langchain/docs/docs/integrations/document_loaders/singlestore.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: SingleStore\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# SingleStoreLoader\n",
    "\n",
    "The `SingleStoreLoader` allows you to load documents directly from a SingleStore database table. It is part of the `langchain-singlestore` integration package.\n",
    "\n",
    "## Overview\n",
    "\n",
    "### Integration Details\n",
    "\n",
    "| Class | Package | JS Support |\n",
    "| :--- | :--- | :---: |\n",
    "| `SingleStoreLoader` | `langchain_singlestore` | ❌ |\n",
    "\n",
    "### Features\n",
    "- Load documents lazily to handle large datasets efficiently.\n",
    "- Supports native asynchronous operations.\n",
    "- Easily configurable to work with different database schemas.\n",
    "\n",
    "## Setup\n",
    "\n",
    "To use the `SingleStoreLoader`, you need to install the `langchain-singlestore` package. Follow the installation instructions below."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Installation\n",
    "\n",
    "Install **langchain_singlestore**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install -qU langchain_singlestore"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initialization\n",
    "\n",
    "To initialize `SingleStoreLoader`, you need to provide connection parameters for the SingleStore database and specify the table and fields to load documents from.\n",
    "\n",
    "### Required Parameters:\n",
    "- **host** (`str`): Hostname, IP address, or URL for the database.\n",
    "- **table_name** (`str`): Name of the table to query. Defaults to `embeddings`.\n",
    "- **content_field** (`str`): Field containing document content. Defaults to `content`.\n",
    "- **metadata_field** (`str`): Field containing document metadata. Defaults to `metadata`.\n",
    "\n",
    "### Optional Parameters:\n",
    "- **id_field** (`str`): Field containing document IDs. Defaults to `id`.\n",
    "\n",
    "### Connection Pool Parameters:\n",
    "- **pool_size** (`int`): Number of active connections in the pool. Defaults to `5`.\n",
    "- **max_overflow** (`int`): Maximum connections beyond `pool_size`. Defaults to `10`.\n",
    "- **timeout** (`float`): Connection timeout in seconds. Defaults to `30`.\n",
    "\n",
    "### Additional Options:\n",
    "- **pure_python** (`bool`): Enables pure Python mode.\n",
    "- **local_infile** (`bool`): Allows local file uploads.\n",
    "- **charset** (`str`): Character set for string values.\n",
    "- **ssl_key**, **ssl_cert**, **ssl_ca** (`str`): Paths to SSL files.\n",
    "- **ssl_disabled** (`bool`): Disables SSL.\n",
    "- **ssl_verify_cert** (`bool`): Verifies server's certificate.\n",
    "- **ssl_verify_identity** (`bool`): Verifies server's identity.\n",
    "- **autocommit** (`bool`): Enables autocommits.\n",
    "- **results_type** (`str`): Structure of query results (e.g., `tuples`, `dicts`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_singlestore.document_loaders import SingleStoreLoader\n",
    "\n",
    "loader = SingleStoreLoader(\n",
    "    host=\"127.0.0.1:3306/db\",\n",
    "    table_name=\"documents\",\n",
    "    content_field=\"content\",\n",
    "    metadata_field=\"metadata\",\n",
    "    id_field=\"id\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "docs = loader.load()\n",
    "docs[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].metadata)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Lazy Load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "page = []\n",
    "for doc in loader.lazy_load():\n",
    "    page.append(doc)\n",
    "    if len(page) >= 10:\n",
    "        # do some paged operation, e.g.\n",
    "        # index.upsert(page)\n",
    "\n",
    "        page = []"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## API reference\n",
    "\n",
    "For detailed documentation of all SingleStore Document Loader features and configurations head to the github page: [https://github.com/singlestore-labs/langchain-singlestore/](https://github.com/singlestore-labs/langchain-singlestore/)"
   ]
  }
 ],
 "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}