Documentation is missing for Search Grounding with DynamicRetrievalConfig in the new SDK. #686
Description
Description of the bug:
I've been checking the docs for the new SDK, and in the Search Grounding section, I saw this:
Before
import google.generativeai as genai
model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content(
contents="what is the Google stock price?",
tools='google_search_retrieval'
)
After
from google import genai
from google.genai import types
client = genai.Client()
response = client.models.generate_content(
model='gemini-2.0-flash',
contents='What is the Google stock price?',
config=types.GenerateContentConfig(
tools=[
types.Tool(
google_search=types.GoogleSearch()
)
]
)
)
However, the example does not explain how to use dynamic retrieval (DynamicRetrievalConfig).
I found this example in the yet-to-be-updated Gemini API Docs, but it clearly follows the old SDK structure.
from google import genai
from google.genai import types
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content(
model='gemini-2.0-flash',
contents="Who won Wimbledon this year?",
config=types.GenerateContentConfig(
tools=[types.Tool(
google_search=types.GoogleSearchRetrieval(
dynamic_retrieval_config=types.DynamicRetrievalConfig(
dynamic_threshold=0.6))
)]
)
)
print(response)
Is it possible to include an example of how to use DynamicRetrievalConfig within the new SDK?
Actual vs expected behavior:
No response
Any other information you'd like to share?
No response