Satu Prompt, Banyak Tool

Anda telah membuat dua tool untuk AgentsCafé:

generate_order_id: menghasilkan ID bertimestamp seperti T5_Latte_20250812_0915
lookup_orders: membaca orders.csv dan mengembalikan daftar minuman untuk meja tersebut

Sekarang mari buat agen yang menggunakan kedua tool tersebut. Jadi, untuk meja mana pun, agen dapat mengambil pesanannya dan menetapkan ID unik untuk setiap minuman.

Catatan: Model, tool, dan impor yang diperlukan sudah didefinisikan untuk Anda. Contoh orders.csv juga telah diunggah.

Latihan ini merupakan bagian dari kursus

Agen AI dengan Hugging Face smolagents

Instruksi latihan

Buat agen pengodean menggunakan tool lookup_orders dan generate_order_id yang telah Anda definisikan sebelumnya.
Tambahkan pandas ke daftar impor yang diotorisasi agar agen dapat membaca CSV.
Gunakan metode .run() milik agen untuk memproses task yang mengambil pesanan untuk sebuah meja dan menetapkan ID.

Latihan interaktif langsung praktik

Cobalah latihan ini dengan melengkapi kode contoh ini.

# Create a code agent with the lookup_orders and generate_order_id tools
agent = CodeAgent(
    tools=[____, ____],
    model=model,
    # Authorize pandas import
    additional_authorized_imports=['____']
)

task = (
    "For table 5, list their current drink orders and generate a unique order ID for each one."
)

# Run the agent passing the task
result = ____
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: Pengantar Hugging Face smolagents Exercise 2: Biarkan Agen Menghitung: Wawasan Pengeluaran Exercise 3: Tunggu, Anda Tidak Menulis Fungsi Apa Pun?Exercise 4: Membuat Agen dengan Tools Exercise 5: Menulis Kode Melalui Prompt: Bunga Majemuk Exercise 6: Biarkan Agent Menelusuri Web Exercise 7: Membuat Agen dengan Alat Kustom Exercise 8: Cukup Tambahkan @tool: Menulis Tool Kustom Exercise 9: Permisi, Tagihannya! Memberi Akses Data kepada Agen Exercise 10: Satu Prompt, Banyak Tool

Latihan Saat Ini

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 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!