langchain/cookbook/custom_multi_action_agent.ipynb
Harrison Chase f20c56db41
[documentation] documentation revamp (#15281)
needs new versions of langchain-core and langchain

---------

Co-authored-by: Nuno Campos <nuno@langchain.dev>
2023-12-29 14:51:06 -08:00

221 lines
6.0 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "ba5f8741",
"metadata": {},
"source": [
"# Custom multi-action agent\n",
"\n",
"This notebook goes through how to create your own custom agent.\n",
"\n",
"An agent consists of two parts:\n",
"\n",
"- Tools: The tools the agent has available to use.\n",
"- The agent class itself: this decides which action to take.\n",
" \n",
" \n",
"In this notebook we walk through how to create a custom agent that predicts/takes multiple steps at a time."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9af9734e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import AgentExecutor, BaseMultiActionAgent, Tool\n",
"from langchain.utilities import SerpAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d7c4ebdc",
"metadata": {},
"outputs": [],
"source": [
"def random_word(query: str) -> str:\n",
" print(\"\\nNow I'm doing this!\")\n",
" return \"foo\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "becda2a1",
"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,
"id": "a33e2f7e",
"metadata": {},
"outputs": [],
"source": [
"from typing import Any, List, Tuple, Union\n",
"\n",
"from langchain.schema import AgentAction, AgentFinish\n",
"\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",
" if len(intermediate_steps) == 0:\n",
" return [\n",
" AgentAction(tool=\"Search\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" AgentAction(tool=\"RandomWord\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" ]\n",
" else:\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=\"Search\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" AgentAction(tool=\"RandomWord\", tool_input=kwargs[\"input\"], log=\"\"),\n",
" ]\n",
" else:\n",
" return AgentFinish(return_values={\"output\": \"bar\"}, log=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "655d72f6",
"metadata": {},
"outputs": [],
"source": [
"agent = FakeAgent()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "490604e9",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(\n",
" agent=agent, tools=tools, verbose=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "653b1617",
"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 38,669,152 as of Monday, April 24, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"Now I'm doing this!\n",
"\u001b[33;1m\u001b[1;3mfoo\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'bar'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"How many people live in canada as of 2023?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "adefb4c2",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}