Spaces:
Runtime error
Runtime error
File size: 6,205 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import Tool, AgentExecutor, BaseMultiActionAgent\n",
"from langchain import OpenAI, SerpAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def random_word(query: str) -> str:\n",
" print(\"\\nNow I'm doing this!\")\n",
" return f\"{query}, foo\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"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",
" ),\n",
" Tool(\n",
" name = \"RandomWord\",\n",
" func=random_word,\n",
" description=\"call this to get a random word.\",\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from langchain.tools import tool\n",
"\n",
"@tool\n",
"def tool1(event) -> str:\n",
" \"\"\"这里必须添加描述，不然AssertionError: Function must have a docstring if description not provided.\"\"\"\n",
" return \"111\"\n",
"\n",
"from langchain.tools import tool\n",
"\n",
"@tool\n",
"def tool2(event) -> str:\n",
" \"\"\"这里必须添加描述，不然AssertionError: Function must have a docstring if description not provided.\"\"\"\n",
" return \"222\"\n",
"\n",
"tools = [tool1, tool2]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from typing import List, Tuple, Any, Union\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"\n",
"class FakeAgent(BaseMultiActionAgent):\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[List[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",
" print(\"lizhen0\",intermediate_steps)\n",
" if len(intermediate_steps) == 0:\n",
" print(\"lizhen1\",intermediate_steps)\n",
" return [\n",
" AgentAction(tool=\"tool1\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" AgentAction(tool=\"tool2\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" ]\n",
" else:\n",
" for tuple in intermediate_steps:\n",
" print(tuple[0].tool, tuple[1])\n",
" return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")\n",
"\n",
" async def aplan(\n",
" self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any\n",
" ) -> Union[List[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",
" if len(intermediate_steps) == 0:\n",
" return [\n",
" AgentAction(tool=\"tool1\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" AgentAction(tool=\"tool2\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" ]\n",
" else:\n",
" return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"agent = FakeAgent()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"lizhen0 []\n",
"lizhen1 []\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[36;1m\u001b[1;3m111\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[33;1m\u001b[1;3m222\u001b[0mlizhen0 [(AgentAction(tool='tool1', tool_input='How many people live in canada as of 2023?', log=''), '111'), (AgentAction(tool='tool2', tool_input='How many people live in canada as of 2023?', log=''), '222')]\n",
"tool1 111\n",
"tool2 222\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'bar'"
]
},
"execution_count": 8,
"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
}
|