langchain/docs/extras/integrations/retrievers/tf_idf.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ab66dd43",
   "metadata": {},
   "source": [
    "# TF-IDF\n",
    "\n",
    ">[TF-IDF](https://scikit-learn.org/stable/modules/feature_extraction.html#tfidf-term-weighting) means term-frequency times inverse document-frequency.\n",
    "\n",
    "This notebook goes over how to use a retriever that under the hood uses [TF-IDF](https://en.wikipedia.org/wiki/Tf%E2%80%93idf) using `scikit-learn` package.\n",
    "\n",
    "For more information on the details of TF-IDF see [this blog post](https://medium.com/data-science-bootcamp/tf-idf-basics-of-information-retrieval-48de122b2a4c)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a801b57c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "393ac030",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.retrievers import TFIDFRetriever"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aaf80e7f",
   "metadata": {},
   "source": [
    "## Create New Retriever with Texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "98b1c017",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "retriever = TFIDFRetriever.from_texts([\"foo\", \"bar\", \"world\", \"hello\", \"foo bar\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c016b266",
   "metadata": {},
   "source": [
    "## Create a New Retriever with Documents\n",
    "\n",
    "You can now create a new retriever with the documents you created."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "53af4f00",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.schema import Document\n",
    "\n",
    "retriever = TFIDFRetriever.from_documents(\n",
    "    [\n",
    "        Document(page_content=\"foo\"),\n",
    "        Document(page_content=\"bar\"),\n",
    "        Document(page_content=\"world\"),\n",
    "        Document(page_content=\"hello\"),\n",
    "        Document(page_content=\"foo bar\"),\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "08437fa2",
   "metadata": {},
   "source": [
    "## Use Retriever\n",
    "\n",
    "We can now use the retriever!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c0455218",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "result = retriever.get_relevant_documents(\"foo\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7dfa5c29",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='foo', metadata={}),\n",
       " Document(page_content='foo bar', metadata={}),\n",
       " Document(page_content='hello', metadata={}),\n",
       " Document(page_content='world', metadata={})]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "363f3c04",
   "metadata": {},
   "source": [
    "## Save and load\n",
    "\n",
    "You can easily save and load this retriever, making it handy for local development!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "10c90d03",
   "metadata": {},
   "outputs": [],
   "source": [
    "retriever.save_local(\"testing.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fb3b153c",
   "metadata": {},
   "outputs": [],
   "source": [
    "retriever_copy = TFIDFRetriever.load_local(\"testing.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c03ff3c7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='foo', metadata={}),\n",
       " Document(page_content='foo bar', metadata={}),\n",
       " Document(page_content='hello', metadata={}),\n",
       " Document(page_content='world', metadata={})]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "retriever_copy.get_relevant_documents(\"foo\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2d7c5728",
   "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": "3.10.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}