What is Semantic Kernel?
Microsoft's SDK for integrating LLMs into applications. Supports plugins, planners, and memory for building AI agents.
Searching Google Play Store with Semantic Kernel
This integration lets your Semantic Kernel agent search Google Play Store in real time via the Scavio API. The agent gets back structured JSON with app listing URLs, listing titles, SERP snippets (rating, reviews, installs as text) -- ready for reasoning and decision-making.
Setup
Bash
pip install semantic-kernel requestsCode Example
Here is a complete Semantic Kernel agent that searches Google Play Store using Scavio:
Text
import semantic_kernel as sk
from semantic_kernel.functions import kernel_function
import json
import os
import requests
# Scavio has no Play Store endpoint. This searches play.google.com listing pages through Google - ratings and install counts appear in the snippet text, not as structured fields.
class ScavioPlugin:
@kernel_function(description="Query Google Play Store using Scavio")
def search(self, query: str) -> str:
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())
kernel = sk.Kernel()
kernel.add_plugin(ScavioPlugin(), "scavio")Full Working Example
A production-ready example with error handling:
Text
import semantic_kernel as sk
from semantic_kernel.functions import kernel_function
import json
import os
import requests
# Scavio has no Play Store endpoint. This searches play.google.com listing pages through Google - ratings and install counts appear in the snippet text, not as structured fields.
class ScavioPlugin:
@kernel_function(description="Query Google Play Store using Scavio")
def search(self, query: str) -> str:
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())
kernel = sk.Kernel()
kernel.add_plugin(ScavioPlugin(), "scavio")
result = await kernel.invoke("scavio", "search", query="site:play.google.com habit tracker")
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 Semantic Kernel integration. Paid plans start at $30/month for higher volumes.