Spaces:
Runtime error
Runtime error
File size: 4,153 Bytes
4968970 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import Tool, AgentExecutor, BaseSingleActionAgent\n",
"from langchain import OpenAI, SerpAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"search = SerpAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name = \"Search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events\",\n",
" return_direct=True\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Tuple, Any, Union\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"\n",
"class FakeAgent(BaseSingleActionAgent):\n",
" \"\"\"Fake Custom Agent.\"\"\"\n",
" \n",
" @property\n",
" def input_keys(self):\n",
" return [\"input\"]\n",
" \n",
" def plan(\n",
" self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
" ) -> Union[AgentAction, AgentFinish]:\n",
" \"\"\"Given input, decided what to do.\n",
"\n",
" Args:\n",
" intermediate_steps: Steps the LLM has taken to date,\n",
" along with observations\n",
" **kwargs: User inputs.\n",
"\n",
" Returns:\n",
" Action specifying what tool to use.\n",
" \"\"\"\n",
" return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")\n",
"\n",
" async def aplan(\n",
" self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
" ) -> Union[AgentAction, AgentFinish]:\n",
" \"\"\"Given input, decided what to do.\n",
"\n",
" Args:\n",
" intermediate_steps: Steps the LLM has taken to date,\n",
" along with observations\n",
" **kwargs: User inputs.\n",
"\n",
" Returns:\n",
" Action specifying what tool to use.\n",
" \"\"\"\n",
" return AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"agent = FakeAgent()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[36;1m\u001b[1;3mThe current population of Canada is 38,680,894 as of Sunday, May 7, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The current population of Canada is 38,680,894 as of Sunday, May 7, 2023, based on Worldometer elaboration of the latest United Nations data.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"How many people live in canada as of 2023?\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.10.10"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|