dc"
    },
-   "source": [
-    "# execute the query with RedisVL\n",
-    "result=index.query(vector_query)\n",
-    "\n",
-    "# view the results\n",
-    "pd.DataFrame(result)"
-   ],
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "         id vector_distance chunk_id  \\\n",
-       "0  chunk:88  0.337694525719       88   \n",
-       "1  chunk:80   0.34205275774       80   \n",
-       "2  chunk:87  0.357761025429       87   \n",
-       "\n",
-       "                                             content  \n",
-       "0  Asia Pacific & Latin America 1,932 1,896 2 % 1...  \n",
-       "1  Table of Contents\\nCONSOLIDATED OPERATING RESU...  \n",
-       "2  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -833,6 +823,17 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "         id vector_distance chunk_id  \\\n",
+       "0  chunk:88  0.337694525719       88   \n",
+       "1  chunk:80   0.34205275774       80   \n",
+       "2  chunk:87  0.357761025429       87   \n",
+       "\n",
+       "                                             content  \n",
+       "0  Asia Pacific & Latin America 1,932 1,896 2 % 1...  \n",
+       "1  Table of Contents\\nCONSOLIDATED OPERATING RESU...  \n",
+       "2  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...  "
       ]
      },
      "execution_count": 13,
@@ -840,26 +841,28 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 13
+   "source": [
+    "# execute the query with RedisVL\n",
+    "result=index.query(vector_query)\n",
+    "\n",
+    "# view the results\n",
+    "pd.DataFrame(result)"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 14,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.075644Z",
+     "start_time": "2025-04-24T16:46:57.067304Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "rZrcd6n7T6LE",
-    "outputId": "fad67a63-76bd-43b9-f62b-b1842ba47605",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.075644Z",
-     "start_time": "2025-04-24T16:46:57.067304Z"
-    }
+    "outputId": "fad67a63-76bd-43b9-f62b-b1842ba47605"
    },
-   "source": [
-    "# paginate through results\n",
-    "for result in index.paginate(vector_query, page_size=1):\n",
-    "    print(result[0][\"chunk_id\"], result[0][\"vector_distance\"], flush=True)"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -871,7 +874,11 @@
      ]
     }
    ],
-   "execution_count": 14
+   "source": [
+    "# paginate through results\n",
+    "for result in index.paginate(vector_query, page_size=1):\n",
+    "    print(result[0][\"chunk_id\"], result[0][\"vector_distance\"], flush=True)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -884,50 +891,22 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 15,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.172397Z",
+     "start_time": "2025-04-24T16:46:57.167834Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 175
     },
     "id": "daLVm6OkLn9T",
-    "outputId": "d77dfc4c-d451-4bf5-91c3-2155232570b9",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.172397Z",
-     "start_time": "2025-04-24T16:46:57.167834Z"
-    }
+    "outputId": "d77dfc4c-d451-4bf5-91c3-2155232570b9"
    },
-   "source": [
-    "# Sort by chunk_id field after vector search limits to topK\n",
-    "vector_query = VectorQuery(\n",
-    "    vector=query_embedding,\n",
-    "    vector_field_name=\"text_embedding\",\n",
-    "    num_results=4,\n",
-    "    return_fields=[\"chunk_id\"],\n",
-    "    return_score=True\n",
-    ")\n",
-    "\n",
-    "# Decompose vector_query into the core query and the params\n",
-    "query = vector_query.query\n",
-    "params = vector_query.params\n",
-    "\n",
-    "# Pass query and params direct to index.search()\n",
-    "result = index.search(\n",
-    "    query.sort_by(\"chunk_id\", asc=True),\n",
-    "    params\n",
-    ")\n",
-    "\n",
-    "pd.DataFrame([doc.__dict__ for doc in result.docs])\n"
-   ],
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "         id payload vector_distance chunk_id\n",
-       "0  chunk:80    None   0.34205275774       80\n",
-       "1  chunk:83    None  0.378765881062       83\n",
-       "2  chunk:87    None  0.357761025429       87\n",
-       "3  chunk:88    None  0.337694525719       88"
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -985,6 +964,13 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "         id payload vector_distance chunk_id\n",
+       "0  chunk:80    None   0.34205275774       80\n",
+       "1  chunk:83    None  0.378765881062       83\n",
+       "2  chunk:87    None  0.357761025429       87\n",
+       "3  chunk:88    None  0.337694525719       88"
       ]
      },
      "execution_count": 15,
@@ -992,7 +978,28 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 15
+   "source": [
+    "# Sort by chunk_id field after vector search limits to topK\n",
+    "vector_query = VectorQuery(\n",
+    "    vector=query_embedding,\n",
+    "    vector_field_name=\"text_embedding\",\n",
+    "    num_results=4,\n",
+    "    return_fields=[\"chunk_id\"],\n",
+    "    return_score=True\n",
+    ")\n",
+    "\n",
+    "# Decompose vector_query into the core query and the params\n",
+    "query = vector_query.query\n",
+    "params = vector_query.params\n",
+    "\n",
+    "# Pass query and params direct to index.search()\n",
+    "result = index.search(\n",
+    "    query.sort_by(\"chunk_id\", asc=True),\n",
+    "    params\n",
+    ")\n",
+    "\n",
+    "pd.DataFrame([doc.__dict__ for doc in result.docs])\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1005,53 +1012,22 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 16,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.279677Z",
+     "start_time": "2025-04-24T16:46:57.274997Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 175
     },
     "id": "a11G3xXJ1ujC",
-    "outputId": "d968add5-704d-4e22-d3bd-97c1d1103a75",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.279677Z",
-     "start_time": "2025-04-24T16:46:57.274997Z"
-    }
+    "outputId": "d968add5-704d-4e22-d3bd-97c1d1103a75"
    },
-   "source": [
-    "from redisvl.query.filter import Text\n",
-    "\n",
-    "vector_query = VectorQuery(\n",
-    "    vector=query_embedding,\n",
-    "    vector_field_name=\"text_embedding\",\n",
-    "    num_results=4,\n",
-    "    return_fields=[\"content\"],\n",
-    "    return_score=True\n",
-    ")\n",
-    "\n",
-    "# Set a text filter\n",
-    "text_filter = Text(\"content\") % \"profit\"\n",
-    "\n",
-    "vector_query.set_filter(text_filter)\n",
-    "\n",
-    "result=index.query(vector_query)\n",
-    "pd.DataFrame(result)"
-   ],
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "          id vector_distance  \\\n",
-       "0   chunk:83  0.378765881062   \n",
-       "1  chunk:129  0.418757200241   \n",
-       "2   chunk:73  0.465415120125   \n",
-       "3   chunk:63   0.49339401722   \n",
-       "\n",
-       "                                             content  \n",
-       "0  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C...  \n",
-       "1  Table of Contents\\nNIKE, INC.\\nCONSOLIDATED ST...  \n",
-       "2  Table of Contents\\nITEM 7. MANAGEMENT'S DISCUS...  \n",
-       "3  existing businesses, such as our NIKE Direct o...  "
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1104,6 +1080,19 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "          id vector_distance  \\\n",
+       "0   chunk:83  0.378765881062   \n",
+       "1  chunk:129  0.418757200241   \n",
+       "2   chunk:73  0.465415120125   \n",
+       "3   chunk:63   0.49339401722   \n",
+       "\n",
+       "                                             content  \n",
+       "0  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C...  \n",
+       "1  Table of Contents\\nNIKE, INC.\\nCONSOLIDATED ST...  \n",
+       "2  Table of Contents\\nITEM 7. MANAGEMENT'S DISCUS...  \n",
+       "3  existing businesses, such as our NIKE Direct o...  "
       ]
      },
      "execution_count": 16,
@@ -1111,7 +1100,25 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 16
+   "source": [
+    "from redisvl.query.filter import Text\n",
+    "\n",
+    "vector_query = VectorQuery(\n",
+    "    vector=query_embedding,\n",
+    "    vector_field_name=\"text_embedding\",\n",
+    "    num_results=4,\n",
+    "    return_fields=[\"content\"],\n",
+    "    return_score=True\n",
+    ")\n",
+    "\n",
+    "# Set a text filter\n",
+    "text_filter = Text(\"content\") % \"profit\"\n",
+    "\n",
+    "vector_query.set_filter(text_filter)\n",
+    "\n",
+    "result=index.query(vector_query)\n",
+    "pd.DataFrame(result)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1124,13 +1131,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 17,
    "metadata": {
-    "id": "bCffoZRx1ujD",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:46:57.391116Z",
      "start_time": "2025-04-24T16:46:57.389349Z"
-    }
+    },
+    "id": "bCffoZRx1ujD"
    },
+   "outputs": [],
    "source": [
     "from redisvl.query import RangeQuery\n",
     "\n",
@@ -1141,39 +1150,27 @@
     "    return_fields=[\"content\"],\n",
     "    return_score=True,\n",
     "    distance_threshold=0.8  # find all items with a semantic distance of less than 0.8\n",
-    ")"
-   ],
-   "outputs": [],
-   "execution_count": 17
+    ")"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 18,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.499232Z",
+     "start_time": "2025-04-24T16:46:57.494328Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 175
     },
     "id": "0gHmam1Q1ujD",
-    "outputId": "ac80a6ed-4eb8-44d3-881d-87c9271aa10e",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.499232Z",
-     "start_time": "2025-04-24T16:46:57.494328Z"
-    }
+    "outputId": "ac80a6ed-4eb8-44d3-881d-87c9271aa10e"
    },
-   "source": [
-    "result=index.query(range_query)\n",
-    "pd.DataFrame(result)"
-   ],
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "         id vector_distance                                            content\n",
-       "0  chunk:88  0.337694525719  Asia Pacific & Latin America 1,932 1,896 2 % 1...\n",
-       "1  chunk:80   0.34205275774  Table of Contents\\nCONSOLIDATED OPERATING RESU...\n",
-       "2  chunk:87  0.357761025429  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...\n",
-       "3  chunk:83  0.378765881062  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C..."
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1226,6 +1223,13 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "         id vector_distance                                            content\n",
+       "0  chunk:88  0.337694525719  Asia Pacific & Latin America 1,932 1,896 2 % 1...\n",
+       "1  chunk:80   0.34205275774  Table of Contents\\nCONSOLIDATED OPERATING RESU...\n",
+       "2  chunk:87  0.357761025429  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...\n",
+       "3  chunk:83  0.378765881062  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C..."
       ]
      },
      "execution_count": 18,
@@ -1233,39 +1237,29 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 18
+   "source": [
+    "result=index.query(range_query)\n",
+    "pd.DataFrame(result)"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 19,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.667013Z",
+     "start_time": "2025-04-24T16:46:57.662153Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 175
     },
     "id": "YZg4U21r1ujD",
-    "outputId": "d3db5ac3-6ae9-42c4-aaee-874cecafe3ad",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.667013Z",
-     "start_time": "2025-04-24T16:46:57.662153Z"
-    }
+    "outputId": "d3db5ac3-6ae9-42c4-aaee-874cecafe3ad"
    },
-   "source": [
-    "# Add filter to range query\n",
-    "range_query.set_filter(text_filter)\n",
-    "\n",
-    "index.query(range_query)\n",
-    "pd.DataFrame(result)"
-   ],
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "         id vector_distance                                            content\n",
-       "0  chunk:88  0.337694525719  Asia Pacific & Latin America 1,932 1,896 2 % 1...\n",
-       "1  chunk:80   0.34205275774  Table of Contents\\nCONSOLIDATED OPERATING RESU...\n",
-       "2  chunk:87  0.357761025429  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...\n",
-       "3  chunk:83  0.378765881062  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C..."
-      ],
       "text/html": [
        "<div>\n",
        "<style scoped>\n",
@@ -1318,6 +1312,13 @@
        "  </tbody>\n",
        "</table>\n",
        "</div>"
+      ],
+      "text/plain": [
+       "         id vector_distance                                            content\n",
+       "0  chunk:88  0.337694525719  Asia Pacific & Latin America 1,932 1,896 2 % 1...\n",
+       "1  chunk:80   0.34205275774  Table of Contents\\nCONSOLIDATED OPERATING RESU...\n",
+       "2  chunk:87  0.357761025429  Table of Contents\\nOPERATING SEGMENTS\\nAs disc...\n",
+       "3  chunk:83  0.378765881062  Table of Contents\\nGROSS MARGIN\\nFISCAL 2023 C..."
       ]
      },
      "execution_count": 19,
@@ -1325,7 +1326,13 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 19
+   "source": [
+    "# Add filter to range query\n",
+    "range_query.set_filter(text_filter)\n",
+    "\n",
+    "index.query(range_query)\n",
+    "pd.DataFrame(result)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1352,24 +1359,24 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 20,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:46:57.734454Z",
+     "start_time": "2025-04-24T16:46:57.732810Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "_esLGYzbT6LG",
-    "outputId": "d3314a08-8746-4239-dcb2-e7e41b51c640",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:46:57.734454Z",
-     "start_time": "2025-04-24T16:46:57.732810Z"
-    }
+    "outputId": "d3314a08-8746-4239-dcb2-e7e41b51c640"
    },
+   "outputs": [],
    "source": [
     "from redisvl.index import AsyncSearchIndex\n",
     "\n",
     "async_index = AsyncSearchIndex.from_dict(schema, redis_url=REDIS_URL)"
-   ],
-   "outputs": [],
-   "execution_count": 20
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1382,17 +1389,19 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 21,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:47:12.289527Z",
+     "start_time": "2025-04-24T16:46:57.837857Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "EgdTvz6zJkED",
-    "outputId": "d2ab0e8e-2ecf-458d-881d-6e4658953a71",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:47:12.289527Z",
-     "start_time": "2025-04-24T16:46:57.837857Z"
-    }
+    "outputId": "d2ab0e8e-2ecf-458d-881d-6e4658953a71"
    },
+   "outputs": [],
    "source": [
     "import openai\n",
     "import os\n",
@@ -1403,9 +1412,7 @@
     "\n",
     "if \"OPENAI_API_KEY\" not in os.environ:\n",
     "    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OPENAI_API_KEY :\")\n"
-   ],
-   "outputs": [],
-   "execution_count": 21
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1424,13 +1431,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 22,
    "metadata": {
-    "id": "1V1Tio4-ZjmA",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:12.308509Z",
      "start_time": "2025-04-24T16:47:12.303243Z"
-    }
+    },
+    "id": "1V1Tio4-ZjmA"
    },
+   "outputs": [],
    "source": [
     "\n",
     "async def answer_question(index: AsyncSearchIndex, query: str):\n",
@@ -1488,9 +1497,7 @@
     "\n",
     "    Answer:\n",
     "    '''"
-   ],
-   "outputs": [],
-   "execution_count": 22
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1503,13 +1510,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 23,
    "metadata": {
-    "id": "pn-PoACdbihY",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:12.339354Z",
      "start_time": "2025-04-24T16:47:12.337769Z"
-    }
+    },
+    "id": "pn-PoACdbihY"
    },
+   "outputs": [],
    "source": [
     "# Generate a list of questions\n",
     "questions = [\n",
@@ -1519,13 +1528,16 @@
     "    \"What does the company say about its environmental, social, and governance (ESG) practices?\",\n",
     "    \"What is the company's strategy for growth?\"\n",
     "]"
-   ],
-   "outputs": [],
-   "execution_count": 23
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 24,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:47:20.587275Z",
+     "start_time": "2025-04-24T16:47:12.352722Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/",
      "height": 264,
@@ -1588,21 +1600,16 @@
      ]
     },
     "id": "9M_iU6_hbv0J",
-    "outputId": "b9fc43d9-883a-4795-8a37-8a2f4c545892",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:47:20.587275Z",
-     "start_time": "2025-04-24T16:47:12.352722Z"
-    }
+    "outputId": "b9fc43d9-883a-4795-8a37-8a2f4c545892"
    },
+   "outputs": [],
    "source": [
     "import asyncio\n",
     "\n",
     "results = await asyncio.gather(*[\n",
     "    answer_question(async_index, question) for question in questions\n",
     "])"
-   ],
-   "outputs": [],
-   "execution_count": 24
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1615,22 +1622,18 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 25,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-04-24T16:47:20.604843Z",
+     "start_time": "2025-04-24T16:47:20.602566Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "7SZM_xg3b9Gb",
-    "outputId": "758ae31a-2291-4191-aa57-ee941d3319cb",
-    "ExecuteTime": {
-     "end_time": "2025-04-24T16:47:20.604843Z",
-     "start_time": "2025-04-24T16:47:20.602566Z"
-    }
+    "outputId": "758ae31a-2291-4191-aa57-ee941d3319cb"
    },
-   "source": [
-    "for i, r in enumerate(results):\n",
-    "    print(f\"Question: {questions[i]}\")\n",
-    "    print(f\"Answer: \\n {r}\", \"\\n-----------\\n\")"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -1683,21 +1686,37 @@
      ]
     }
    ],
-   "execution_count": 25
+   "source": [
+    "for i, r in enumerate(results):\n",
+    "    print(f\"Question: {questions[i]}\")\n",
+    "    print(f\"Answer: \\n {r}\", \"\\n-----------\\n\")"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
-   "source": "### Improve performance and cut costs with LLM caching"
+   "metadata": {},
+   "source": [
+    "### Improve performance and cut costs with LLM caching"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 26,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:20.654925Z",
      "start_time": "2025-04-24T16:47:20.639324Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "09:47:20 redisvl.index.index INFO   Index already exists, overwriting.\n"
+     ]
+    }
+   ],
    "source": [
     "from redisvl.extensions.llmcache import SemanticCache\n",
     "\n",
@@ -1709,26 +1728,18 @@
     "    distance_threshold=0.2,\n",
     "    overwrite=True,\n",
     ")"
-   ],
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "09:47:20 redisvl.index.index INFO   Index already exists, overwriting.\n"
-     ]
-    }
-   ],
-   "execution_count": 26
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 27,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:20.666720Z",
      "start_time": "2025-04-24T16:47:20.664080Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "from functools import wraps\n",
     "\n",
@@ -1770,24 +1781,17 @@
     "    )\n",
     "    # Response provided by GPT-3.5\n",
     "    return response.choices[0].message.content"
-   ],
-   "outputs": [],
-   "execution_count": 27
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 28,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:21.577338Z",
      "start_time": "2025-04-24T16:47:20.691181Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "# NBVAL_SKIP\n",
-    "query = \"What was Nike's revenue last year compared to this year??\"\n",
-    "\n",
-    "await answer_question(async_index, query)"
-   ],
    "outputs": [
     {
      "data": {
@@ -1800,24 +1804,22 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 28
+   "source": [
+    "# NBVAL_SKIP\n",
+    "query = \"What was Nike's revenue last year compared to this year??\"\n",
+    "\n",
+    "await answer_question(async_index, query)"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 29,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:21.606033Z",
      "start_time": "2025-04-24T16:47:21.590864Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "# NBVAL_SKIP\n",
-    "query = \"What was Nike's total revenue in the last year compared to now??\"\n",
-    "\n",
-    "await answer_question(async_index, query)\n",
-    "\n",
-    "# notice no HTTP request to OpenAI since this question is \"close enough\" to the last one"
-   ],
    "outputs": [
     {
      "name": "stdout",
@@ -1837,11 +1839,18 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 29
+   "source": [
+    "# NBVAL_SKIP\n",
+    "query = \"What was Nike's total revenue in the last year compared to now??\"\n",
+    "\n",
+    "await answer_question(async_index, query)\n",
+    "\n",
+    "# notice no HTTP request to OpenAI since this question is \"close enough\" to the last one"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "### Improve personalization by including chat session history\n",
     "\n",
@@ -1849,13 +1858,15 @@
    ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 30,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:21.642412Z",
      "start_time": "2025-04-24T16:47:21.634222Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "from functools import wraps\n",
     "from redisvl.extensions.session_manager import StandardSessionManager\n",
@@ -1945,39 +1956,49 @@
     "        ])\n",
     "\n",
     "        return answer"
-   ],
-   "outputs": [],
-   "execution_count": 30
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
-   "source": "## Test the entire RAG workflow"
+   "metadata": {},
+   "source": [
+    "## Test the entire RAG workflow"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 31,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:21.669248Z",
      "start_time": "2025-04-24T16:47:21.663308Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "# Setup Session\n",
     "chat = ChatBot(async_index, vectorizer=hf, user=\"Andrew\")\n",
     "await chat.clear_history()"
-   ],
-   "outputs": [],
-   "execution_count": 31
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 32,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:27.496044Z",
      "start_time": "2025-04-24T16:47:21.702428Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hi! How can I assist you today?\n"
+     ]
+    }
+   ],
    "source": [
     "# Run a simple chat\n",
     "stopterms = [\"exit\", \"quit\", \"end\", \"cancel\"]\n",
@@ -1990,30 +2011,17 @@
     "        break\n",
     "    answer = await chat.answer_question(user_query)\n",
     "    print(answer, flush=True)"
-   ],
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hi! How can I assist you today?\n"
-     ]
-    }
-   ],
-   "execution_count": 32
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 33,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:27.527276Z",
      "start_time": "2025-04-24T16:47:27.522755Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "# NBVAL_SKIP\n",
-    "chat.session_manager.messages"
-   ],
    "outputs": [
     {
      "data": {
@@ -2027,7 +2035,10 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 33
+   "source": [
+    "# NBVAL_SKIP\n",
+    "chat.session_manager.messages"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -2059,16 +2070,14 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 37,
    "metadata": {
-    "id": "On6yNuQn1ujD",
     "ExecuteTime": {
      "end_time": "2025-04-24T16:47:34.042787Z",
      "start_time": "2025-04-24T16:47:34.036106Z"
-    }
+    },
+    "id": "On6yNuQn1ujD"
    },
-   "source": [
-    "await async_index.client.flushall()"
-   ],
    "outputs": [
     {
      "data": {
@@ -2081,7 +2090,9 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 37
+   "source": [
+    "await async_index.client.flushall()"
+   ]
   }
  ],
  "metadata": {
diff --git a/python-recipes/RAG/04_advanced_redisvl.ipynb b/python-recipes/RAG/04_advanced_redisvl.ipynb
index 96141b2a..0a85530e 100644
--- a/python-recipes/RAG/04_advanced_redisvl.ipynb
+++ b/python-recipes/RAG/04_advanced_redisvl.ipynb
@@ -92,7 +92,7 @@
     }
    ],
    "source": [
-    "%pip install -q \"redisvl>=0.4.1\" pandas \"unstructured[pdf]\" sentence-transformers langchain langchain-community \"openai>=1.57.0\" tqdm"
+    "%pip install -q \"redisvl>=0.6.0\" pandas \"unstructured[pdf]\" sentence-transformers langchain langchain-community \"openai>=1.57.0\" tqdm"
    ]
   },
   {
@@ -431,10 +431,20 @@
    ],
    "source": [
     "from redisvl.utils.vectorize import HFTextVectorizer\n",
+    "from redisvl.extensions.cache.embeddings import EmbeddingsCache\n",
+    "\n",
     "\n",
-    "hf = HFTextVectorizer(\"sentence-transformers/all-MiniLM-L6-v2\")\n",
     "os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
     "\n",
+    "hf = HFTextVectorizer(\n",
+    "    model=\"sentence-transformers/all-MiniLM-L6-v2\",\n",
+    "    cache=EmbeddingsCache(\n",
+    "        name=\"embedcache\",\n",
+    "        ttl=600,\n",
+    "        redis_url=REDIS_URL,\n",
+    "    )\n",
+    ")\n",
+    "\n",
     "prop_embeddings = hf.embed_many([\n",
     "    proposition for proposition in propositions\n",
     "])\n",
diff --git a/python-recipes/vector-search/01_redisvl.ipynb b/python-recipes/vector-search/01_redisvl.ipynb
index 10a8fb87..327a101f 100644
--- a/python-recipes/vector-search/01_redisvl.ipynb
+++ b/python-recipes/vector-search/01_redisvl.ipynb
@@ -82,7 +82,7 @@
       },
       "outputs": [],
       "source": [
-        "%pip install -q \"redisvl==0.5.2\" sentence-transformers pandas nltk"
+        "%pip install -q \"redisvl>=0.6.0\" sentence-transformers pandas nltk"
       ]
     },
     {
@@ -592,11 +592,19 @@
       "outputs": [],
       "source": [
         "from redisvl.utils.vectorize import HFTextVectorizer\n",
+        "from redisvl.extensions.cache.embeddings import EmbeddingsCache\n",
         "\n",
         "os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
         "\n",
         "\n",
-        "hf = HFTextVectorizer(\"sentence-transformers/all-MiniLM-L6-v2\")"
+        "hf = HFTextVectorizer(\n",
+        "    model=\"sentence-transformers/all-MiniLM-L6-v2\",\n",
+        "    cache=EmbeddingsCache(\n",
+        "        name=\"embedcache\",\n",
+        "        ttl=600,\n",
+        "        redis_client=client,\n",
+        "    )\n",
+        ")"
       ]
     },
     {
diff --git a/python-recipes/vector-search/02_hybrid_search.ipynb b/python-recipes/vector-search/02_hybrid_search.ipynb
index 577d4e52..f39d564e 100644
--- a/python-recipes/vector-search/02_hybrid_search.ipynb
+++ b/python-recipes/vector-search/02_hybrid_search.ipynb
@@ -32,7 +32,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install sentence-transformers pandas nltk \"redisvl==0.5.1\""
+    "%pip install sentence-transformers pandas nltk \"redisvl>=0.6.0\""
    ]
   },
   {
@@ -180,9 +180,18 @@
    "outputs": [],
    "source": [
     "from redisvl.utils.vectorize import HFTextVectorizer\n",
+    "from redisvl.extensions.cache.embeddings import EmbeddingsCache\n",
+    "\n",
     "\n",
     "# load model for embedding our movie descriptions\n",
-    "model = HFTextVectorizer('sentence-transformers/all-MiniLM-L6-v2')\n",
+    "model = HFTextVectorizer(\n",
+    "    model='sentence-transformers/all-MiniLM-L6-v2',\n",
+    "    cache=EmbeddingsCache(\n",
+    "        name=\"embedcache\",\n",
+    "        ttl=600,\n",
+    "        redis_client=client,\n",
+    "    )\n",
+    ")\n",
     "\n",
     "# embed movie descriptions\n",
     "movie_data = [\n",