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/examples/custom_tools.ipynb

532 lines
15 KiB
Plaintext

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"cells": [
{
"cell_type": "markdown",
"id": "5436020b",
"metadata": {},
"source": [
"# Defining Custom Tools\n",
"\n",
"When constructing your own agent, you will need to provide it with a list of Tools that it can use. A Tool is defined as below.\n",
"\n",
"```python\n",
"@dataclass \n",
"class Tool:\n",
" \"\"\"Interface for tools.\"\"\"\n",
"\n",
" name: str\n",
" func: Callable[[str], str]\n",
" description: Optional[str] = None\n",
" return_direct: bool = True\n",
"```\n",
"\n",
"The two required components of a Tool are the name and then the tool itself. A tool description is optional, as it is needed for some agents but not all. You can create these tools directly, but we also provide a decorator to easily convert any function into a tool."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "1aaba18c",
"metadata": {},
"outputs": [],
"source": [
"# Import things that are needed generically\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.llms import OpenAI\n",
"from langchain import LLMMathChain, SerpAPIWrapper"
]
},
{
"cell_type": "markdown",
"id": "8e2c3874",
"metadata": {},
"source": [
"Initialize the LLM to use for the agent."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "36ed392e",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "f8bc72c2",
"metadata": {},
"source": [
"## Completely New Tools\n",
"First, we show how to create completely new tools from scratch."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "56ff7670",
"metadata": {},
"outputs": [],
"source": [
"# Load the tool configs that are needed.\n",
"search = SerpAPIWrapper()\n",
"llm_math_chain = LLMMathChain(llm=llm, verbose=True)\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=\"Calculator\",\n",
" func=llm_math_chain.run,\n",
" description=\"useful for when you need to answer questions about math\"\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5b93047d",
"metadata": {},
"outputs": [],
"source": [
"# Construct the agent. We will use the default agent type here.\n",
"# See documentation for a full list of options.\n",
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "6f96a891",
"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 find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: Olivia Wilde's boyfriend\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mHarry Styles\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate Harry Styles' age raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 23^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"23^0.23\u001b[32;1m\u001b[1;3m\n",
"```python\n",
"import math\n",
"print(math.pow(23, 0.23))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.0568252837687546\n",
"\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.0568252837687546\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles' age raised to the 0.23 power is 2.0568252837687546.\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Harry Styles' age raised to the 0.23 power is 2.0568252837687546.\""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
"cell_type": "markdown",
"id": "824eaf74",
"metadata": {},
"source": [
"## Using the `tool` decorator\n",
"\n",
"To make it easier to define custom tools, a `@tool` decorator is provided. This decorator can be used to quickly create a `Tool` from a simple function. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "8f15307d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import tool\n",
"\n",
"@tool\n",
"def search_api(query: str) -> str:\n",
" \"\"\"Searches the API for the query.\"\"\"\n",
" return \"Results\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "0a23b91b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Tool(name='search_api', func=<function search_api at 0x10dad7d90>, description='search_api(query: str) -> str - Searches the API for the query.', return_direct=False)"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search_api"
]
},
{
"cell_type": "markdown",
"id": "cc6ee8c1",
"metadata": {},
"source": [
"You can also provide arguments like the tool name and whether to return directly."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "28cdf04d",
"metadata": {},
"outputs": [],
"source": [
"@tool(\"search\", return_direct=True)\n",
"def search_api(query: str) -> str:\n",
" \"\"\"Searches the API for the query.\"\"\"\n",
" return \"Results\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "1085a4bd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Tool(name='search', func=<function search_api at 0x112301bd0>, description='search(query: str) -> str - Searches the API for the query.', return_direct=True)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search_api"
]
},
{
"cell_type": "markdown",
"id": "1d0430d6",
"metadata": {},
"source": [
"## Modify existing tools\n",
"\n",
"Now, we show how to load existing tools and just modify them. In the example below, we do something really simple and change the Search tool to have the name `Google Search`."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "79213f40",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e1067dcb",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "6c66ffe8",
"metadata": {},
"outputs": [],
"source": [
"tools[0].name = \"Google Search\""
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f45b5bc3",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "565e2b9b",
"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 find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Google Search\n",
"Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mHarry Styles\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age\n",
"Action: Google Search\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 raised to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.1520202182226886.\u001b[0m\n",
"\u001b[1m> Finished AgentExecutor chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.1520202182226886.\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")"
]
},
{
"cell_type": "markdown",
"id": "376813ed",
"metadata": {},
"source": [
"## Defining the priorities among Tools\n",
"When you made a Custom tool, you may want the Agent to use the custom tool more than normal tools.\n",
"\n",
"For example, you made a custom tool, which gets information on music from your database. When a user wants information on songs, You want the Agent to use `the custom tool` more than the normal `Search tool`. But the Agent might prioritize a normal Search tool.\n",
"\n",
"This can be accomplished by adding a statement such as `Use this more than the normal search if the question is about Music, like 'who is the singer of yesterday?' or 'what is the most popular song in 2022?'` to the description.\n",
"\n",
"An example is below."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "3450512e",
"metadata": {},
"outputs": [],
"source": [
"# Import things that are needed generically\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.llms import OpenAI\n",
"from langchain import LLMMathChain, SerpAPIWrapper\n",
"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=\"Music Search\",\n",
" func=lambda x: \"'All I Want For Christmas Is You' by Mariah Carey.\", #Mock Function\n",
" description=\"A Music search engine. Use this more than the normal search if the question is about Music, like 'who is the singer of yesterday?' or 'what is the most popular song in 2022?'\",\n",
" )\n",
"]\n",
"\n",
"agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4b9a7849",
"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 should use a music search engine to find the answer\n",
"Action: Music Search\n",
"Action Input: most famous song of christmas\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m'All I Want For Christmas Is You' by Mariah Carey.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 'All I Want For Christmas Is You' by Mariah Carey.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"'All I Want For Christmas Is You' by Mariah Carey.\""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"what is the most famous song of christmas\")"
]
},
{
"cell_type": "markdown",
"id": "bc477d43",
"metadata": {},
"source": [
"## Using tools to return directly\n",
"Often, it can be desirable to have a tool output returned directly to the user, if its called. You can do this easily with LangChain by setting the return_direct flag for a tool to be True."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3bb6185f",
"metadata": {},
"outputs": [],
"source": [
"llm_math_chain = LLMMathChain(llm=llm)\n",
"tools = [\n",
" Tool(\n",
" name=\"Calculator\",\n",
" func=llm_math_chain.run,\n",
" description=\"useful for when you need to answer questions about math\",\n",
" return_direct=True\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "113ddb84",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "582439a6",
"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 calculate this\n",
"Action: Calculator\n",
"Action Input: 2**.12\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2599210498948732\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Answer: 1.2599210498948732'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats 2**.12\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "537bc628",
"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": "3.10.9"
},
"vscode": {
"interpreter": {
"hash": "e90c8aa204a57276aa905271aff2d11799d0acb3547adabc5892e639a5e45e34"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}