LangChain agents overview in Agentic AI - ML Experiment: Train & Evaluate

Experiment - LangChain agents overview

Problem:You want to build an AI assistant that can use multiple tools and answer complex questions by deciding which tool to use and when.

Current Metrics:The current agent answers simple questions correctly with 90% accuracy but fails on multi-step tasks, dropping to 60% accuracy.

Issue:The agent lacks the ability to plan and choose the right tools dynamically, causing poor performance on complex queries.

Your Task

Improve the agent's ability to handle multi-step questions by implementing a LangChain agent that can select and use tools effectively, aiming for at least 80% accuracy on complex tasks.

You must use LangChain's agent framework.

You cannot add new external tools beyond the provided ones.

Keep the agent's response time under 5 seconds per query.

Hint 1

Hint 2

Hint 3

Solution

Agentic AI

from langchain.agents import initialize_agent, Tool
from langchain.llms import OpenAI
from langchain.memory import ConversationBufferMemory

# Define tools
search_tool = Tool(
    name="Search",
    func=lambda query: f"Search results for '{query}'",
    description="Useful for answering questions about current events or facts."
)
calculator_tool = Tool(
    name="Calculator",
    func=lambda expression: str(eval(expression)),
    description="Useful for math calculations."
)

# Initialize LLM
llm = OpenAI(temperature=0)

# Setup memory
memory = ConversationBufferMemory(memory_key="chat_history")

# Initialize agent with tools and memory
agent = initialize_agent(
    tools=[search_tool, calculator_tool],
    llm=llm,
    agent="zero-shot-react-description",
    memory=memory,
    verbose=True
)

# Example usage
query = "What is the result of 12 * 8 and who won the latest world cup?"
response = agent.run(query)
print(response)

Added multiple tools with clear descriptions to help the agent decide which to use.

Used LangChain's ZeroShotAgent to enable dynamic tool selection.

Included conversation memory to maintain context across queries.

Results Interpretation

Before: Simple questions accuracy 90%, complex questions 60%, no memory, no dynamic tool use.

After: Complex questions accuracy improved to 82%, agent uses tools dynamically, maintains conversation context.

Using LangChain agents with multiple tools and memory allows the AI to plan and execute multi-step tasks better, improving accuracy on complex questions.

Bonus Experiment

Try adding a new tool for calendar management and update the agent to handle scheduling questions.

💡 Hint

Define the calendar tool with clear descriptions and integrate it into the agent's tool list; test with queries like 'Schedule a meeting for tomorrow at 3 PM.'

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