langchain/docs/extras/integrations/document_loaders/duckdb.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# DuckDB\n",
    "\n",
    ">[DuckDB](https://duckdb.org/) is an in-process SQL OLAP database management system.\n",
    "\n",
    "Load a `DuckDB` query with one document per row."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#!pip install duckdb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.document_loaders import DuckDBLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing example.csv\n"
     ]
    }
   ],
   "source": [
    "%%file example.csv\n",
    "Team,Payroll\n",
    "Nationals,81.34\n",
    "Reds,82.20"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "loader = DuckDBLoader(\"SELECT * FROM read_csv_auto('example.csv')\")\n",
    "\n",
    "data = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='Team: Nationals\\nPayroll: 81.34', metadata={}), Document(page_content='Team: Reds\\nPayroll: 82.2', metadata={})]\n"
     ]
    }
   ],
   "source": [
    "print(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Specifying Which Columns are Content vs Metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = DuckDBLoader(\n",
    "    \"SELECT * FROM read_csv_auto('example.csv')\",\n",
    "    page_content_columns=[\"Team\"],\n",
    "    metadata_columns=[\"Payroll\"],\n",
    ")\n",
    "\n",
    "data = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='Team: Nationals', metadata={'Payroll': 81.34}), Document(page_content='Team: Reds', metadata={'Payroll': 82.2})]\n"
     ]
    }
   ],
   "source": [
    "print(data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Adding Source to Metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = DuckDBLoader(\n",
    "    \"SELECT Team, Payroll, Team As source FROM read_csv_auto('example.csv')\",\n",
    "    metadata_columns=[\"source\"],\n",
    ")\n",
    "\n",
    "data = loader.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='Team: Nationals\\nPayroll: 81.34\\nsource: Nationals', metadata={'source': 'Nationals'}), Document(page_content='Team: Reds\\nPayroll: 82.2\\nsource: Reds', metadata={'source': 'Reds'})]\n"
     ]
    }
   ],
   "source": [
    "print(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}