diff --git a/examples/sqlite_example.ipynb b/examples/sqlite_example.ipynb
new file mode 100644
index 0000000..e7219da
--- /dev/null
+++ b/examples/sqlite_example.ipynb
@@ -0,0 +1,316 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Using Defog.ai SQL-Eval with SQLite database"
+      ],
+      "metadata": {
+        "id": "HCvehWlRJHeB"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This notebook runs through the process of using the sql-eval repository with Sqlite database. It uses sample data from https://github.com/defog-ai/defog-data"
+      ],
+      "metadata": {
+        "id": "OCfYLRx6Je0u"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "5-mrSRmDM332"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Clone repo and install requirements"
+      ],
+      "metadata": {
+        "id": "cY0PrwrcM7hj"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!git clone https://github.com/defog-ai/defog-data.git\n",
+        "!pip install -r /content/defog-data/requirements.txt"
+      ],
+      "metadata": {
+        "id": "Q_dRdIPcC5zU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!git clone https://github.com/defog-ai/sql-eval.git\n",
+        "!mv sql-eval/* .\n",
+        "!pip install -r requirements.txt"
+      ],
+      "metadata": {
+        "id": "yBXaZkMHOjw3"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!mv defog-data/defog_data ."
+      ],
+      "metadata": {
+        "id": "_rfF5_i_C51r"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "import pandas\n",
+        "\n",
+        "os.environ[\"OPENAI_API_KEY\"] = \"OPEN-API-KEY\""
+      ],
+      "metadata": {
+        "id": "d3T5YTF0C54V"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# NOTE"
+      ],
+      "metadata": {
+        "id": "bVnZczKRT5gs"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "For the sake of this example, we will be using only 3 databases - academic, advising and atis. Hence modify `db_names` and `test_queries` variable in ***defog-data/translate_ddl_dialect.py*** to have only these 3 tables"
+      ],
+      "metadata": {
+        "id": "N3vc2K0ENEcv"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# modify translate_ddl_dialect.py to have only first 3 databases\n",
+        "# db_names = [\n",
+        "#     \"academic\",\n",
+        "#     \"advising\",\n",
+        "#     \"atis\",\n",
+        "# ]\n",
+        "# test_queries = [\n",
+        "#     (\"academic\", \"writes\"),\n",
+        "#     (\"advising\", \"student_record\"),\n",
+        "#     (\"atis\", \"time_zone\"),\n",
+        "# ]"
+      ],
+      "metadata": {
+        "id": "pF0CdzUN92NS"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Create and populate SQLite databases"
+      ],
+      "metadata": {
+        "id": "RD8iC9uOOWe-"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!python /content/defog-data/translate_ddl_dialect.py --dialects sqlite\n"
+      ],
+      "metadata": {
+        "id": "ozUvxXbCvmb5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "NOTE : In utils/creds.py change `\"path_to_folder\": f\"/content/sqlite_dbs/\"` for sqlite (or whatever the path of sqlite database is)\n"
+      ],
+      "metadata": {
+        "id": "RaiV1RQtO_HL"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "U1PJ0keiRhMR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Modify questions set to have only question for selected db"
+      ],
+      "metadata": {
+        "id": "ANA1cXAZRiAC"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "questions_gen_sqlite = pd.read_csv(\"data/questions_gen_sqlite.csv\")"
+      ],
+      "metadata": {
+        "id": "fMOFkE1EAMDf"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "questions_gen_sqlite_trimmed = questions_gen_sqlite[questions_gen_sqlite['db_name'].isin([\"academic\",\"advising\",\"atis\"])]"
+      ],
+      "metadata": {
+        "id": "niN4kV6zAY4P"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "questions_gen_sqlite_trimmed.to_csv(\"questions_gen_sqlite_trimmed.csv\", index=False)"
+      ],
+      "metadata": {
+        "id": "j8AARBihA6I6"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "Pb-k0jrxSPFa"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Run evaluation code"
+      ],
+      "metadata": {
+        "id": "iM0gyDNeSPYG"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!python main.py \\\n",
+        "  -db sqlite \\\n",
+        "  -q questions_gen_sqlite_trimmed.csv \\\n",
+        "  -o results/openai_classic.csv \\\n",
+        "  -g oa \\\n",
+        "  -f prompts/prompt_openai.json \\\n",
+        "  -m gpt-3.5-turbo\n"
+      ],
+      "metadata": {
+        "id": "7HHm3oirxRtP"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "qBipGtrE2bRn"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "The evaluation results will be available in csv file within results folder"
+      ],
+      "metadata": {
+        "id": "fTUCqso_SmFF"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Check data in SQLite databases"
+      ],
+      "metadata": {
+        "id": "z1_f_ooPSeoL"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import sqlite3\n",
+        "conn = sqlite3.connect('sqlite_dbs/academic.db')\n",
+        "c = conn.cursor()\n",
+        "\n",
+        "sql_query=\"\"\"\n",
+        "SELECT publication.year, AVG(publication.citation_num) AS average_citations FROM publication GROUP BY publication.year ORDER BY publication.year NULLS LAST;\n",
+        "\n",
+        "\"\"\"\n",
+        "\n",
+        "c.execute(sql_query)\n",
+        "print(c.fetchall())"
+      ],
+      "metadata": {
+        "id": "W3XNBatD5Lk7"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "_mjX0K4O7cC6"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}
\ No newline at end of file