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.
If we compare it to the standard ReAct agent, the main difference is the prompt. We want it to be much more conversational.
OPENAI_API_KEY = "..."
from langchain.agents import AgentType, Tool, initialize_agent
from langchain.llms import OpenAI
from langchain.memory import ConversationBufferMemory
from langchain.utilities import SerpAPIWrapper
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",
),
]
llm = OpenAI(temperature=0)
Using LCEL
We will first show how to create this agent using LCEL
from langchain import hub
from langchain.agents.format_scratchpad import format_log_to_str
from langchain.agents.output_parsers import ReActSingleInputOutputParser
from langchain.tools.render import render_text_description
prompt = hub.pull("hwchase17/react-chat")
prompt = prompt.partial(
tools=render_text_description(tools),
tool_names=", ".join([t.name for t in tools]),
)
llm_with_stop = llm.bind(stop=["\nObservation"])
agent = (
{
"input": lambda x: x["input"],
"agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
"chat_history": lambda x: x["chat_history"],
}
| prompt
| llm_with_stop
| ReActSingleInputOutputParser()
)
from langchain.agents import AgentExecutor
memory = ConversationBufferMemory(memory_key="chat_history")
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)
agent_executor.invoke({"input": "hi, i am bob"})["output"]
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? No
Final Answer: 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?'
agent_executor.invoke({"input": "whats my name?"})["output"]
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? No
Final Answer: Your name is Bob.
> Finished chain.
'Your name is Bob.'
agent_executor.invoke({"input": "what are some movies showing 9/21/2023?"})["output"]
> Entering new AgentExecutor chain...
Thought: Do I need to use a tool? Yes
Action: Current Search
Action Input: Movies showing 9/21/2023['September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...'] Do I need to use a tool? No
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.
> Finished chain.
'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.'
Use the off-the-shelf agent
We can also create this agent using the off-the-shelf agent class
agent_executor = initialize_agent(
tools,
llm,
agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,
verbose=True,
memory=memory,
)
Use a chat model
We can also use a chat model here. The main difference here is in the prompts used.
from langchain import hub
from langchain.chat_models import ChatOpenAI
prompt = hub.pull("hwchase17/react-chat-json")
chat_model = ChatOpenAI(temperature=0, model="gpt-4")
prompt = prompt.partial(
tools=render_text_description(tools),
tool_names=", ".join([t.name for t in tools]),
)
chat_model_with_stop = chat_model.bind(stop=["\nObservation"])
from langchain.agents.format_scratchpad import format_log_to_messages
from langchain.agents.output_parsers import JSONAgentOutputParser
# We need some extra steering, or the chat model forgets how to respond sometimes
TEMPLATE_TOOL_RESPONSE = """TOOL RESPONSE:
---------------------
{observation}
USER'S INPUT
--------------------
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!"""
agent = (
{
"input": lambda x: x["input"],
"agent_scratchpad": lambda x: format_log_to_messages(
x["intermediate_steps"], template_tool_response=TEMPLATE_TOOL_RESPONSE
),
"chat_history": lambda x: x["chat_history"],
}
| prompt
| chat_model_with_stop
| JSONAgentOutputParser()
)
from langchain.agents import AgentExecutor
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)
agent_executor.invoke({"input": "hi, i am bob"})["output"]
> Entering new AgentExecutor chain...
```json
{
"action": "Final Answer",
"action_input": "Hello Bob, how can I assist you today?"
}
```
> Finished chain.
'Hello Bob, how can I assist you today?'
agent_executor.invoke({"input": "whats my name?"})["output"]
> Entering new AgentExecutor chain...
```json
{
"action": "Final Answer",
"action_input": "Your name is Bob."
}
```
> Finished chain.
'Your name is Bob.'
agent_executor.invoke({"input": "what are some movies showing 9/21/2023?"})["output"]
> Entering new AgentExecutor chain...
```json
{
"action": "Current Search",
"action_input": "movies showing on 9/21/2023"
}
```['September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...']```json
{
"action": "Final Answer",
"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'."
}
```
> Finished chain.
"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'."
We can also initialize the agent executor with a predefined agent type
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
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,
)