Google AI Studio and Gemini API jointly launched the "real-time connection with Google Search" function, which is designed to improve the response accuracy of AI models and allow developers to use real-time data from Google Search to enhance their AI applications. The editor of Downcodes will give you an in-depth understanding of the features, advantages and position of this new feature in the competitive landscape of the AI field.
Google AI Studio and Gemini API recently jointly launched the "real-time connection with Google Search" function, aiming to help developers improve the response accuracy of AI models by integrating real-time data from Google search.
With this update, Gemini 1.5 models can pull the latest information from Google searches, enhancing the accuracy and transparency of answers. Developers can access this feature directly through the "Tools" section of Google AI Studio, or enable the "google_search_retrieval" tool in the Gemini API.
The "live connection to Google Search" feature is currently available in a free trial of Google AI Studio, while Gemini API pricing is set at $35 per 1,000 queries with a live connection. The main benefit of this feature is its ability to reduce false information in model responses and provide users with relevant and up-to-date information. In addition, this feature supports linking answers to real-time search results, increasing transparency and providing traffic direction to information sources.
Developers can activate the dynamic retrieval feature for use when a specific query requires real-time data. This feature predicts when accessing real-time data will improve response quality based on ratings, allowing developers to control the use of real-time connections based on set thresholds.
In Google AI Studio’s comparison mode, developers can see how real-time connectivity improves answer quality. Answers without a live connection will only reflect information as of the model's knowledge deadline, while answers with live data will provide the latest information, supporting links, and search suggestions.
The launch of this Google feature coincides with the release of OpenAI's SearchGPT and ChatGPT, which enhances web search capabilities and can provide users with timely and accurate answers, combining natural language interaction with the latest data, including sports, news, and stock markets. Quotations and other fields of information.
In addition, Google Gemini's real-time connectivity capabilities will compete with platforms such as Perplexity AI and ChatGPT's web search. Recently, the head of Perplexity AI also announced that the platform will be rolling out a new update soon. At the same time, Meta is also developing its own search engine and plans to integrate it into social media platforms such as WhatsApp and Instagram to provide real-time information services.
All in all, Google’s move aims to enhance Gemini’s competitiveness and gain an advantage in the competition with other AI search engines. The introduction of real-time data undoubtedly improves the accuracy and timeliness of information, providing users with a better AI experience. This will further promote the innovation of AI technology in the field of information acquisition and processing.