Sambungkan Tool, Aktifkan Agentic RAG

Sekarang Anda memiliki tool kustom yang berfungsi untuk menelusuri manual peralatan menggunakan kemiripan semantik. Pada latihan ini, Anda akan menyambungkan tool tersebut ke sebuah agent agar dapat menjawab pertanyaan berdasarkan isi manual.

Di balik layar, Anda sudah memiliki akses ke:

Variabel bernama vector_store, yang memuat konten manual yang dapat ditelusuri
ApplianceSearchTool untuk melakukan pencarian semantik
Variabel bernama model, yang berisi model bahasa prakonfigurasi untuk agent

Tujuan Anda adalah menghubungkan semuanya agar agent dapat menggunakan tool Anda untuk menjawab pertanyaan layaknya asisten peralatan yang membantu.

Latihan ini merupakan bagian dari kursus

Agen AI dengan Hugging Face smolagents

Instruksi latihan

Instansiasikan ApplianceSearchTool dengan meneruskan vector_store.
Tambahkan tool appliance_tool ke daftar tools saat menginisialisasi CodeAgent.

Latihan interaktif langsung praktik

Cobalah latihan ini dengan melengkapi kode contoh ini.

# 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 dan Jalankan Kode

Latihan ini merupakan bagian dari kursus

Agen AI dengan Hugging Face smolagents

SkillTag.level.advancedSkillTag.label

4.8+

Mulai Kursus Gratis

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: Pengingat RAG Exercise 2: RAG Berurutan: Dari Manual ke Jawaban Exercise 3: Jadi, Apa yang Sebenarnya Terjadi dalam RAG?Exercise 4: Langkah yang Menambahkan Makna Exercise 5: Pengantar Agentic RAG Exercise 6: Bertahan dengan Status: Bangun Alat Pencarian RAG Exercise 7: Sambungkan Tool, Aktifkan Agentic RAG

Latihan Saat Ini

Exercise 8: Bekerja dengan Agen Multi-Langkah Exercise 9: Lacak Langkah Agen, Pantau Aksi Exercise 10: Waktunya Bertanding: Jalankan Agen Lengkap

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!