From 4d456e27f9e64172a70410efc283f73a02837546 Mon Sep 17 00:00:00 2001
From: Andreas Motl <andreas.motl@crate.io>
Date: Thu, 4 Jan 2024 12:16:30 +0100
Subject: [PATCH] ML/LLM: RAG example copy edits

---
 .../cratedb_rag_customer_support.ipynb        | 1281 +++++------------
 .../llm-langchain/pyproject.toml              |    3 +
 2 files changed, 369 insertions(+), 915 deletions(-)

diff --git a/topic/machine-learning/llm-langchain/cratedb_rag_customer_support.ipynb b/topic/machine-learning/llm-langchain/cratedb_rag_customer_support.ipynb
index ca9f167f..fd1ef21e 100644
--- a/topic/machine-learning/llm-langchain/cratedb_rag_customer_support.ipynb
+++ b/topic/machine-learning/llm-langchain/cratedb_rag_customer_support.ipynb
@@ -1,924 +1,375 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "This notebook shows how to use the CrateDB vector store functionality around FLOAT_VECTOR and KNN_MATCH. You will learn how to use it to create a retrieval augmented generation (RAG) pipeline."
+   ],
+   "metadata": {
+    "id": "rUPQQ-jlMkUd"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## What is CrateDB?\n",
+    "\n",
+    "CrateDB is an open-source, distributed, and scalable SQL analytics database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is wire-compatible to PostgreSQL, based on Lucene, and inherits the shared-nothing distribution layer of Elasticsearch.\n",
+    "\n",
+    "This example uses the Python client driver for CrateDB."
+   ],
+   "metadata": {
+    "id": "Pe-5yxFDMl0S"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Getting Started\n",
+    "CrateDB supports storing vectors since version 5.5. You can leverage the fully managed service of CrateDB Cloud, or install CrateDB on your own, for example using Docker.\n",
+    "\n",
+    "```shell\n",
+    "docker run --publish 4200:4200 --publish 5432:5432 --pull=always crate:latest -Cdiscovery.type=single-node\n",
+    "```\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "Install required Python packages, and import Python modules."
+   ],
+   "metadata": {
+    "id": "rE-UtZJnMs2q"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "#!pip install -r requirements.txt"
+   ],
+   "metadata": {
     "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
+     "base_uri": "https://localhost:8080/"
     },
-    "language_info": {
-      "name": "python"
-    }
+    "id": "RJyP1GEXNHUy",
+    "outputId": "9c62258f-f6a1-4578-ced4-40f15f586e9a"
+   },
+   "execution_count": null,
+   "outputs": []
   },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "This notebook shows how to use the CrateDB vector store functionality around FLOAT_VECTOR and KNN_MATCH. You will learn how to use it to create a retrieval augmented generation (RAG) pipeline."
-      ],
-      "metadata": {
-        "id": "rUPQQ-jlMkUd"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#What is CrateDB?\n",
-        "CrateDB is an open-source, distributed, and scalable SQL analytics database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is wire-compatible to PostgreSQL, based on Lucene, and inherits the shared-nothing distribution layer of Elasticsearch.\n",
-        "\n",
-        "This example uses the Python client driver for CrateDB."
-      ],
-      "metadata": {
-        "id": "Pe-5yxFDMl0S"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#Getting Started\n",
-        "CrateDB supports storing vectors since version 5.5. You can leverage the fully managed service of CrateDB Cloud, or install CrateDB on your own, for example using Docker.\n",
-        "\n",
-        "`docker run --publish 4200:4200 --publish 5432:5432 --pull=always crate:latest -Cdiscovery.type=single-node`\n",
-        "\n",
-        "Install required Python packages, and import Python modules."
-      ],
-      "metadata": {
-        "id": "rE-UtZJnMs2q"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "pip install langchain pypdf chromadb openai sentence_transformers sqlalchemy 'crate[sqlalchemy]' tiktoken"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "RJyP1GEXNHUy",
-        "outputId": "9c62258f-f6a1-4578-ced4-40f15f586e9a"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Collecting langchain\n",
-            "  Downloading langchain-0.0.352-py3-none-any.whl (794 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m794.4/794.4 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting pypdf\n",
-            "  Downloading pypdf-3.17.3-py3-none-any.whl (277 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m277.9/277.9 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting chromadb\n",
-            "  Downloading chromadb-0.4.21-py3-none-any.whl (508 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m508.6/508.6 kB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting openai\n",
-            "  Downloading openai-1.6.0-py3-none-any.whl (225 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.4/225.4 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting sentence_transformers\n",
-            "  Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.0/86.0 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: sqlalchemy in /usr/local/lib/python3.10/dist-packages (2.0.23)\n",
-            "Collecting crate[sqlalchemy]\n",
-            "  Downloading crate-0.34.0-py2.py3-none-any.whl (117 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.5/117.5 kB\u001b[0m \u001b[31m16.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting tiktoken\n",
-            "  Downloading tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m16.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: PyYAML>=5.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (6.0.1)\n",
-            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.10/dist-packages (from langchain) (3.9.1)\n",
-            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (4.0.3)\n",
-            "Collecting dataclasses-json<0.7,>=0.5.7 (from langchain)\n",
-            "  Downloading dataclasses_json-0.6.3-py3-none-any.whl (28 kB)\n",
-            "Collecting jsonpatch<2.0,>=1.33 (from langchain)\n",
-            "  Downloading jsonpatch-1.33-py2.py3-none-any.whl (12 kB)\n",
-            "Collecting langchain-community<0.1,>=0.0.2 (from langchain)\n",
-            "  Downloading langchain_community-0.0.5-py3-none-any.whl (1.5 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m20.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting langchain-core<0.2,>=0.1 (from langchain)\n",
-            "  Downloading langchain_core-0.1.2-py3-none-any.whl (191 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m191.5/191.5 kB\u001b[0m \u001b[31m26.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting langsmith<0.1.0,>=0.0.70 (from langchain)\n",
-            "  Downloading langsmith-0.0.72-py3-none-any.whl (46 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.3/46.3 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.23.5)\n",
-            "Requirement already satisfied: pydantic<3,>=1 in /usr/local/lib/python3.10/dist-packages (from langchain) (1.10.13)\n",
-            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.10/dist-packages (from langchain) (2.31.0)\n",
-            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.10/dist-packages (from langchain) (8.2.3)\n",
-            "Collecting chroma-hnswlib==0.7.3 (from chromadb)\n",
-            "  Downloading chroma_hnswlib-0.7.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.4 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting fastapi>=0.95.2 (from chromadb)\n",
-            "  Downloading fastapi-0.105.0-py3-none-any.whl (93 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.1/93.1 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting uvicorn[standard]>=0.18.3 (from chromadb)\n",
-            "  Downloading uvicorn-0.25.0-py3-none-any.whl (60 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.3/60.3 kB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting posthog>=2.4.0 (from chromadb)\n",
-            "  Downloading posthog-3.1.0-py2.py3-none-any.whl (37 kB)\n",
-            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.5.0)\n",
-            "Collecting pulsar-client>=3.1.0 (from chromadb)\n",
-            "  Downloading pulsar_client-3.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m35.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting onnxruntime>=1.14.1 (from chromadb)\n",
-            "  Downloading onnxruntime-1.16.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.4 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.4/6.4 MB\u001b[0m \u001b[31m49.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting opentelemetry-api>=1.2.0 (from chromadb)\n",
-            "  Downloading opentelemetry_api-1.22.0-py3-none-any.whl (57 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.9/57.9 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting opentelemetry-exporter-otlp-proto-grpc>=1.2.0 (from chromadb)\n",
-            "  Downloading opentelemetry_exporter_otlp_proto_grpc-1.22.0-py3-none-any.whl (18 kB)\n",
-            "Collecting opentelemetry-instrumentation-fastapi>=0.41b0 (from chromadb)\n",
-            "  Downloading opentelemetry_instrumentation_fastapi-0.43b0-py3-none-any.whl (11 kB)\n",
-            "Collecting opentelemetry-sdk>=1.2.0 (from chromadb)\n",
-            "  Downloading opentelemetry_sdk-1.22.0-py3-none-any.whl (105 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.6/105.6 kB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: tokenizers>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.15.0)\n",
-            "Collecting pypika>=0.48.9 (from chromadb)\n",
-            "  Downloading PyPika-0.48.9.tar.gz (67 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: tqdm>=4.65.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.66.1)\n",
-            "Collecting overrides>=7.3.1 (from chromadb)\n",
-            "  Downloading overrides-7.4.0-py3-none-any.whl (17 kB)\n",
-            "Requirement already satisfied: importlib-resources in /usr/local/lib/python3.10/dist-packages (from chromadb) (6.1.1)\n",
-            "Requirement already satisfied: grpcio>=1.58.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.60.0)\n",
-            "Collecting bcrypt>=4.0.1 (from chromadb)\n",
-            "  Downloading bcrypt-4.1.2-cp39-abi3-manylinux_2_28_x86_64.whl (698 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m698.9/698.9 kB\u001b[0m \u001b[31m61.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: typer>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.9.0)\n",
-            "Collecting kubernetes>=28.1.0 (from chromadb)\n",
-            "  Downloading kubernetes-28.1.0-py2.py3-none-any.whl (1.6 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m52.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting mmh3>=4.0.1 (from chromadb)\n",
-            "  Downloading mmh3-4.0.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (72 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.6/72.6 kB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai) (3.7.1)\n",
-            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n",
-            "Collecting httpx<1,>=0.23.0 (from openai)\n",
-            "  Downloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.0)\n",
-            "Collecting typing-extensions>=4.5.0 (from chromadb)\n",
-            "  Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n",
-            "Requirement already satisfied: transformers<5.0.0,>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (4.35.2)\n",
-            "Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (2.1.0+cu121)\n",
-            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (0.16.0+cu121)\n",
-            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (1.2.2)\n",
-            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (1.11.4)\n",
-            "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (3.8.1)\n",
-            "Collecting sentencepiece (from sentence_transformers)\n",
-            "  Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m52.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: huggingface-hub>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from sentence_transformers) (0.19.4)\n",
-            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from sqlalchemy) (3.0.2)\n",
-            "Requirement already satisfied: urllib3<2.1 in /usr/local/lib/python3.10/dist-packages (from crate[sqlalchemy]) (2.0.7)\n",
-            "Collecting geojson<4,>=2.5.0 (from crate[sqlalchemy])\n",
-            "  Downloading geojson-3.1.0-py3-none-any.whl (15 kB)\n",
-            "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.6.3)\n",
-            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.1.0)\n",
-            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n",
-            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.4)\n",
-            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.4.1)\n",
-            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
-            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.6)\n",
-            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.0)\n",
-            "Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
-            "  Downloading marshmallow-3.20.1-py3-none-any.whl (49 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting typing-inspect<1,>=0.4.0 (from dataclasses-json<0.7,>=0.5.7->langchain)\n",
-            "  Downloading typing_inspect-0.9.0-py3-none-any.whl (8.8 kB)\n",
-            "Collecting starlette<0.28.0,>=0.27.0 (from fastapi>=0.95.2->chromadb)\n",
-            "  Downloading starlette-0.27.0-py3-none-any.whl (66 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.0/67.0 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2023.11.17)\n",
-            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n",
-            "  Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai)\n",
-            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (3.13.1)\n",
-            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (2023.6.0)\n",
-            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.4.0->sentence_transformers) (23.2)\n",
-            "Collecting jsonpointer>=1.9 (from jsonpatch<2.0,>=1.33->langchain)\n",
-            "  Downloading jsonpointer-2.4-py2.py3-none-any.whl (7.8 kB)\n",
-            "Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.16.0)\n",
-            "Requirement already satisfied: python-dateutil>=2.5.3 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2.8.2)\n",
-            "Requirement already satisfied: google-auth>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2.17.3)\n",
-            "Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.7.0)\n",
-            "Requirement already satisfied: requests-oauthlib in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.3.1)\n",
-            "Requirement already satisfied: oauthlib>=3.2.2 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (3.2.2)\n",
-            "Collecting urllib3<2.1 (from crate[sqlalchemy])\n",
-            "  Downloading urllib3-1.26.18-py2.py3-none-any.whl (143 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.8/143.8 kB\u001b[0m \u001b[31m20.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting coloredlogs (from onnxruntime>=1.14.1->chromadb)\n",
-            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (23.5.26)\n",
-            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (3.20.3)\n",
-            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (1.12)\n",
-            "Collecting deprecated>=1.2.6 (from opentelemetry-api>=1.2.0->chromadb)\n",
-            "  Downloading Deprecated-1.2.14-py2.py3-none-any.whl (9.6 kB)\n",
-            "Collecting importlib-metadata<7.0,>=6.0 (from opentelemetry-api>=1.2.0->chromadb)\n",
-            "  Downloading importlib_metadata-6.11.0-py3-none-any.whl (23 kB)\n",
-            "Collecting backoff<3.0.0,>=1.10.0 (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb)\n",
-            "  Downloading backoff-2.2.1-py3-none-any.whl (15 kB)\n",
-            "Requirement already satisfied: googleapis-common-protos~=1.52 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.62.0)\n",
-            "Collecting opentelemetry-exporter-otlp-proto-common==1.22.0 (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb)\n",
-            "  Downloading opentelemetry_exporter_otlp_proto_common-1.22.0-py3-none-any.whl (17 kB)\n",
-            "Collecting opentelemetry-proto==1.22.0 (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb)\n",
-            "  Downloading opentelemetry_proto-1.22.0-py3-none-any.whl (50 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.8/50.8 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting opentelemetry-instrumentation-asgi==0.43b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb)\n",
-            "  Downloading opentelemetry_instrumentation_asgi-0.43b0-py3-none-any.whl (14 kB)\n",
-            "Collecting opentelemetry-instrumentation==0.43b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb)\n",
-            "  Downloading opentelemetry_instrumentation-0.43b0-py3-none-any.whl (28 kB)\n",
-            "Collecting opentelemetry-semantic-conventions==0.43b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb)\n",
-            "  Downloading opentelemetry_semantic_conventions-0.43b0-py3-none-any.whl (36 kB)\n",
-            "Collecting opentelemetry-util-http==0.43b0 (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb)\n",
-            "  Downloading opentelemetry_util_http-0.43b0-py3-none-any.whl (6.9 kB)\n",
-            "Requirement already satisfied: setuptools>=16.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (67.7.2)\n",
-            "Requirement already satisfied: wrapt<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (1.14.1)\n",
-            "Collecting asgiref~=3.0 (from opentelemetry-instrumentation-asgi==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb)\n",
-            "  Downloading asgiref-3.7.2-py3-none-any.whl (24 kB)\n",
-            "Collecting monotonic>=1.5 (from posthog>=2.4.0->chromadb)\n",
-            "  Downloading monotonic-1.6-py2.py3-none-any.whl (8.2 kB)\n",
-            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2->langchain) (3.3.2)\n",
-            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (3.2.1)\n",
-            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (3.1.2)\n",
-            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->sentence_transformers) (2.1.0)\n",
-            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (0.4.1)\n",
-            "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/dist-packages (from typer>=0.9.0->chromadb) (8.1.7)\n",
-            "Collecting httptools>=0.5.0 (from uvicorn[standard]>=0.18.3->chromadb)\n",
-            "  Downloading httptools-0.6.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (341 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m35.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting python-dotenv>=0.13 (from uvicorn[standard]>=0.18.3->chromadb)\n",
-            "  Downloading python_dotenv-1.0.0-py3-none-any.whl (19 kB)\n",
-            "Collecting uvloop!=0.15.0,!=0.15.1,>=0.14.0 (from uvicorn[standard]>=0.18.3->chromadb)\n",
-            "  Downloading uvloop-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.4 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m61.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting watchfiles>=0.13 (from uvicorn[standard]>=0.18.3->chromadb)\n",
-            "  Downloading watchfiles-0.21.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m75.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting websockets>=10.4 (from uvicorn[standard]>=0.18.3->chromadb)\n",
-            "  Downloading websockets-12.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk->sentence_transformers) (1.3.2)\n",
-            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence_transformers) (3.2.0)\n",
-            "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision->sentence_transformers) (9.4.0)\n",
-            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (5.3.2)\n",
-            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.3.0)\n",
-            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (4.9)\n",
-            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata<7.0,>=6.0->opentelemetry-api>=1.2.0->chromadb) (3.17.0)\n",
-            "Collecting mypy-extensions>=0.3.0 (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain)\n",
-            "  Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)\n",
-            "Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime>=1.14.1->chromadb)\n",
-            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.6.0->sentence_transformers) (2.1.3)\n",
-            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxruntime>=1.14.1->chromadb) (1.3.0)\n",
-            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.5.1)\n",
-            "Building wheels for collected packages: sentence_transformers, pypika\n",
-            "  Building wheel for sentence_transformers (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for sentence_transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125923 sha256=4dba6c5f23884559a8be69462a03c893eb469e85ec77b835b30a55164465006b\n",
-            "  Stored in directory: /root/.cache/pip/wheels/62/f2/10/1e606fd5f02395388f74e7462910fe851042f97238cbbd902f\n",
-            "  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for pypika: filename=PyPika-0.48.9-py2.py3-none-any.whl size=53723 sha256=7449bcabb799137847f21b45c165fc24d48392abca2a4ef4fef4987bf92b2399\n",
-            "  Stored in directory: /root/.cache/pip/wheels/e1/26/51/d0bffb3d2fd82256676d7ad3003faea3bd6dddc9577af665f4\n",
-            "Successfully built sentence_transformers pypika\n",
-            "Installing collected packages: sentencepiece, pypika, monotonic, mmh3, websockets, uvloop, urllib3, typing-extensions, python-dotenv, pypdf, pulsar-client, overrides, opentelemetry-util-http, opentelemetry-semantic-conventions, opentelemetry-proto, mypy-extensions, marshmallow, jsonpointer, importlib-metadata, humanfriendly, httptools, h11, geojson, deprecated, chroma-hnswlib, bcrypt, backoff, watchfiles, uvicorn, typing-inspect, starlette, opentelemetry-exporter-otlp-proto-common, opentelemetry-api, jsonpatch, httpcore, crate, coloredlogs, asgiref, tiktoken, posthog, opentelemetry-sdk, opentelemetry-instrumentation, onnxruntime, langsmith, httpx, fastapi, dataclasses-json, opentelemetry-instrumentation-asgi, opentelemetry-exporter-otlp-proto-grpc, openai, langchain-core, kubernetes, opentelemetry-instrumentation-fastapi, langchain-community, sentence_transformers, langchain, chromadb\n",
-            "  Attempting uninstall: urllib3\n",
-            "    Found existing installation: urllib3 2.0.7\n",
-            "    Uninstalling urllib3-2.0.7:\n",
-            "      Successfully uninstalled urllib3-2.0.7\n",
-            "  Attempting uninstall: typing-extensions\n",
-            "    Found existing installation: typing_extensions 4.5.0\n",
-            "    Uninstalling typing_extensions-4.5.0:\n",
-            "      Successfully uninstalled typing_extensions-4.5.0\n",
-            "  Attempting uninstall: importlib-metadata\n",
-            "    Found existing installation: importlib-metadata 7.0.0\n",
-            "    Uninstalling importlib-metadata-7.0.0:\n",
-            "      Successfully uninstalled importlib-metadata-7.0.0\n",
-            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-            "lida 0.0.10 requires kaleido, which is not installed.\n",
-            "lida 0.0.10 requires python-multipart, which is not installed.\n",
-            "llmx 0.0.15a0 requires cohere, which is not installed.\n",
-            "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
-            "\u001b[0mSuccessfully installed asgiref-3.7.2 backoff-2.2.1 bcrypt-4.1.2 chroma-hnswlib-0.7.3 chromadb-0.4.21 coloredlogs-15.0.1 crate-0.34.0 dataclasses-json-0.6.3 deprecated-1.2.14 fastapi-0.105.0 geojson-3.1.0 h11-0.14.0 httpcore-1.0.2 httptools-0.6.1 httpx-0.26.0 humanfriendly-10.0 importlib-metadata-6.11.0 jsonpatch-1.33 jsonpointer-2.4 kubernetes-28.1.0 langchain-0.0.352 langchain-community-0.0.5 langchain-core-0.1.2 langsmith-0.0.72 marshmallow-3.20.1 mmh3-4.0.1 monotonic-1.6 mypy-extensions-1.0.0 onnxruntime-1.16.3 openai-1.6.0 opentelemetry-api-1.22.0 opentelemetry-exporter-otlp-proto-common-1.22.0 opentelemetry-exporter-otlp-proto-grpc-1.22.0 opentelemetry-instrumentation-0.43b0 opentelemetry-instrumentation-asgi-0.43b0 opentelemetry-instrumentation-fastapi-0.43b0 opentelemetry-proto-1.22.0 opentelemetry-sdk-1.22.0 opentelemetry-semantic-conventions-0.43b0 opentelemetry-util-http-0.43b0 overrides-7.4.0 posthog-3.1.0 pulsar-client-3.3.0 pypdf-3.17.3 pypika-0.48.9 python-dotenv-1.0.0 sentence_transformers-2.2.2 sentencepiece-0.1.99 starlette-0.27.0 tiktoken-0.5.2 typing-extensions-4.9.0 typing-inspect-0.9.0 urllib3-1.26.18 uvicorn-0.25.0 uvloop-0.19.0 watchfiles-0.21.0 websockets-12.0\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "from langchain.document_loaders.csv_loader import CSVLoader\n",
-        "from langchain.vectorstores import Chroma\n",
-        "from langchain.chat_models import ChatOpenAI\n",
-        "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-        "from langchain.chains import RetrievalQA, ConversationalRetrievalChain\n",
-        "from langchain.llms import OpenAI\n",
-        "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-        "import pandas as pd\n",
-        "import sqlalchemy as sa\n",
-        "from sqlalchemy import create_engine\n",
-        "from sqlalchemy import text\n",
-        "import crate\n",
-        "import openai\n",
-        "import os\n",
-        "import getpass"
-      ],
-      "metadata": {
-        "id": "VUNjBDrXNNoG"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Create embeddings from dataset\n"
-      ],
-      "metadata": {
-        "id": "Cd2BLNlReU01"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Open AI API Key:\")\n",
-        "openai.api_key = os.environ[\"OPENAI_API_KEY\"]"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "LsRfzgmeNjJc",
-        "outputId": "6fdff9a4-8007-4773-818d-2cf2fcce28b9"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Open AI API Key:··········\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "loader = CSVLoader(file_path=\"./sample_data/twitter_support_microsoft.csv\", encoding=\"utf-8\", csv_args={'delimiter': ','})\n",
-        "data = loader.load()\n",
-        "pages_text = [doc.page_content for doc in data]\n",
-        "print(pages_text[0])"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "6Po5rpReNuhn",
-        "outputId": "84e363de-84be-4c96-d3b7-8c4561fd03db"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "tweet_id: 2301\n",
-            "author_id: 116231\n",
-            "inbound: True\n",
-            "created_at: Tue Oct 31 20:22:23 +0000 2017\n",
-            "text: @MicrosoftHelps Please get back to me immediately this is of the upmost importance\n",
-            "response_tweet_id: 2299\n",
-            "in_response_to_tweet_id: 2306\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "embeddings = OpenAIEmbeddings(deployment='my-embedding-model', chunk_size=1)\n",
-        "pages_embeddings = embeddings.embed_documents(pages_text)"
-      ],
-      "metadata": {
-        "id": "nWl5RSPjPgGv"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#Write data to CrateDB\n",
-        "\n",
-        "The next step creates a dataframe that contains the text of the documents and their embeddings. The embeddings will be stored in CrateDB using FLOAT_VECTOR type."
-      ],
-      "metadata": {
-        "id": "QhOU-4aXQkTX"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "df = pd.DataFrame(list(zip(pages_text, pages_embeddings)),columns =['text', 'embedding'])"
-      ],
-      "metadata": {
-        "id": "r_I0dlUNQgKU"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "host = getpass.getpass(\"Host:\")\n",
-        "password = getpass.getpass(\"password:\")\n",
-        "dbname=\"crate://admin:{0}@{1}:4200?ssl=true\".format(password,host)\n",
-        "create_table = text(\"CREATE TABLE text_data (text TEXT, embedding FLOAT_VECTOR(1536))\")\n",
-        "engine = create_engine(dbname, echo=False)\n",
-        "\n",
-        "with engine.connect() as con:\n",
-        "     con.execute(create_table)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "vzsx_YdaV2et",
-        "outputId": "221fe177-212e-4e74-9a26-e4d48d6eae3d"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Host:··········\n",
-            "password:··········\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "The text and embeddings are written to CrateDB database using CrateDB vector storage support:"
-      ],
-      "metadata": {
-        "id": "r5MDKdW5Y_Um"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "df.to_sql(name='text_data', con=engine, if_exists='append', index=False)\n",
-        "df.head(5)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 206
-        },
-        "id": "8pzKlr3uV3Ql",
-        "outputId": "93566fa0-7ef4-44fd-e29e-23e7b29c645f"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "                                                text  \\\n",
-              "0  tweet_id: 2301\\nauthor_id: 116231\\ninbound: Tr...   \n",
-              "1  tweet_id: 11879\\nauthor_id: MicrosoftHelps\\nin...   \n",
-              "2  tweet_id: 11881\\nauthor_id: MicrosoftHelps\\nin...   \n",
-              "3  tweet_id: 11890\\nauthor_id: 118332\\ninbound: T...   \n",
-              "4  tweet_id: 11912\\nauthor_id: MicrosoftHelps\\nin...   \n",
-              "\n",
-              "                                           embedding  \n",
-              "0  [-0.037185399571588756, -0.01364005917049614, ...  \n",
-              "1  [-0.015454164058839018, 0.0032340502581370413,...  \n",
-              "2  [-0.005936504790842904, 0.01942733669848253, 0...  \n",
-              "3  [-0.011779013479771422, 0.005725434705161641, ...  \n",
-              "4  [-0.022950152341946847, 0.004767860370434739, ...  "
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-de059b13-ae53-4653-942a-812756ee061e\" class=\"colab-df-container\">\n",
-              "    <div>\n",
-              "<style scoped>\n",
-              "    .dataframe tbody tr th:only-of-type {\n",
-              "        vertical-align: middle;\n",
-              "    }\n",
-              "\n",
-              "    .dataframe tbody tr th {\n",
-              "        vertical-align: top;\n",
-              "    }\n",
-              "\n",
-              "    .dataframe thead th {\n",
-              "        text-align: right;\n",
-              "    }\n",
-              "</style>\n",
-              "<table border=\"1\" class=\"dataframe\">\n",
-              "  <thead>\n",
-              "    <tr style=\"text-align: right;\">\n",
-              "      <th></th>\n",
-              "      <th>text</th>\n",
-              "      <th>embedding</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>tweet_id: 2301\\nauthor_id: 116231\\ninbound: Tr...</td>\n",
-              "      <td>[-0.037185399571588756, -0.01364005917049614, ...</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>tweet_id: 11879\\nauthor_id: MicrosoftHelps\\nin...</td>\n",
-              "      <td>[-0.015454164058839018, 0.0032340502581370413,...</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>tweet_id: 11881\\nauthor_id: MicrosoftHelps\\nin...</td>\n",
-              "      <td>[-0.005936504790842904, 0.01942733669848253, 0...</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>tweet_id: 11890\\nauthor_id: 118332\\ninbound: T...</td>\n",
-              "      <td>[-0.011779013479771422, 0.005725434705161641, ...</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>tweet_id: 11912\\nauthor_id: MicrosoftHelps\\nin...</td>\n",
-              "      <td>[-0.022950152341946847, 0.004767860370434739, ...</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "</div>\n",
-              "    <div class=\"colab-df-buttons\">\n",
-              "\n",
-              "  <div class=\"colab-df-container\">\n",
-              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-de059b13-ae53-4653-942a-812756ee061e')\"\n",
-              "            title=\"Convert this dataframe to an interactive table.\"\n",
-              "            style=\"display:none;\">\n",
-              "\n",
-              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
-              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
-              "  </svg>\n",
-              "    </button>\n",
-              "\n",
-              "  <style>\n",
-              "    .colab-df-container {\n",
-              "      display:flex;\n",
-              "      gap: 12px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert {\n",
-              "      background-color: #E8F0FE;\n",
-              "      border: none;\n",
-              "      border-radius: 50%;\n",
-              "      cursor: pointer;\n",
-              "      display: none;\n",
-              "      fill: #1967D2;\n",
-              "      height: 32px;\n",
-              "      padding: 0 0 0 0;\n",
-              "      width: 32px;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-convert:hover {\n",
-              "      background-color: #E2EBFA;\n",
-              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "      fill: #174EA6;\n",
-              "    }\n",
-              "\n",
-              "    .colab-df-buttons div {\n",
-              "      margin-bottom: 4px;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert {\n",
-              "      background-color: #3B4455;\n",
-              "      fill: #D2E3FC;\n",
-              "    }\n",
-              "\n",
-              "    [theme=dark] .colab-df-convert:hover {\n",
-              "      background-color: #434B5C;\n",
-              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
-              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
-              "      fill: #FFFFFF;\n",
-              "    }\n",
-              "  </style>\n",
-              "\n",
-              "    <script>\n",
-              "      const buttonEl =\n",
-              "        document.querySelector('#df-de059b13-ae53-4653-942a-812756ee061e button.colab-df-convert');\n",
-              "      buttonEl.style.display =\n",
-              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "      async function convertToInteractive(key) {\n",
-              "        const element = document.querySelector('#df-de059b13-ae53-4653-942a-812756ee061e');\n",
-              "        const dataTable =\n",
-              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
-              "                                                    [key], {});\n",
-              "        if (!dataTable) return;\n",
-              "\n",
-              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
-              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
-              "          + ' to learn more about interactive tables.';\n",
-              "        element.innerHTML = '';\n",
-              "        dataTable['output_type'] = 'display_data';\n",
-              "        await google.colab.output.renderOutput(dataTable, element);\n",
-              "        const docLink = document.createElement('div');\n",
-              "        docLink.innerHTML = docLinkHtml;\n",
-              "        element.appendChild(docLink);\n",
-              "      }\n",
-              "    </script>\n",
-              "  </div>\n",
-              "\n",
-              "\n",
-              "<div id=\"df-38ca133a-a775-425a-a744-b7dec73cc024\">\n",
-              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-38ca133a-a775-425a-a744-b7dec73cc024')\"\n",
-              "            title=\"Suggest charts\"\n",
-              "            style=\"display:none;\">\n",
-              "\n",
-              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
-              "     width=\"24px\">\n",
-              "    <g>\n",
-              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
-              "    </g>\n",
-              "</svg>\n",
-              "  </button>\n",
-              "\n",
-              "<style>\n",
-              "  .colab-df-quickchart {\n",
-              "      --bg-color: #E8F0FE;\n",
-              "      --fill-color: #1967D2;\n",
-              "      --hover-bg-color: #E2EBFA;\n",
-              "      --hover-fill-color: #174EA6;\n",
-              "      --disabled-fill-color: #AAA;\n",
-              "      --disabled-bg-color: #DDD;\n",
-              "  }\n",
-              "\n",
-              "  [theme=dark] .colab-df-quickchart {\n",
-              "      --bg-color: #3B4455;\n",
-              "      --fill-color: #D2E3FC;\n",
-              "      --hover-bg-color: #434B5C;\n",
-              "      --hover-fill-color: #FFFFFF;\n",
-              "      --disabled-bg-color: #3B4455;\n",
-              "      --disabled-fill-color: #666;\n",
-              "  }\n",
-              "\n",
-              "  .colab-df-quickchart {\n",
-              "    background-color: var(--bg-color);\n",
-              "    border: none;\n",
-              "    border-radius: 50%;\n",
-              "    cursor: pointer;\n",
-              "    display: none;\n",
-              "    fill: var(--fill-color);\n",
-              "    height: 32px;\n",
-              "    padding: 0;\n",
-              "    width: 32px;\n",
-              "  }\n",
-              "\n",
-              "  .colab-df-quickchart:hover {\n",
-              "    background-color: var(--hover-bg-color);\n",
-              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
-              "    fill: var(--button-hover-fill-color);\n",
-              "  }\n",
-              "\n",
-              "  .colab-df-quickchart-complete:disabled,\n",
-              "  .colab-df-quickchart-complete:disabled:hover {\n",
-              "    background-color: var(--disabled-bg-color);\n",
-              "    fill: var(--disabled-fill-color);\n",
-              "    box-shadow: none;\n",
-              "  }\n",
-              "\n",
-              "  .colab-df-spinner {\n",
-              "    border: 2px solid var(--fill-color);\n",
-              "    border-color: transparent;\n",
-              "    border-bottom-color: var(--fill-color);\n",
-              "    animation:\n",
-              "      spin 1s steps(1) infinite;\n",
-              "  }\n",
-              "\n",
-              "  @keyframes spin {\n",
-              "    0% {\n",
-              "      border-color: transparent;\n",
-              "      border-bottom-color: var(--fill-color);\n",
-              "      border-left-color: var(--fill-color);\n",
-              "    }\n",
-              "    20% {\n",
-              "      border-color: transparent;\n",
-              "      border-left-color: var(--fill-color);\n",
-              "      border-top-color: var(--fill-color);\n",
-              "    }\n",
-              "    30% {\n",
-              "      border-color: transparent;\n",
-              "      border-left-color: var(--fill-color);\n",
-              "      border-top-color: var(--fill-color);\n",
-              "      border-right-color: var(--fill-color);\n",
-              "    }\n",
-              "    40% {\n",
-              "      border-color: transparent;\n",
-              "      border-right-color: var(--fill-color);\n",
-              "      border-top-color: var(--fill-color);\n",
-              "    }\n",
-              "    60% {\n",
-              "      border-color: transparent;\n",
-              "      border-right-color: var(--fill-color);\n",
-              "    }\n",
-              "    80% {\n",
-              "      border-color: transparent;\n",
-              "      border-right-color: var(--fill-color);\n",
-              "      border-bottom-color: var(--fill-color);\n",
-              "    }\n",
-              "    90% {\n",
-              "      border-color: transparent;\n",
-              "      border-bottom-color: var(--fill-color);\n",
-              "    }\n",
-              "  }\n",
-              "</style>\n",
-              "\n",
-              "  <script>\n",
-              "    async function quickchart(key) {\n",
-              "      const quickchartButtonEl =\n",
-              "        document.querySelector('#' + key + ' button');\n",
-              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
-              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
-              "      try {\n",
-              "        const charts = await google.colab.kernel.invokeFunction(\n",
-              "            'suggestCharts', [key], {});\n",
-              "      } catch (error) {\n",
-              "        console.error('Error during call to suggestCharts:', error);\n",
-              "      }\n",
-              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
-              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
-              "    }\n",
-              "    (() => {\n",
-              "      let quickchartButtonEl =\n",
-              "        document.querySelector('#df-38ca133a-a775-425a-a744-b7dec73cc024 button');\n",
-              "      quickchartButtonEl.style.display =\n",
-              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "    })();\n",
-              "  </script>\n",
-              "</div>\n",
-              "    </div>\n",
-              "  </div>\n"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 10
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#Ask question\n",
-        "Let's define our question and create an embedding using OpenAI embedding model:"
-      ],
-      "metadata": {
-        "id": "GkAPZ55RZQ09"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "my_question = \"How to update shipping address on existing order in Microsoft Store?\"\n",
-        "query_embedding = embeddings.embed_query(my_question)"
-      ],
-      "metadata": {
-        "id": "InhR73isZJCB"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#Find relevant context using similarity search\n",
-        "\n",
-        "The `knn_match (search_vector, query_vector, k) `function in CrateDB performs an approximate k-nearest neighbors (KNN) search within a dataset. KNN search involves finding the k data points that are most similar to a given query data point. We find the most similar vectors to our query vector using knn search capability in CrateDB:"
-      ],
-      "metadata": {
-        "id": "6XnNZHI6ajaS"
-      }
+  {
+   "cell_type": "code",
+   "source": [
+    "import os\n",
+    "\n",
+    "import openai\n",
+    "import pandas as pd\n",
+    "import sqlalchemy as sa\n",
+    "\n",
+    "from langchain.document_loaders.csv_loader import CSVLoader\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from pueblo.util.environ import getenvpass"
+   ],
+   "metadata": {
+    "id": "VUNjBDrXNNoG"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Configure database settings"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "CONNECTION_STRING = os.environ.get(\n",
+    "    \"CRATEDB_CONNECTION_STRING\",\n",
+    "    \"crate://crate@localhost/\",\n",
+    ")\n",
+    "\n",
+    "# For CrateDB Cloud, use:\n",
+    "# CONNECTION_STRING = os.environ.get(\n",
+    "#     \"CRATEDB_CONNECTION_STRING\",\n",
+    "#     \"crate://username:password@hostname/?ssl=true\",\n",
+    "# )"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Configure OpenAI"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "getenvpass(\"OPENAI_API_KEY\", prompt=\"OpenAI API key:\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Patches\n",
+    "Those can be removed again after they have been upstreamed."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "# TODO: Bring this into the `crate-python` driver.\n",
+    "from cratedb_toolkit.sqlalchemy.patch import patch_inspector\n",
+    "patch_inspector()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Create embeddings from dataset"
+   ],
+   "metadata": {
+    "id": "Cd2BLNlReU01"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "loader = CSVLoader(file_path=\"./sample_data/twitter_support_microsoft.csv\", encoding=\"utf-8\", csv_args={'delimiter': ','})\n",
+    "data = loader.load()\n",
+    "pages_text = [doc.page_content for doc in data]\n",
+    "print(pages_text[0])"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
-    {
-      "cell_type": "code",
-      "source": [
-        "knn_query = text(\"\"\"SELECT text FROM text_data\n",
-        "            WHERE knn_match(embedding, {0}, 2)\"\"\".format(query_embedding))\n",
-        "documents=[]\n",
-        "\n",
-        "with engine.connect() as con:\n",
-        "    results = con.execute(knn_query)\n",
-        "    for record in results:\n",
-        "        documents.append(record[0])\n",
-        "\n",
-        "print(documents)\n"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "VjLeMkwMagOf",
-        "outputId": "2c92d6fc-22aa-4914-b58c-bbd3928108e1"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "['tweet_id: 12858\\nauthor_id: 118603\\ninbound: True\\ncreated_at: Mon Oct 30 18:33:00 +0000 2017\\ntext: @MicrosoftHelps The store never gave me an error message.  It\\'s STILL sitting there \"thinking/working\" after 2 hours.\\nresponse_tweet_id: 12857,12859\\nin_response_to_tweet_id: 12860', 'tweet_id: 12881\\nauthor_id: 118606\\ninbound: True\\ncreated_at: Wed Nov 01 12:18:10 +0000 2017\\ntext: @MicrosoftHelps okay. let me contact them\\nresponse_tweet_id: \\nin_response_to_tweet_id: 12879', \"tweet_id: 12868\\nauthor_id: MicrosoftHelps\\ninbound: False\\ncreated_at: Tue Oct 31 13:23:00 +0000 2017\\ntext: @118604 1/2 We don't have direct email. You can post your query via Community Forum for assistance: https://t.co/jsa5yeYZ1T.\\nresponse_tweet_id: \\nin_response_to_tweet_id: 12867\", \"tweet_id: 11883\\nauthor_id: MicrosoftHelps\\ninbound: False\\ncreated_at: Thu Oct 26 16:30:01 +0000 2017\\ntext: @118331 Hi. That's strange. Let's make sure that all your driver was updated. Here's how: https://t.co/paTrSXK1Xn. Update us.\\nresponse_tweet_id: 11882\\nin_response_to_tweet_id: 11884\", 'tweet_id: 9692\\nauthor_id: MicrosoftHelps\\ninbound: False\\ncreated_at: Fri Oct 20 23:34:51 +0000 2017\\ntext: @117762 Hellos James. You will need to cancel your current order and place a new one so you can include your updated details.\\nresponse_tweet_id: \\nin_response_to_tweet_id: 9691', \"tweet_id: 9685\\nauthor_id: 117762\\ninbound: True\\ncreated_at: Thu Oct 26 17:54:08 +0000 2017\\ntext: @MicrosoftHelps Seems to be good.  Support responded by email saying that the order status won't change online, but the warehouse will ship to the new addr.\\nresponse_tweet_id: 9684,9686\\nin_response_to_tweet_id: 9687\", 'tweet_id: 11894\\nauthor_id: MicrosoftHelps\\ninbound: False\\ncreated_at: Fri Oct 27 19:42:25 +0000 2017\\ntext: @118333 2/2 Store app or via Microsoft Store online?\\nresponse_tweet_id: 11892\\nin_response_to_tweet_id: 11895', \"tweet_id: 9688\\nauthor_id: 117762\\ninbound: True\\ncreated_at: Wed Oct 25 01:36:41 +0000 2017\\ntext: @MicrosoftHelps I was helped when I called support again. However, the address hasn't changed in the order status yet.\\nresponse_tweet_id: 9689,9687\\nin_response_to_tweet_id: 9690\"]\n"
-          ]
-        }
-      ]
+    "id": "6Po5rpReNuhn",
+    "outputId": "84e363de-84be-4c96-d3b7-8c4561fd03db"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "embeddings = OpenAIEmbeddings(deployment='my-embedding-model', chunk_size=1)\n",
+    "pages_embeddings = embeddings.embed_documents(pages_text)"
+   ],
+   "metadata": {
+    "id": "nWl5RSPjPgGv"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Write data to CrateDB\n",
+    "\n",
+    "The next step creates a dataframe that contains the text of the documents and their embeddings. The embeddings will be stored in CrateDB using FLOAT_VECTOR type."
+   ],
+   "metadata": {
+    "id": "QhOU-4aXQkTX"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "df = pd.DataFrame(list(zip(pages_text, pages_embeddings)), columns=['text', 'embedding'])"
+   ],
+   "metadata": {
+    "id": "r_I0dlUNQgKU"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "engine = sa.create_engine(CONNECTION_STRING, echo=False)\n",
+    "\n",
+    "create_table = sa.text(\"CREATE TABLE IF NOT EXISTS text_data (text TEXT, embedding FLOAT_VECTOR(1536))\")\n",
+    "with engine.connect() as con:\n",
+    "     con.execute(create_table)"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#Augment system prompt and query LLM"
-      ],
-      "metadata": {
-        "id": "-j94BF-3e1Je"
-      }
+    "id": "vzsx_YdaV2et",
+    "outputId": "221fe177-212e-4e74-9a26-e4d48d6eae3d"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "The text and embeddings are written to CrateDB database using CrateDB vector storage support:"
+   ],
+   "metadata": {
+    "id": "r5MDKdW5Y_Um"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "df.to_sql(name='text_data', con=engine, if_exists='append', index=False)\n",
+    "df.head(5)"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
     },
-    {
-      "cell_type": "code",
-      "source": [
-        "context = '---\\n'.join(documents)\n",
-        "\n",
-        "system_prompt = f\"\"\"\n",
-        "You are customer support expert and get questions about Microsoft products and services.\n",
-        "To answer question use the information from the context. Remove new line characters from the answer.\n",
-        "If you don't find the relevant information there, say \"I don't know\".\n",
-        "\n",
-        "Context:\n",
-        "{context}\"\"\"\n",
-        "\n",
-        "chat_completion = openai.chat.completions.create(model=\"gpt-4\",\n",
-        "                                               messages=[{\"role\": \"system\", \"content\": system_prompt},\n",
-        "                                                         {\"role\": \"user\", \"content\": my_question}])\n"
-      ],
-      "metadata": {
-        "id": "IEuq9r2EaqUz"
-      },
-      "execution_count": null,
-      "outputs": []
+    "id": "8pzKlr3uV3Ql",
+    "outputId": "93566fa0-7ef4-44fd-e29e-23e7b29c645f"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Ask question\n",
+    "Let's define our question and create an embedding using OpenAI embedding model:"
+   ],
+   "metadata": {
+    "id": "GkAPZ55RZQ09"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "my_question = \"How to update shipping address on existing order in Microsoft Store?\"\n",
+    "query_embedding = embeddings.embed_query(my_question)"
+   ],
+   "metadata": {
+    "id": "InhR73isZJCB"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Find relevant context using similarity search\n",
+    "\n",
+    "The `knn_match (search_vector, query_vector, k) `function in CrateDB performs an approximate k-nearest neighbors (KNN) search within a dataset. KNN search involves finding the k data points that are most similar to a given query data point. We find the most similar vectors to our query vector using knn search capability in CrateDB:"
+   ],
+   "metadata": {
+    "id": "6XnNZHI6ajaS"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "knn_query = sa.text(\"\"\"SELECT text FROM text_data\n",
+    "            WHERE knn_match(embedding, {0}, 2)\"\"\".format(query_embedding))\n",
+    "documents=[]\n",
+    "\n",
+    "with engine.connect() as con:\n",
+    "    results = con.execute(knn_query)\n",
+    "    for record in results:\n",
+    "        documents.append(record[0])\n",
+    "\n",
+    "print(documents)\n"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
-    {
-      "cell_type": "code",
-      "source": [
-        "chat_completion.choices[0].message.content"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 53
-        },
-        "id": "aQnmpCIZa13L",
-        "outputId": "a10c71a7-a6c7-4f83-c069-df49703d4654"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "'To update the shipping address on an existing order in the Microsoft Store, you will need to cancel your current order and place a new one so you can include your updated details.'"
-            ],
-            "application/vnd.google.colaboratory.intrinsic+json": {
-              "type": "string"
-            }
-          },
-          "metadata": {},
-          "execution_count": 14
-        }
-      ]
+    "id": "VjLeMkwMagOf",
+    "outputId": "2c92d6fc-22aa-4914-b58c-bbd3928108e1"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Augment system prompt and query LLM"
+   ],
+   "metadata": {
+    "id": "-j94BF-3e1Je"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "context = '---\\n'.join(documents)\n",
+    "\n",
+    "system_prompt = f\"\"\"\n",
+    "You are customer support expert and get questions about Microsoft products and services.\n",
+    "To answer question use the information from the context. Remove new line characters from the answer.\n",
+    "If you don't find the relevant information there, say \"I don't know\".\n",
+    "\n",
+    "Context:\n",
+    "{context}\"\"\"\n",
+    "\n",
+    "chat_completion = openai.chat.completions.create(model=\"gpt-4\",\n",
+    "                                               messages=[{\"role\": \"system\", \"content\": system_prompt},\n",
+    "                                                         {\"role\": \"user\", \"content\": my_question}])\n"
+   ],
+   "metadata": {
+    "id": "IEuq9r2EaqUz"
+   },
+   "execution_count": null,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "chat_completion.choices[0].message.content"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 53
     },
-    {
-      "cell_type": "code",
-      "source": [],
-      "metadata": {
-        "id": "iTGxziOBvK25"
-      },
-      "execution_count": null,
-      "outputs": []
-    }
-  ]
-}
\ No newline at end of file
+    "id": "aQnmpCIZa13L",
+    "outputId": "a10c71a7-a6c7-4f83-c069-df49703d4654"
+   },
+   "execution_count": null,
+   "outputs": []
+  }
+ ]
+}
diff --git a/topic/machine-learning/llm-langchain/pyproject.toml b/topic/machine-learning/llm-langchain/pyproject.toml
index ac48fed6..5f2bc638 100644
--- a/topic/machine-learning/llm-langchain/pyproject.toml
+++ b/topic/machine-learning/llm-langchain/pyproject.toml
@@ -36,6 +36,9 @@ nb_diff_ignore = [
     "/cells/13/outputs",
     "/cells/15/outputs",
     "/cells/17/outputs",
+
+    # cratedb_rag_customer_support.ipynb
+    "/cells/*/outputs",
 ]
 
 [tool.coverage.run]