You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/docs/modules/agents/tools/multi_input_tool.ipynb

143 lines
4.0 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "87455ddb",
"metadata": {},
"source": [
"# Multi Input Tools\n",
"\n",
"This notebook shows how to use a tool that requires multiple inputs with an agent.\n",
"\n",
"The difficulty in doing so comes from the fact that an agent decides it's next step from a language model, which outputs a string. So if that step requires multiple inputs, they need to be parsed from that. Therefor, the currently supported way to do this is write a smaller wrapper function that parses that a string into multiple inputs.\n",
"\n",
"For a concrete example, let's work on giving an agent access to a multiplication function, which takes as input two integers. In order to use this, we will tell the agent to generate the \"Action Input\" as a comma separated list of length two. We will then write a thin wrapper that takes a string, splits it into two around a comma, and passes both parsed sides as integers to the multiplication function."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "291149b6",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.agents import initialize_agent, Tool"
]
},
{
"cell_type": "markdown",
"id": "71b6bead",
"metadata": {},
"source": [
"Here is the multiplication function, as well as a wrapper to parse a string as input."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f0b82020",
"metadata": {},
"outputs": [],
"source": [
"def multiplier(a, b):\n",
" return a * b\n",
"\n",
"def parsing_multiplier(string):\n",
" a, b = string.split(\",\")\n",
" return multiplier(int(a), int(b))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "6db1d43f",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"tools = [\n",
" Tool(\n",
" name = \"Multiplier\",\n",
" func=parsing_multiplier,\n",
" description=\"useful for when you need to multiply two numbers together. The input to this tool should be a comma separated list of numbers of length two, representing the two numbers you want to multiply together. For example, `1,2` would be the input if you wanted to multiply 1 by 2.\"\n",
" )\n",
"]\n",
"mrkl = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "aa25d0ca",
"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 I need to multiply two numbers\n",
"Action: Multiplier\n",
"Action Input: 3,4\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m12\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 3 times 4 is 12\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'3 times 4 is 12'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mrkl.run(\"What is 3 times 4\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7ea340c0",
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}