Hugging Face smolagents로 AI 에이전트 만들기
Adel Nehme
VP of AI Curriculum, DataCamp
from smolagents import CodeAgent, InferenceClientModel agent = CodeAgent( tools=[], model=InferenceClientModel() )agent.run("Calculate the average of the list [23, 45, 67, 89]")
Executing parsed code:
numbers = [23, 45, 67, 89]
average = sum(numbers) / len(numbers)
final_answer(average)
Final answer: 56.0
[Step 1: Duration 4.14 seconds| Input tokens: 1,900 | Output tokens: 109]
56.0
정의한 에이전트는 이미 다음으로 많은 작업을 해결합니다:
하지만 외부 정보가 필요할 수 있습니다:

바로 여기에 도구가 필요합니다!
from smolagents import CodeAgent, InferenceClientModel, WebSearchTool
agent = CodeAgent(
model=InferenceClientModel(),
tools=[WebSearchTool()]
)
agent.run("What's the tallest building in the world right now?")
Executing parsed code:
tallest_building_info = web_search("tallest building in the world 2023")
print(tallest_building_info)
# Search results omitted for brevity...
Executing parsed code:
final_answer("Burj Khalifa, Dubai, 828 meters")
Final answer: Burj Khalifa, Dubai, 828 meters
[Step 2: Duration 2.97 seconds| Input tokens: 5,078 | Output tokens: 153]
Burj Khalifa, Dubai, 828 meters
| 범주 | 도구 |
|---|---|
| 정보 검색 | ApiWebSearchTool, DuckDuckGoSearchTool, GoogleSearchTool, WebSearchTool, WikipediaSearchTool |
| 웹 상호작용 | VisitWebpageTool |
| 코드 실행 | PythonInterpreterTool |
| 사용자 상호작용 | UserInputTool |
| 음성 처리 | SpeechToTextTool |
| 워크플로 제어 | FinalAnswerTool |

from smolagents import load_tool # Load remote tool from Hugging Face model_downloads_tool = load_tool( repo_id="example-repo/hf-model-downloads", trust_remote_code=True ) # Create agent with remote + built-in tools agent = CodeAgent( tools=[model_downloads_tool, WebSearchTool()], model=InferenceClientModel() )agent.run("Find the most downloaded image classification model on Hugging Face")
google/vit-base-patch16-224-in21k
Hugging Face smolagents로 AI 에이전트 만들기