ReAct agent implementation in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the base class for ReAct agents from LangChain.

LangChain

from langchain.agents import [1]

Drag options to blanks, or click blank then click option'

AAgentExecutor

BReActAgent

CTool

DLLMChain

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated classes like AgentExecutor or Tool instead of ReActAgent.

The ReActAgent class is the base for implementing ReAct agents in LangChain.

2fill in blank

medium

Complete the code to create a ReAct agent using the LLM and tools.

LangChain

agent = ReActAgent.from_llm_and_tools(llm, tools, [1]=True)

Drag options to blanks, or click blank then click option'

Averbose

Bsilent

Cdebug

Dinteractive

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'silent' or 'debug' which are not valid parameters here.

The verbose parameter enables detailed output during agent execution.

3fill in blank

hard

Fix the error in the agent execution call to get the final output.

LangChain

result = agent.run([1])

Drag options to blanks, or click blank then click option'

Aquestion

Bquery

Cprompt

Dinput

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a variable named 'input' or 'query' which may not be defined.

The run method expects the input question as a string argument, commonly named question.

4fill in blank

hard

Fill both blanks to define tools and initialize the LLM for the ReAct agent.

LangChain

tools = [[1]]
llm = [2](temperature=0)

Drag options to blanks, or click blank then click option'

ATool(name='search', func=search_func, description='useful for web search')

BOpenAI

CChatOpenAI

DAgentExecutor

Attempts:

3 left

💡 Hint

Common Mistakes

Using AgentExecutor as a tool or using OpenAI instead of ChatOpenAI.

Tools are defined as Tool instances. The LLM used here is ChatOpenAI with temperature set to 0 for deterministic output.

5fill in blank

hard

Fill all three blanks to create and run a ReAct agent with tools and print the output.

LangChain

agent = ReActAgent.from_llm_and_tools([1], [2], verbose=True)
output = agent.run([3])
print(output)

Drag options to blanks, or click blank then click option'

Allm

Btools

Cquestion

Dinput_text

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up variable names or passing undefined variables.

The agent is created with the LLM and tools variables, then run with the question string input.