Spaces:
Sleeping
Sleeping
File size: 6,084 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Google BigQuery\n",
"\n",
">[Google BigQuery](https://cloud.google.com/bigquery) is a serverless and cost-effective enterprise data warehouse that works across clouds and scales with your data.\n",
"`BigQuery` is a part of the `Google Cloud Platform`.\n",
"\n",
"Load a `BigQuery` query with one document per row."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install google-cloud-bigquery"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.document_loaders import BigQueryLoader"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"BASE_QUERY = '''\n",
"SELECT\n",
" id,\n",
" dna_sequence,\n",
" organism\n",
"FROM (\n",
" SELECT\n",
" ARRAY (\n",
" SELECT\n",
" AS STRUCT 1 AS id, \"ATTCGA\" AS dna_sequence, \"Lokiarchaeum sp. (strain GC14_75).\" AS organism\n",
" UNION ALL\n",
" SELECT\n",
" AS STRUCT 2 AS id, \"AGGCGA\" AS dna_sequence, \"Heimdallarchaeota archaeon (strain LC_2).\" AS organism\n",
" UNION ALL\n",
" SELECT\n",
" AS STRUCT 3 AS id, \"TCCGGA\" AS dna_sequence, \"Acidianus hospitalis (strain W1).\" AS organism) AS new_array),\n",
" UNNEST(new_array)\n",
"'''"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Basic Usage"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"loader = BigQueryLoader(BASE_QUERY)\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='id: 1\\ndna_sequence: ATTCGA\\norganism: Lokiarchaeum sp. (strain GC14_75).', lookup_str='', metadata={}, lookup_index=0), Document(page_content='id: 2\\ndna_sequence: AGGCGA\\norganism: Heimdallarchaeota archaeon (strain LC_2).', lookup_str='', metadata={}, lookup_index=0), Document(page_content='id: 3\\ndna_sequence: TCCGGA\\norganism: Acidianus hospitalis (strain W1).', lookup_str='', metadata={}, lookup_index=0)]\n"
]
}
],
"source": [
"print(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Specifying Which Columns are Content vs Metadata"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"loader = BigQueryLoader(BASE_QUERY, page_content_columns=[\"dna_sequence\", \"organism\"], metadata_columns=[\"id\"])\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='dna_sequence: ATTCGA\\norganism: Lokiarchaeum sp. (strain GC14_75).', lookup_str='', metadata={'id': 1}, lookup_index=0), Document(page_content='dna_sequence: AGGCGA\\norganism: Heimdallarchaeota archaeon (strain LC_2).', lookup_str='', metadata={'id': 2}, lookup_index=0), Document(page_content='dna_sequence: TCCGGA\\norganism: Acidianus hospitalis (strain W1).', lookup_str='', metadata={'id': 3}, lookup_index=0)]\n"
]
}
],
"source": [
"print(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Adding Source to Metadata"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# Note that the `id` column is being returned twice, with one instance aliased as `source`\n",
"ALIASED_QUERY = '''\n",
"SELECT\n",
" id,\n",
" dna_sequence,\n",
" organism,\n",
" id as source\n",
"FROM (\n",
" SELECT\n",
" ARRAY (\n",
" SELECT\n",
" AS STRUCT 1 AS id, \"ATTCGA\" AS dna_sequence, \"Lokiarchaeum sp. (strain GC14_75).\" AS organism\n",
" UNION ALL\n",
" SELECT\n",
" AS STRUCT 2 AS id, \"AGGCGA\" AS dna_sequence, \"Heimdallarchaeota archaeon (strain LC_2).\" AS organism\n",
" UNION ALL\n",
" SELECT\n",
" AS STRUCT 3 AS id, \"TCCGGA\" AS dna_sequence, \"Acidianus hospitalis (strain W1).\" AS organism) AS new_array),\n",
" UNNEST(new_array)\n",
"'''"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"loader = BigQueryLoader(ALIASED_QUERY, metadata_columns=[\"source\"])\n",
"\n",
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Document(page_content='id: 1\\ndna_sequence: ATTCGA\\norganism: Lokiarchaeum sp. (strain GC14_75).\\nsource: 1', lookup_str='', metadata={'source': 1}, lookup_index=0), Document(page_content='id: 2\\ndna_sequence: AGGCGA\\norganism: Heimdallarchaeota archaeon (strain LC_2).\\nsource: 2', lookup_str='', metadata={'source': 2}, lookup_index=0), Document(page_content='id: 3\\ndna_sequence: TCCGGA\\norganism: Acidianus hospitalis (strain W1).\\nsource: 3', lookup_str='', metadata={'source': 3}, lookup_index=0)]\n"
]
}
],
"source": [
"print(data)"
]
}
],
"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
}
|