Gemini in Practice: Real Google Examples · Lesson 2
Search Grounding: Real-Time Data in Responses
Connect Google Search Tool to Gemini 2.0+ to generate current business reports with live data. Understand the difference between search grounding and the new search tool.
Practical exercise
What to do after this lesson
Build an agent that takes a list of companies from a CSV and generates a short report (3 sections: overview, recent news, financial highlights) for each, saving results to separate files.
Task grader
Build an agent that takes a list of companies from a CSV and generates a short report (3 sections: overview, recent news, financial highlights) for each, saving results to separate files.
Ready-to-use prompt
Template for this lesson
Copy and adapt to your context. Text in angle brackets should be replaced.
from google import genai
from google.genai.types import GenerateContentConfig, Tool
client = genai.Client(api_key=GOOGLE_API_KEY)
MODEL_ID = "gemini-2.5-flash"
config = GenerateContentConfig(
system_instruction="You are a company analyst. Write concise reports.",
tools=[Tool(google_search={})],
temperature=0
)
response = client.models.generate_content(
model=MODEL_ID,
config=config,
contents=["Write a brief report on Apple Inc."]
)
print(response.text)