mirror of https://github.com/hwchase17/langchain
beef up agent docs (#10866)
Harrison Chase
1 year ago
committed by
GitHub
parent
4b558c9e17
commit
808caca607
@ -1,13 +0,0 @@
|
||||
# Conversational
|
||||
|
||||
This walkthrough demonstrates how to use an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.
|
||||
|
||||
import Example from "@snippets/modules/agents/agent_types/conversational_agent.mdx"
|
||||
|
||||
<Example/>
|
||||
|
||||
import ChatExample from "@snippets/modules/agents/agent_types/chat_conversation_agent.mdx"
|
||||
|
||||
## Using a chat model
|
||||
|
||||
<ChatExample/>
|
||||
@ -1,11 +0,0 @@
|
||||
# OpenAI functions
|
||||
|
||||
Certain OpenAI models (like gpt-3.5-turbo-0613 and gpt-4-0613) have been fine-tuned to detect when a function should be called and respond with the inputs that should be passed to the function.
|
||||
In an API call, you can describe functions and have the model intelligently choose to output a JSON object containing arguments to call those functions.
|
||||
The goal of the OpenAI Function APIs is to more reliably return valid and useful function calls than a generic text completion or chat API.
|
||||
|
||||
The OpenAI Functions Agent is designed to work with these models.
|
||||
|
||||
import Example from "@snippets/modules/agents/agent_types/openai_functions_agent.mdx";
|
||||
|
||||
<Example/>
|
||||
@ -1,11 +0,0 @@
|
||||
# Plan-and-execute
|
||||
|
||||
Plan-and-execute agents accomplish an objective by first planning what to do, then executing the sub tasks. This idea is largely inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) and then the ["Plan-and-Solve" paper](https://arxiv.org/abs/2305.04091).
|
||||
|
||||
The planning is almost always done by an LLM.
|
||||
|
||||
The execution is usually done by a separate agent (equipped with tools).
|
||||
|
||||
import Example from "@snippets/modules/agents/agent_types/plan_and_execute.mdx"
|
||||
|
||||
<Example/>
|
||||
@ -1,15 +0,0 @@
|
||||
# ReAct
|
||||
|
||||
This walkthrough showcases using an agent to implement the [ReAct](https://react-lm.github.io/) logic.
|
||||
|
||||
import Example from "@snippets/modules/agents/agent_types/react.mdx"
|
||||
|
||||
<Example/>
|
||||
|
||||
## Using chat models
|
||||
|
||||
You can also create ReAct agents that use chat models instead of LLMs as the agent driver.
|
||||
|
||||
import ChatExample from "@snippets/modules/agents/agent_types/react_chat.mdx"
|
||||
|
||||
<ChatExample/>
|
||||
@ -0,0 +1,528 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "69014601",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Conversational\n",
|
||||
"\n",
|
||||
"This walkthrough demonstrates how to use an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\n",
|
||||
"\n",
|
||||
"If we compare it to the standard ReAct agent, the main difference is the prompt.\n",
|
||||
"We want it to be much more conversational."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "cc3fad9e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import Tool\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.utilities import SerpAPIWrapper\n",
|
||||
"from langchain.agents import initialize_agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "2d84b9bc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Current Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events or the current state of the world\"\n",
|
||||
" ),\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "799a31bf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm=OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f9d11cb6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using LCEL\n",
|
||||
"\n",
|
||||
"We will first show how to create this agent using LCEL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "03c09ef9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools.render import render_text_description\n",
|
||||
"from langchain.agents.output_parsers import ReActSingleInputOutputParser\n",
|
||||
"from langchain.agents.format_scratchpad import format_log_to_str"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"id": "6bd84102",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import hub\n",
|
||||
"prompt = hub.pull(\"hwchase17/react-chat\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"id": "7ccc785d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = prompt.partial(\n",
|
||||
" tools=render_text_description(tools),\n",
|
||||
" tool_names=\", \".join([t.name for t in tools]),\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "d7aac2b0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_with_stop = llm.bind(stop=[\"\\nObservation\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "a028bca6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"agent_scratchpad\": lambda x: format_log_to_str(x['intermediate_steps']),\n",
|
||||
" \"chat_history\": lambda x: x[\"chat_history\"]\n",
|
||||
"} | prompt | llm_with_stop | ReActSingleInputOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"id": "9b044ae9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"id": "adcdd0c7",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\n",
|
||||
"Thought: Do I need to use a tool? No\n",
|
||||
"Final Answer: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hi Bob, nice to meet you! How can I help you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"hi, i am bob\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"id": "c5846cd1",
|
||||
"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\n",
|
||||
"Thought: Do I need to use a tool? No\n",
|
||||
"Final Answer: Your name is Bob.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Your name is Bob.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"whats my name?\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"id": "95a1192a",
|
||||
"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\n",
|
||||
"Thought: Do I need to use a tool? Yes\n",
|
||||
"Action: Current Search\n",
|
||||
"Action Input: Movies showing 9/21/2023\u001b[0m\u001b[36;1m\u001b[1;3m['September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...']\u001b[0m\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
|
||||
"Final Answer: According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"what are some movies showing 9/21/2023?\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c0b2d86d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use the off-the-shelf agent\n",
|
||||
"\n",
|
||||
"We can also create this agent using the off-the-shelf agent class"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "53e43064",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "68e45a24",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use a chat model\n",
|
||||
"\n",
|
||||
"We can also use a chat model here. The main difference here is in the prompts used."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "16b17ca8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import hub\n",
|
||||
"prompt = hub.pull(\"hwchase17/react-chat-json\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"id": "e93c0832",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"\n",
|
||||
"chat_model = ChatOpenAI(temperature=0, model='gpt-4')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"id": "c8a94b0b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = prompt.partial(\n",
|
||||
" tools=render_text_description(tools),\n",
|
||||
" tool_names=\", \".join([t.name for t in tools]),\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"id": "c5d710f2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_model_with_stop = chat_model.bind(stop=[\"\\nObservation\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"id": "2c845796",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.output_parsers import JSONAgentOutputParser\n",
|
||||
"from langchain.agents.format_scratchpad import format_log_to_messages\n",
|
||||
"\n",
|
||||
"# We need some extra steering, or the chat model forgets how to respond sometimes\n",
|
||||
"TEMPLATE_TOOL_RESPONSE = \"\"\"TOOL RESPONSE: \n",
|
||||
"---------------------\n",
|
||||
"{observation}\n",
|
||||
"\n",
|
||||
"USER'S INPUT\n",
|
||||
"--------------------\n",
|
||||
"\n",
|
||||
"Okay, so what is the response to my last comment? If using information obtained from the tools you must mention it explicitly without mentioning the tool names - I have forgotten all TOOL RESPONSES! Remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else - even if you just want to respond to the user. Do NOT respond with anything except a JSON snippet no matter what!\"\"\"\n",
|
||||
"\n",
|
||||
"agent = {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"agent_scratchpad\": lambda x: format_log_to_messages(x['intermediate_steps'], template_tool_response=TEMPLATE_TOOL_RESPONSE),\n",
|
||||
" \"chat_history\": lambda x: x[\"chat_history\"],\n",
|
||||
"} | prompt | chat_model_with_stop | JSONAgentOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "332ba2ff",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)\n",
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"id": "139717b4",
|
||||
"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```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Hello Bob, how can I assist you today?\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Hello Bob, how can I assist you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"hi, i am bob\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"id": "7e7cf6d3",
|
||||
"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```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Your name is Bob.\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Your name is Bob.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"whats my name?\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"id": "3fc00073",
|
||||
"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```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Current Search\",\n",
|
||||
" \"action_input\": \"movies showing on 9/21/2023\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\u001b[36;1m\u001b[1;3m['September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...']\u001b[0m\u001b[32;1m\u001b[1;3m```json\n",
|
||||
"{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"Some movies that are showing on 9/21/2023 include 'The Creator', 'Dumb Money', 'Expend4bles', 'The Kill Room', 'The Inventor', 'The Equalizer 3', and 'PAW Patrol: The Mighty Movie'.\"\n",
|
||||
"}\n",
|
||||
"```\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Some movies that are showing on 9/21/2023 include 'The Creator', 'Dumb Money', 'Expend4bles', 'The Kill Room', 'The Inventor', 'The Equalizer 3', and 'PAW Patrol: The Mighty Movie'.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"what are some movies showing 9/21/2023?\"})['output']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8d464ead",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can also initialize the agent executor with a predefined agent type"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "734d1b21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)\n",
|
||||
"llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0)\n",
|
||||
"agent_chain = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,259 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e10aa932",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenAI functions\n",
|
||||
"\n",
|
||||
"Certain OpenAI models (like gpt-3.5-turbo-0613 and gpt-4-0613) have been fine-tuned to detect when a function should be called and respond with the inputs that should be passed to the function. In an API call, you can describe functions and have the model intelligently choose to output a JSON object containing arguments to call those functions. The goal of the OpenAI Function APIs is to more reliably return valid and useful function calls than a generic text completion or chat API.\n",
|
||||
"\n",
|
||||
"The OpenAI Functions Agent is designed to work with these models.\n",
|
||||
"\n",
|
||||
"Install `openai`, `google-search-results` packages which are required as the LangChain packages call them internally."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ec89be68",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! pip install openai google-search-results"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "82787d8d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize tools\n",
|
||||
"\n",
|
||||
"We will first create some tools we can use"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "b812b982",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import initialize_agent, AgentType, Tool\n",
|
||||
"from langchain.chains import LLMMathChain\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.utilities import SerpAPIWrapper, SQLDatabase\n",
|
||||
"from langchain_experimental.sql import SQLDatabaseChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "23fc0aa6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
|
||||
"db_chain = SQLDatabaseChain.from_llm(llm, db, 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. You should ask targeted questions\"\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",
|
||||
" Tool(\n",
|
||||
" name=\"FooBar-DB\",\n",
|
||||
" func=db_chain.run,\n",
|
||||
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39c3ba21",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using LCEL\n",
|
||||
"\n",
|
||||
"We will first use LangChain Expression Language to create this agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "55292bed",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
|
||||
"prompt = ChatPromptTemplate.from_messages([\n",
|
||||
" (\"system\", \"You are a helpful assistant\"),\n",
|
||||
" (\"user\", \"{input}\"),\n",
|
||||
" MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
|
||||
"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "552421b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools.render import format_tool_to_openai_function\n",
|
||||
"llm_with_tools = llm.bind(\n",
|
||||
" functions=[format_tool_to_openai_function(t) for t in tools]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "bf514eb4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.format_scratchpad import format_to_openai_functions\n",
|
||||
"from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser\n",
|
||||
"agent = {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"agent_scratchpad\": lambda x: format_to_openai_functions(x['intermediate_steps'])\n",
|
||||
"} | prompt | llm_with_tools | OpenAIFunctionsAgentOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "bdc7e506",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "2cd65218",
|
||||
"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\n",
|
||||
"Invoking: `Search` with `Leo DiCaprio's girlfriend`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3m['Blake Lively and DiCaprio are believed to have enjoyed a whirlwind five-month romance in 2011. The pair were seen on a yacht together in Cannes, ...']\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `Calculator` with `0.43`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
|
||||
"0.43\u001b[32;1m\u001b[1;3m```text\n",
|
||||
"0.43\n",
|
||||
"```\n",
|
||||
"...numexpr.evaluate(\"0.43\")...\n",
|
||||
"\u001b[0m\n",
|
||||
"Answer: \u001b[33;1m\u001b[1;3m0.43\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\u001b[33;1m\u001b[1;3mAnswer: 0.43\u001b[0m\u001b[32;1m\u001b[1;3mI'm sorry, but I couldn't find any information about Leo DiCaprio's current girlfriend. As for raising her age to the power of 0.43, I'm not sure what her current age is, so I can't provide an answer for that.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\",\n",
|
||||
" 'output': \"I'm sorry, but I couldn't find any information about Leo DiCaprio's current girlfriend. As for raising her age to the power of 0.43, I'm not sure what her current age is, so I can't provide an answer for that.\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8e91393f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using OpenAIFunctionsAgent\n",
|
||||
"\n",
|
||||
"We can now use `OpenAIFunctionsAgent`, which creates this agent under the hood"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "9ed07c8f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8d9fb674",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2bc581dc",
|
||||
"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": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,365 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d82e62ec",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ReAct\n",
|
||||
"\n",
|
||||
"This walkthrough showcases using an agent to implement the [ReAct](https://react-lm.github.io/) logic."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "102b0e52",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import load_tools\n",
|
||||
"from langchain.agents import initialize_agent\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e0c9c056",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First, let's load the language model we're going to use to control the agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "184f0682",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2e67a000",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "256408d5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b7d04f53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using LCEL\n",
|
||||
"\n",
|
||||
"We will first show how to create the agent using LCEL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "bb0813a3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools.render import render_text_description\n",
|
||||
"from langchain.agents.output_parsers import ReActSingleInputOutputParser\n",
|
||||
"from langchain.agents.format_scratchpad import format_log_to_str"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "d3ae5fcd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import hub\n",
|
||||
"prompt = hub.pull(\"hwchase17/react\")\n",
|
||||
"prompt = prompt.partial(\n",
|
||||
" tools=render_text_description(tools),\n",
|
||||
" tool_names=\", \".join([t.name for t in tools]),\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "bf47a3c7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_with_stop = llm.bind(stop=[\"\\nObservation\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "b3d3958b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"agent_scratchpad\": lambda x: format_log_to_str(x['intermediate_steps'])\n",
|
||||
"} | prompt | llm_with_stop | ReActSingleInputOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "026de6cd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "57780ce1",
|
||||
"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 Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\u001b[36;1m\u001b[1;3mmodel Vittoria Ceretti\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out Vittoria Ceretti's age\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Vittoria Ceretti age\"\u001b[0m\u001b[36;1m\u001b[1;3m25 years\u001b[0m\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.43 power\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 25^0.43\u001b[0m\u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\",\n",
|
||||
" 'output': \"Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b4a33ea8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using ZeroShotReactAgent\n",
|
||||
"\n",
|
||||
"We will now show how to use the agent with an off-the-shelf agent implementation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "9752e90e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "04c5bcf6",
|
||||
"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 Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mmodel Vittoria Ceretti\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Vittoria Ceretti's age\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Vittoria Ceretti age\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m25 years\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.43 power\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 25^0.43\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\",\n",
|
||||
" 'output': \"Leo DiCaprio's girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7f3e8fc8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using chat models\n",
|
||||
"\n",
|
||||
"You can also create ReAct agents that use chat models instead of LLMs as the agent driver.\n",
|
||||
"\n",
|
||||
"The main difference here is a different prompt. We will use JSON to encode the agent's actions (chat models are a bit tougher to steet, so using JSON helps to enforce the output format)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"id": "fe846c48",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"\n",
|
||||
"chat_model = ChatOpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "0843590d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = hub.pull(\"hwchase17/react-json\")\n",
|
||||
"prompt = prompt.partial(\n",
|
||||
" tools=render_text_description(tools),\n",
|
||||
" tool_names=\", \".join([t.name for t in tools]),\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"id": "a863b763",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_model_with_stop = chat_model.bind(stop=[\"\\nObservation\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"id": "6336a378",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents.output_parsers import ReActJsonSingleInputOutputParser\n",
|
||||
"agent = {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"agent_scratchpad\": lambda x: format_log_to_str(x['intermediate_steps'])\n",
|
||||
"} | prompt | chat_model_with_stop | ReActJsonSingleInputOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"id": "13ad514e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3a3394a4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ffc28e29",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can also use an off-the-shelf agent class"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6c41464c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\n",
|
||||
"agent = initialize_agent(tools, chat_model, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",
|
||||
"agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -1,3 +1,11 @@
|
||||
# Plan-and-execute
|
||||
|
||||
Plan-and-execute agents accomplish an objective by first planning what to do, then executing the sub tasks. This idea is largely inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) and then the ["Plan-and-Solve" paper](https://arxiv.org/abs/2305.04091).
|
||||
|
||||
The planning is almost always done by an LLM.
|
||||
|
||||
The execution is usually done by a separate agent (equipped with tools).
|
||||
|
||||
## Imports
|
||||
|
||||
|
||||
@ -1,130 +0,0 @@
|
||||
The `chat-conversational-react-description` agent type lets us create a conversational agent using a chat model instead of an LLM.
|
||||
|
||||
```python
|
||||
from langchain.memory import ConversationBufferMemory
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
|
||||
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
|
||||
llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0)
|
||||
agent_chain = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="hi, i am bob")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
{
|
||||
"action": "Final Answer",
|
||||
"action_input": "Hello Bob! How can I assist you today?"
|
||||
}
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Hello Bob! How can I assist you today?'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="what's my name?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
{
|
||||
"action": "Final Answer",
|
||||
"action_input": "Your name is Bob."
|
||||
}
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Your name is Bob.'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run("what are some good dinners to make this week, if i like thai food?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
{
|
||||
"action": "Current Search",
|
||||
"action_input": "Thai food dinner recipes"
|
||||
}
|
||||
Observation: 64 easy Thai recipes for any night of the week · Thai curry noodle soup · Thai yellow cauliflower, snake bean and tofu curry · Thai-spiced chicken hand pies · Thai ...
|
||||
Thought:{
|
||||
"action": "Final Answer",
|
||||
"action_input": "Here are some Thai food dinner recipes you can try this week: Thai curry noodle soup, Thai yellow cauliflower, snake bean and tofu curry, Thai-spiced chicken hand pies, and many more. You can find the full list of recipes at the source I found earlier."
|
||||
}
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Here are some Thai food dinner recipes you can try this week: Thai curry noodle soup, Thai yellow cauliflower, snake bean and tofu curry, Thai-spiced chicken hand pies, and many more. You can find the full list of recipes at the source I found earlier.'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="tell me the last letter in my name, and also tell me who won the world cup in 1978?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
{
|
||||
"action": "Final Answer",
|
||||
"action_input": "The last letter in your name is 'b'. Argentina won the World Cup in 1978."
|
||||
}
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
"The last letter in your name is 'b'. Argentina won the World Cup in 1978."
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="whats the weather like in pomfret?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
{
|
||||
"action": "Current Search",
|
||||
"action_input": "weather in pomfret"
|
||||
}
|
||||
Observation: Cloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%.
|
||||
Thought:{
|
||||
"action": "Final Answer",
|
||||
"action_input": "Cloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%."
|
||||
}
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Cloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%.'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
@ -1,150 +0,0 @@
|
||||
This is accomplished with a specific type of agent (`conversational-react-description`) which expects to be used with a memory component.
|
||||
|
||||
```python
|
||||
from langchain.agents import Tool
|
||||
from langchain.agents import AgentType
|
||||
from langchain.memory import ConversationBufferMemory
|
||||
from langchain.llms import OpenAI
|
||||
from langchain.utilities import SerpAPIWrapper
|
||||
from langchain.agents import initialize_agent
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
search = SerpAPIWrapper()
|
||||
tools = [
|
||||
Tool(
|
||||
name = "Current Search",
|
||||
func=search.run,
|
||||
description="useful for when you need to answer questions about current events or the current state of the world"
|
||||
),
|
||||
]
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
memory = ConversationBufferMemory(memory_key="chat_history")
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
llm=OpenAI(temperature=0)
|
||||
agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="hi, i am bob")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
|
||||
Thought: Do I need to use a tool? No
|
||||
AI: Hi Bob, nice to meet you! How can I help you today?
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Hi Bob, nice to meet you! How can I help you today?'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="what's my name?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
|
||||
Thought: Do I need to use a tool? No
|
||||
AI: Your name is Bob!
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'Your name is Bob!'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run("what are some good dinners to make this week, if i like thai food?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
|
||||
Thought: Do I need to use a tool? Yes
|
||||
Action: Current Search
|
||||
Action Input: Thai food dinner recipes
|
||||
Observation: 59 easy Thai recipes for any night of the week · Marion Grasby's Thai spicy chilli and basil fried rice · Thai curry noodle soup · Marion Grasby's Thai Spicy ...
|
||||
Thought: Do I need to use a tool? No
|
||||
AI: Here are some great Thai dinner recipes you can try this week: Marion Grasby's Thai Spicy Chilli and Basil Fried Rice, Thai Curry Noodle Soup, Thai Green Curry with Coconut Rice, Thai Red Curry with Vegetables, and Thai Coconut Soup. I hope you enjoy them!
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
"Here are some great Thai dinner recipes you can try this week: Marion Grasby's Thai Spicy Chilli and Basil Fried Rice, Thai Curry Noodle Soup, Thai Green Curry with Coconut Rice, Thai Red Curry with Vegetables, and Thai Coconut Soup. I hope you enjoy them!"
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="tell me the last letter in my name, and also tell me who won the world cup in 1978?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
|
||||
Thought: Do I need to use a tool? Yes
|
||||
Action: Current Search
|
||||
Action Input: Who won the World Cup in 1978
|
||||
Observation: Argentina national football team
|
||||
Thought: Do I need to use a tool? No
|
||||
AI: The last letter in your name is "b" and the winner of the 1978 World Cup was the Argentina national football team.
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'The last letter in your name is "b" and the winner of the 1978 World Cup was the Argentina national football team.'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
|
||||
|
||||
```python
|
||||
agent_chain.run(input="whats the current temperature in pomfret?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
|
||||
Thought: Do I need to use a tool? Yes
|
||||
Action: Current Search
|
||||
Action Input: Current temperature in Pomfret
|
||||
Observation: Partly cloudy skies. High around 70F. Winds W at 5 to 10 mph. Humidity41%.
|
||||
Thought: Do I need to use a tool? No
|
||||
AI: The current temperature in Pomfret is around 70F with partly cloudy skies and winds W at 5 to 10 mph. The humidity is 41%.
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
'The current temperature in Pomfret is around 70F with partly cloudy skies and winds W at 5 to 10 mph. The humidity is 41%.'
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
@ -1,80 +0,0 @@
|
||||
Install `openai`, `google-search-results` packages which are required as the LangChain packages call them internally.
|
||||
|
||||
```bash
|
||||
pip install openai google-search-results
|
||||
```
|
||||
|
||||
```python
|
||||
from langchain.agents import initialize_agent, AgentType, Tool
|
||||
from langchain.chains import LLMMathChain
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.llms import OpenAI
|
||||
from langchain.utilities import SerpAPIWrapper, SQLDatabase
|
||||
from langchain_experimental.sql import SQLDatabaseChain
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
|
||||
search = SerpAPIWrapper()
|
||||
llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)
|
||||
db = SQLDatabase.from_uri("sqlite:///../../../../../notebooks/Chinook.db")
|
||||
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
|
||||
tools = [
|
||||
Tool(
|
||||
name = "Search",
|
||||
func=search.run,
|
||||
description="useful for when you need to answer questions about current events. You should ask targeted questions"
|
||||
),
|
||||
Tool(
|
||||
name="Calculator",
|
||||
func=llm_math_chain.run,
|
||||
description="useful for when you need to answer questions about math"
|
||||
),
|
||||
Tool(
|
||||
name="FooBar-DB",
|
||||
func=db_chain.run,
|
||||
description="useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context"
|
||||
)
|
||||
]
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
agent = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new chain...
|
||||
|
||||
Invoking: `Search` with `{'query': 'Leo DiCaprio girlfriend'}`
|
||||
|
||||
|
||||
Amidst his casual romance with Gigi, Leo allegedly entered a relationship with 19-year old model, Eden Polani, in February 2023.
|
||||
Invoking: `Calculator` with `{'expression': '19^0.43'}`
|
||||
|
||||
|
||||
> Entering new chain...
|
||||
19^0.43```text
|
||||
19**0.43
|
||||
```
|
||||
...numexpr.evaluate("19**0.43")...
|
||||
|
||||
Answer: 3.547023357958959
|
||||
> Finished chain.
|
||||
Answer: 3.547023357958959Leo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55.
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
"Leo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55."
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
@ -1,62 +0,0 @@
|
||||
```python
|
||||
from langchain.agents import load_tools
|
||||
from langchain.agents import initialize_agent
|
||||
from langchain.agents import AgentType
|
||||
from langchain.llms import OpenAI
|
||||
```
|
||||
|
||||
First, let's load the language model we're going to use to control the agent.
|
||||
|
||||
|
||||
```python
|
||||
llm = OpenAI(temperature=0)
|
||||
```
|
||||
|
||||
Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.
|
||||
|
||||
|
||||
```python
|
||||
tools = load_tools(["serpapi", "llm-math"], llm=llm)
|
||||
```
|
||||
|
||||
Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
|
||||
|
||||
|
||||
```python
|
||||
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
|
||||
```
|
||||
|
||||
Now let's test it out!
|
||||
|
||||
|
||||
```python
|
||||
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
|
||||
```
|
||||
|
||||
<CodeOutputBlock lang="python">
|
||||
|
||||
```
|
||||
> Entering new AgentExecutor chain...
|
||||
I need to find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.
|
||||
Action: Search
|
||||
Action Input: "Leo DiCaprio girlfriend"
|
||||
Observation: Camila Morrone
|
||||
Thought: I need to find out Camila Morrone's age
|
||||
Action: Search
|
||||
Action Input: "Camila Morrone age"
|
||||
Observation: 25 years
|
||||
Thought: I need to calculate 25 raised to the 0.43 power
|
||||
Action: Calculator
|
||||
Action Input: 25^0.43
|
||||
Observation: Answer: 3.991298452658078
|
||||
|
||||
Thought: I now know the final answer
|
||||
Final Answer: Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078.
|
||||
|
||||
> Finished chain.
|
||||
|
||||
|
||||
"Camila Morrone is Leo DiCaprio's girlfriend and her current age raised to the 0.43 power is 3.991298452658078."
|
||||
```
|
||||
|
||||
</CodeOutputBlock>
|
||||
@ -1,7 +0,0 @@
|
||||
```python
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
|
||||
chat_model = ChatOpenAI(temperature=0)
|
||||
agent = initialize_agent(tools, chat_model, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
|
||||
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
|
||||
```
|
||||
@ -0,0 +1,13 @@
|
||||
from langchain.agents.format_scratchpad.log import format_log_to_str
|
||||
from langchain.agents.format_scratchpad.log_to_messages import format_log_to_messages
|
||||
from langchain.agents.format_scratchpad.openai_functions import (
|
||||
format_to_openai_functions,
|
||||
)
|
||||
from langchain.agents.format_scratchpad.xml import format_xml
|
||||
|
||||
__all__ = [
|
||||
"format_xml",
|
||||
"format_to_openai_functions",
|
||||
"format_log_to_str",
|
||||
"format_log_to_messages",
|
||||
]
|
||||
@ -1,30 +1,4 @@
|
||||
from langchain.tools import BaseTool
|
||||
from langchain.utils.openai_functions import (
|
||||
FunctionDescription,
|
||||
convert_pydantic_to_openai_function,
|
||||
)
|
||||
from langchain.tools.render import format_tool_to_openai_function
|
||||
|
||||
|
||||
def format_tool_to_openai_function(tool: BaseTool) -> FunctionDescription:
|
||||
"""Format tool into the OpenAI function API."""
|
||||
if tool.args_schema:
|
||||
return convert_pydantic_to_openai_function(
|
||||
tool.args_schema, name=tool.name, description=tool.description
|
||||
)
|
||||
else:
|
||||
return {
|
||||
"name": tool.name,
|
||||
"description": tool.description,
|
||||
"parameters": {
|
||||
# This is a hack to get around the fact that some tools
|
||||
# do not expose an args_schema, and expect an argument
|
||||
# which is a string.
|
||||
# And Open AI does not support an array type for the
|
||||
# parameters.
|
||||
"properties": {
|
||||
"__arg1": {"title": "__arg1", "type": "string"},
|
||||
},
|
||||
"required": ["__arg1"],
|
||||
"type": "object",
|
||||
},
|
||||
}
|
||||
# For backwards compatibility
|
||||
__all__ = ["format_tool_to_openai_function"]
|
||||
|
||||
Loading…
Reference in New Issue