Spaces:
Runtime error
Runtime error
File size: 3,713 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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "dc23c48e",
"metadata": {},
"source": [
"# Google Serper API\n",
"\n",
"This notebook goes over how to use the Google Serper component to search the web. First you need to sign up for a free account at [serper.dev](https://serper.dev) and get your api key."
]
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"import os\n",
"os.environ[\"SERPER_API_KEY\"] = \"\""
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 2,
"id": "54bf5afd",
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities import GoogleSerperAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "31f8f382",
"metadata": {},
"outputs": [],
"source": [
"search = GoogleSerperAPIWrapper()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "25ce0225",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": "'Barack Hussein Obama II'"
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search.run(\"Obama's first name?\")"
]
},
{
"cell_type": "markdown",
"source": [
"## As part of a Self Ask With Search Chain"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"os.environ['OPENAI_API_KEY'] = \"\""
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": 5,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3mCurrent champions Carlos Alcaraz, 2022 men's singles champion.\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mFollow up: Where is Carlos Alcaraz from?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3mEl Palmar, Spain\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mSo the final answer is: El Palmar, Spain\u001B[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
"data": {
"text/plain": "'El Palmar, Spain'"
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.utilities import GoogleSerperAPIWrapper\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.agents import initialize_agent, Tool\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"search = GoogleSerperAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name=\"Intermediate Answer\",\n",
" func=search.run\n",
" )\n",
"]\n",
"\n",
"self_ask_with_search = initialize_agent(tools, llm, agent=\"self-ask-with-search\", verbose=True)\n",
"self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
],
"metadata": {
"collapsed": false
}
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|