What is smolagents?
Hugging Face's lightweight framework for building AI agents. Minimal, code-first approach to agent development.
Searching Apple App Store with smolagents
This integration lets your smolagents agent search Apple App Store in real time via the Scavio API. The agent gets back structured JSON with app listing URLs, listing titles, SERP snippets (rating, category, price as text) -- ready for reasoning and decision-making.
Setup
pip install smolagents requestsCode Example
Here is a complete smolagents agent that searches Apple App Store using Scavio:
from smolagents import tool, CodeAgent, HfApiModel
import json
import os
import requests
# Scavio has no App Store endpoint. This searches apps.apple.com listing pages through Google - ratings and prices appear in the snippet text, not as structured fields.
@tool
def scavio_search(query: str) -> str:
"""Query Apple App Store through the Scavio API (POST /api/v2/google).
Args:
query: What to look for.
"""
response = requests.post(
"https://api.scavio.dev/api/v2/google",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"query": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
agent = CodeAgent(tools=[scavio_search], model=HfApiModel())
result = agent.run("site:apps.apple.com best productivity app")
print(result)Full Working Example
A production-ready example with error handling:
from smolagents import tool, CodeAgent, HfApiModel
import json
import os
import requests
# Scavio has no App Store endpoint. This searches apps.apple.com listing pages through Google - ratings and prices appear in the snippet text, not as structured fields.
@tool
def scavio_search(query: str) -> str:
"""Query Apple App Store through the Scavio API (POST /api/v2/google).
Args:
query: What to look for.
"""
response = requests.post(
"https://api.scavio.dev/api/v2/google",
headers={
"Authorization": "Bearer " + os.environ["SCAVIO_API_KEY"],
"Content-Type": "application/json",
},
json={"query": query},
timeout=60,
)
response.raise_for_status()
return json.dumps(response.json())
agent = CodeAgent(tools=[scavio_search], model=HfApiModel())
result = agent.run("site:apps.apple.com best productivity app")
print(result)Pricing
Scavio offers a free tier with 50 credits on signup (1 credit per search). No credit card required. This is enough to build and test your smolagents integration. Paid plans start at $30/month for higher volumes.