Google AI Studio and the Gemini API have recently introduced a feature called "Real-Time Connection with Google Search," aimed at helping developers enhance the accuracy of AI model responses by integrating real-time data from Google Search.
With this update, the Gemini 1.5 model can access the latest information from Google Search, thereby improving the accuracy and transparency of its answers. Developers can directly access this feature through the "Tools" section of Google AI Studio or enable the "google_search_retrieval" tool in the Gemini API.
The "Real-Time Connection with Google Search" feature is currently available in the free trial version of Google AI Studio, while the pricing for the Gemini API is set at $35 per 1,000 queries with real-time connection. The main advantage of this feature is its ability to reduce false information in model responses and provide users with relevant and up-to-date information. Additionally, the feature supports linking answers with real-time search results, enhancing transparency and directing traffic to the source of information.
Developers can activate the dynamic retrieval feature to use in cases where specific queries require real-time data. This feature predicts when accessing real-time data will improve response quality, allowing developers to control the use of real-time connections based on set thresholds.
In the comparison mode of Google AI Studio, developers can see how real-time connections enhance answer quality. Answers without real-time connections will only reflect information up to the model's knowledge cut-off date, while answers with real-time data will provide the latest information, supporting links, and search suggestions.
The launch of this feature by Google coincides with OpenAI's release of SearchGPT into ChatGPT, which enhances web search capabilities to provide users with timely and accurate answers, combining natural language interaction with the latest data, including information from sports, news, stock quotes, and more.
Additionally, Google Gemini's real-time connection feature will compete with platforms like Perplexity AI and ChatGPT's web search. Recently, the head of Perplexity AI also announced that the platform will soon release new updates. Meanwhile, Meta is developing its own search engine, planning to integrate it into social media platforms like WhatsApp and Instagram to provide real-time information services.
Key Points:
🌐 The new feature "Real-Time Connection with Google Search" aims to improve the accuracy of AI model responses.
💰 The Gemini API pricing is $35 per 1,000 queries, supporting real-time data retrieval.
🔄 Developers can flexibly activate real-time data retrieval based on requirements, enhancing answer quality.