Connect the Tool, Unlock Agentic RAG

You now have a working custom tool that can search appliance manuals using semantic similarity. In this exercise, you'll connect that tool to an agent so it can answer questions based on manual content.

Behind the scenes, you already have access to:

A variable called vector_store, which holds your searchable manual content
An ApplianceSearchTool to perform semantic search
A variable called model, which contains a preconfigured language model for the agent

Your goal is to wire everything together so the agent can use your tool to answer questions like a helpful appliance assistant.

This exercise is part of the course

AI Agents with Hugging Face smolagents

Exercise instructions

Instantiate the ApplianceSearchTool by passing in the vector_store.
Add your appliance_tool tool to the tools list when initializing the CodeAgent.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Create appliance search tool
appliance_tool = ApplianceSearchTool(____)

# Create AI assistant for appliance help
assistant = CodeAgent(
    tools=[____],
    model=model,
    instructions="Help with appliance questions using manual information. Search multiple times if needed for complete answers.",
    verbosity_level=1,
    max_steps=6
)

result = assistant.run("If the AC isn’t cooling and shows error E1, what should I check and what’s the next step?")
print(result)

Edit and Run Code

This exercise is part of the course

AI Agents with Hugging Face smolagents

AdvancedSkill Level

5.0+

Start Course for Free

Discover what makes code agents special and how they use Python to reason and act. Build your first agent with smolagents, add built-in and community tools for web access, and create custom tools to connect agents with data.

Exercise 1: Introduction to Hugging Face smolagents Exercise 2: Let the Agent Do the Math: Expense Insights Exercise 3: Wait, You Didn't Write Any Functions?Exercise 4: Creating an Agent With Tools Exercise 5: Writing Code Through Prompts: Compound Interest Exercise 6: Let Agents Search the Web Exercise 7: Creating an Agent With Custom Tools Exercise 8: Just Add @tool: Writing a Custom Tool Exercise 9: Check, Please! Giving Agents Access to Data Exercise 10: One Prompt, Many Tools

Transform your traditional RAG pipeline into an agentic system that retrieves information iteratively and reasons across multiple steps. Build stateful tools to support advanced retrieval, guide agents with planning intervals to improve outcomes, and use callbacks to track and customize agent behavior at runtime.

Exercise 1: RAG Refresher Exercise 2: RAG in Order: From Manuals to Answers Exercise 3: So, What’s Actually Happening in RAG?Exercise 4: The Step That Adds Meaning Exercise 5: Introduction to Agentic RAG Exercise 6: Stateful by Design: Build a RAG Search Tool Exercise 7: Connect the Tool, Unlock Agentic RAG

Current Exercise

Exercise 8: Working With Multi-Step Agents Exercise 9: Track Agent Steps, Monitor the Action Exercise 10: Game Time: Run the Full Agent

Tackle complex workflows by orchestrating teams of specialized agents under a coordinating manager. Add memory to retain context across interactions, debug agent behavior using execution traces and reasoning steps, and implement robust validation strategies to ensure high-quality, reliable responses.

Exercise 1: Introduction to Multi-Agent Systems Exercise 2: Divide and Conquer: Creating Specialist Agents Exercise 3: Meet the Team: Agent Coordination Exercise 4: Managing Agent Memory Exercise 5: Don't Forget: Keeping Memory Between Calls Exercise 6: Tracing the Agent’s Code Execution Exercise 7: Agent Final Answer Validation Exercise 8: Say More, Agent: Enforcing Answers Length Exercise 9: Smarter Agents: Validate and Retry Exercise 10: Congratulations!