Spaces:
Sleeping
Sleeping
File size: 3,650 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
{
"cells": [
{
"cell_type": "markdown",
"id": "ab66dd43",
"metadata": {},
"source": [
"# ElasticSearch BM25\n",
"\n",
"This notebook goes over how to use a retriever that under the hood uses ElasticSearcha and BM25.\n",
"\n",
"For more information on the details of BM25 see [this blog post](https://www.elastic.co/blog/practical-bm25-part-2-the-bm25-algorithm-and-its-variables)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "393ac030",
"metadata": {},
"outputs": [],
"source": [
"from langchain.retrievers import ElasticSearchBM25Retriever"
]
},
{
"cell_type": "markdown",
"id": "aaf80e7f",
"metadata": {},
"source": [
"## Create New Retriever"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "bcb3c8c2",
"metadata": {},
"outputs": [],
"source": [
"elasticsearch_url=\"http://localhost:9200\"\n",
"retriever = ElasticSearchBM25Retriever.create(elasticsearch_url, \"langchain-index-4\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "b605284d",
"metadata": {},
"outputs": [],
"source": [
"# Alternatively, you can load an existing index\n",
"# import elasticsearch\n",
"# elasticsearch_url=\"http://localhost:9200\"\n",
"# retriever = ElasticSearchBM25Retriever(elasticsearch.Elasticsearch(elasticsearch_url), \"langchain-index\")"
]
},
{
"cell_type": "markdown",
"id": "1c518c42",
"metadata": {},
"source": [
"## Add texts (if necessary)\n",
"\n",
"We can optionally add texts to the retriever (if they aren't already in there)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "98b1c017",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['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": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"retriever.add_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={})]"
]
},
"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
}
|