Harrison/tfidf retriever (#2440)

docs/modules/indexes/retrievers/examples/elastic_search_bm25.ipynb

@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "393ac030",
    "metadata": {},
    "outputs": [],
@@ -32,13 +32,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 2,
    "id": "bcb3c8c2",
    "metadata": {},
    "outputs": [],
    "source": [
     "elasticsearch_url=\"http://localhost:9200\"\n",
-    "retriever = ElasticSearchBM25Retriever.create(elasticsearch_url, \"langchain-index-3\")"
+    "retriever = ElasticSearchBM25Retriever.create(elasticsearch_url, \"langchain-index-4\")"
    ]
   },
   {
@@ -66,21 +66,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 3,
    "id": "98b1c017",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "['386c76c9-4355-4c12-aaeb-7b80054caf93',\n",
-       " 'fffd279c-a0c9-4158-a904-6e242c517c99',\n",
-       " '7f5528a3-18d0-43b0-894d-f6770a002219',\n",
-       " 'e2ef5e32-d5bd-44e2-b045-cfc5a8e0a0a1',\n",
-       " 'cce8ba48-e473-4235-bca2-2c8d65e73ccf']"
+       "['cbd4cb47-8d9f-4f34-b80e-ea871bc49856',\n",
+       " 'f3bd2e24-76d1-4f9b-826b-ec4c0e8c7365',\n",
+       " '8631bfc8-7c12-48ee-ab56-8ad5f373676e',\n",
+       " '8be8374c-3253-4d87-928d-d73550a2ecf0',\n",
+       " 'd79f457b-2842-4eab-ae10-77aa420b53d7']"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -101,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 4,
    "id": "c0455218",
    "metadata": {},
    "outputs": [],
@@ -111,7 +111,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 5,
    "id": "7dfa5c29",
    "metadata": {},
    "outputs": [
@@ -122,7 +122,7 @@
        " Document(page_content='foo bar', metadata={})]"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/modules/indexes/retrievers/examples/tf_idf_retriever.ipynb

@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ab66dd43",
+   "metadata": {},
+   "source": [
+    "# TF-IDF Retriever\n",
+    "\n",
+    "This notebook goes over how to use a retriever that under the hood uses TF-IDF using scikit-learn.\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": 1,
+   "id": "393ac030",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import TFIDFRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a801b57c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aaf80e7f",
+   "metadata": {},
+   "source": [
+    "## Create New Retriever with Texts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "98b1c017",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = TFIDFRetriever.from_texts([\"foo\", \"bar\", \"world\", \"hello\", \"foo bar\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08437fa2",
+   "metadata": {},
+   "source": [
+    "## Use Retriever\n",
+    "\n",
+    "We can now use the retriever!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c0455218",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = retriever.get_relevant_documents(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7dfa5c29",
+   "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": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74bd9256",
+   "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}