LangChain agents overview in Agentic AI

Introduction

LangChain agents help programs think and act by using tools and language models together. They make AI smarter by letting it decide what to do next.

When you want an AI to answer questions by using external tools like calculators or databases.

When you need an AI to perform multiple steps to solve a problem, like booking a flight and checking the weather.

When you want to build a chatbot that can search the internet or access APIs to give better answers.

When you want AI to decide which tool to use based on the question it receives.

When you want to combine language understanding with actions in a flexible way.

Syntax

Agentic AI

from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from langchain.tools import Tool

# Define tools
tools = [Tool(name="Calculator", func=calculator_function, description="Performs math calculations")]

# Initialize language model
llm = OpenAI(temperature=0)

# Create agent
agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)

# Run agent
agent.run("What is 12 times 15?")

The initialize_agent function sets up the agent with tools and a language model.

Agents can use different strategies like 'zero-shot-react-description' to decide actions.

Examples

This example creates an agent that uses a calculator tool to answer math questions.

Agentic AI

agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)
agent.run("Calculate 5 plus 7")

This agent can handle conversations and decide which tool to use based on the question.

Agentic AI

agent = initialize_agent(tools, llm, agent="conversational-react-description", verbose=True)
agent.run("What is the weather in New York?")

Sample Model

This program creates a LangChain agent that uses a calculator tool to answer a math question. It runs the agent to calculate 12 times 15 and prints the answer.

Agentic AI

from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from langchain.tools import Tool
import math

# Define a simple calculator function
def calculator_function(query: str) -> str:
    try:
        # Evaluate math expression safely
        result = str(eval(query, {"__builtins__": None}, {}))
    except Exception:
        result = "Error in calculation"
    return result

# Create a calculator tool
calculator_tool = Tool(name="Calculator", func=calculator_function, description="Performs math calculations")

# Initialize language model
llm = OpenAI(temperature=0)

# Initialize agent with the calculator tool
agent = initialize_agent([calculator_tool], llm, agent="zero-shot-react-description", verbose=False)

# Run agent to calculate 12 times 15
output = agent.run("What is 12 times 15?")
print(output)

Important Notes

Agents combine language models and tools to solve tasks step-by-step.

Choosing the right agent type affects how the AI decides what to do next.

Always test tools separately to ensure they work before adding to agents.

Summary

LangChain agents let AI use tools and language models together.

They help AI decide actions based on questions or tasks.

Agents make AI more flexible and powerful for real-world problems.

Practice

1. What is the main purpose of LangChain agents in AI?

easy

A. To help AI decide which tools to use for a task

B. To store large amounts of data efficiently

C. To train AI models faster using GPUs

D. To create static reports from data

Solution

1. Step 1: Understand LangChain agents' role

   LangChain agents help AI decide actions by choosing tools or language models based on the task.

2. Step 2: Compare options with this role

   Only To help AI decide which tools to use for a task matches this purpose; others describe unrelated tasks.

3. Final Answer:

   To help AI decide which tools to use for a task -> Option A

4. Quick Check:

   Agent purpose = Decide tools [OK]

Hint: Agents decide actions and tools for AI tasks [OK]

Common Mistakes:

• Confusing agents with data storage systems
• Thinking agents speed up training
• Assuming agents create reports

2. Which of the following is the correct way to create a simple LangChain agent in Python?

easy

A. agent = Agent(llm, tools)

B. agent = Agent(llm=llm, tools=tools)

C. agent = Agent.create(llm, tools)

D. agent = create_agent(llm, tools)

Solution

1. Step 1: Recall LangChain agent creation syntax

   LangChain agents are created by calling Agent with named parameters like llm= and tools=.

2. Step 2: Check each option's syntax

   agent = Agent(llm=llm, tools=tools) uses named parameters correctly; others use incorrect or non-existent methods.

3. Final Answer:

   agent = Agent(llm=llm, tools=tools) -> Option B

4. Quick Check:

   Correct syntax uses named parameters [OK]

Hint: Use named parameters llm= and tools= to create agents [OK]

Common Mistakes:

• Omitting parameter names
• Using non-existent create methods
• Confusing function names

3. Given this code snippet, what will be the output?

from langchain.agents import Agent
llm = MockLLM(responses=["Answer 1"])
tools = [Tool(name="search", func=lambda x: "found info")]
agent = Agent(llm=llm, tools=tools)
result = agent.run("Find info about AI")
print(result)

medium

A. Error: Missing tool function

B. "found info"

C. "Answer 1"

D. "Find info about AI"

Solution

1. Step 1: Understand the MockLLM and tools setup

   The MockLLM is set to respond with "Answer 1" regardless of input; tools have a function but agent uses LLM response first.

2. Step 2: Analyze agent.run behavior

   Agent calls LLM which returns "Answer 1"; tools are available but not triggered to override LLM output.

3. Final Answer:

   "Answer 1" -> Option C

4. Quick Check:

   LLM response = "Answer 1" [OK]

Hint: MockLLM returns preset answer, tools don't override by default [OK]

Common Mistakes:

• Assuming tool output replaces LLM output
• Confusing input with output
• Expecting runtime errors without cause

4. What is wrong with this LangChain agent code?

from langchain.agents import Agent
llm = SomeLLM()
tools = [Tool(name="calc", func=calculate)]
agent = Agent(llm, tools)
result = agent.run("Calculate 2+2")
print(result)

medium

A. Tool function 'calculate' is undefined

B. LLM instance is not imported

C. Agent.run() requires extra arguments

D. Agent constructor missing named parameters

Solution

1. Step 1: Check Agent constructor usage

   Agent requires named parameters like llm= and tools=; code uses positional arguments incorrectly.

2. Step 2: Verify other parts

   Assuming 'calculate' is defined and LLM imported, the main error is constructor call.

3. Final Answer:

   Agent constructor missing named parameters -> Option D

4. Quick Check:

   Constructor needs llm= and tools= [OK]

Hint: Always use named parameters when creating Agent [OK]

Common Mistakes:

• Using positional arguments for Agent
• Assuming undefined functions cause error here
• Thinking run() needs extra args

5. You want to build a LangChain agent that uses both a calculator tool and a web search tool. Which approach best ensures the agent chooses the right tool based on the question?

hard

A. Provide both tools and use an agent type that decides tool usage automatically

B. Manually call each tool in sequence and combine results

C. Use only one tool at a time to avoid confusion

D. Train separate agents for each tool and merge outputs later

Solution

1. Step 1: Understand agent tool selection

   LangChain agents can automatically decide which tool to use when given multiple tools and an appropriate agent type.

2. Step 2: Evaluate options for flexibility and automation

   Provide both tools and use an agent type that decides tool usage automatically uses this automatic decision feature; others require manual or less efficient approaches.

3. Final Answer:

   Provide both tools and use an agent type that decides tool usage automatically -> Option A

4. Quick Check:

   Agent auto-selects tools = Provide both tools and use an agent type that decides tool usage automatically [OK]

Hint: Use agent types that pick tools automatically [OK]

Common Mistakes:

• Manually calling tools defeats agent purpose
• Using only one tool limits flexibility
• Training separate agents adds complexity