Spaces:
Runtime error
Runtime error
File size: 5,662 Bytes
acc4ffe |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
{
"cells": [
{
"cell_type": "markdown",
"id": "a6850189",
"metadata": {},
"source": [
"# Graph QA\n",
"\n",
"This notebook goes over how to do question answering over a graph data structure."
]
},
{
"cell_type": "markdown",
"id": "9e516e3e",
"metadata": {},
"source": [
"## Create the graph\n",
"\n",
"In this section, we construct an example graph. At the moment, this works best for small pieces of text."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3849873d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.indexes import GraphIndexCreator\n",
"from langchain.llms import OpenAI\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "05d65c87",
"metadata": {},
"outputs": [],
"source": [
"index_creator = GraphIndexCreator(llm=OpenAI(temperature=0))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "0a45a5b9",
"metadata": {},
"outputs": [],
"source": [
"with open(\"../../state_of_the_union.txt\") as f:\n",
" all_text = f.read()"
]
},
{
"cell_type": "markdown",
"id": "3fca3e1b",
"metadata": {},
"source": [
"We will use just a small snippet, because extracting the knowledge triplets is a bit intensive at the moment."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "80522bd6",
"metadata": {},
"outputs": [],
"source": [
"text = \"\\n\".join(all_text.split(\"\\n\\n\")[105:108])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "da5aad5a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'It won’t look like much, but if you stop and look closely, you’ll see a “Field of dreams,” the ground on which America’s future will be built. \\nThis is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor “mega site”. \\nUp to eight state-of-the-art factories in one place. 10,000 new good-paying jobs. '"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8dad7b59",
"metadata": {},
"outputs": [],
"source": [
"graph = index_creator.from_text(text)"
]
},
{
"cell_type": "markdown",
"id": "2118f363",
"metadata": {},
"source": [
"We can inspect the created graph."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "32878c13",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('Intel', '$20 billion semiconductor \"mega site\"', 'is going to build'),\n",
" ('Intel', 'state-of-the-art factories', 'is building'),\n",
" ('Intel', '10,000 new good-paying jobs', 'is creating'),\n",
" ('Intel', 'Silicon Valley', 'is helping build'),\n",
" ('Field of dreams',\n",
" \"America's future will be built\",\n",
" 'is the ground on which')]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"graph.get_triples()"
]
},
{
"cell_type": "markdown",
"id": "e9737be1",
"metadata": {},
"source": [
"## Querying the graph\n",
"We can now use the graph QA chain to ask question of the graph"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "76edc854",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import GraphQAChain"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "8e7719b4",
"metadata": {},
"outputs": [],
"source": [
"chain = GraphQAChain.from_llm(OpenAI(temperature=0), graph=graph, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "f6511169",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
"Entities Extracted:\n",
"\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
"Full Context:\n",
"\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"Intel is building state-of-the-art factories\n",
"Intel is creating 10,000 new good-paying jobs\n",
"Intel is helping build Silicon Valley\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Intel is going to build a $20 billion semiconductor \"mega site\" with state-of-the-art factories, creating 10,000 new good-paying jobs and helping to build Silicon Valley.'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(\"what is Intel going to build?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f70b9ada",
"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
}
|