forked from Archives/langchain
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.
286 lines
8.0 KiB
Plaintext
286 lines
8.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4658d71a",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Conversation Agent\n",
|
|
"\n",
|
|
"This notebook walks through using 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",
|
|
"This is accomplished with a specific type of agent (`conversational-react-description`) which expects to be used with a memory component."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "f65308ab",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.agents import Tool\n",
|
|
"from langchain.agents import AgentType\n",
|
|
"from langchain.memory import ConversationBufferMemory\n",
|
|
"from langchain import OpenAI\n",
|
|
"from langchain.utilities import SerpAPIWrapper\n",
|
|
"from langchain.agents import initialize_agent"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "5fb14d6d",
|
|
"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": "dddc34c4",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"memory = ConversationBufferMemory(memory_key=\"chat_history\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "cafe9bc1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"llm=OpenAI(temperature=0)\n",
|
|
"agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "dc70b454",
|
|
"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",
|
|
"AI: 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": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_chain.run(input=\"hi, i am bob\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "3dcf7953",
|
|
"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",
|
|
"AI: Your name is Bob!\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Your name is Bob!'"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_chain.run(input=\"what's my name?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "aa05f566",
|
|
"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: Thai food dinner recipes\u001b[0m\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3m59 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 ...\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
|
|
"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!\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"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!\""
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "c5d8b7ea",
|
|
"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: Who won the World Cup in 1978\u001b[0m\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3mArgentina national football team\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
|
|
"AI: The last letter in your name is \"b\" and the winner of the 1978 World Cup was the Argentina national football team.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The last letter in your name is \"b\" and the winner of the 1978 World Cup was the Argentina national football team.'"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "f608889b",
|
|
"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: Current temperature in Pomfret\u001b[0m\n",
|
|
"Observation: \u001b[36;1m\u001b[1;3mPartly cloudy skies. High around 70F. Winds W at 5 to 10 mph. Humidity41%.\u001b[0m\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
|
|
"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%.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The current temperature in Pomfret is around 70F with partly cloudy skies and winds W at 5 to 10 mph. The humidity is 41%.'"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_chain.run(input=\"whats the current temperature in pomfret?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0084efd6",
|
|
"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"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|