Google is adding a new feature to the Gemini application programming interface (API) and AI Studio to help developers ground the responses generated by artificial intelligence. Announced on Thursday, the feature dubbed Grounding with Google Search will allow developers to check the AI-generated responses against similar information available on the Internet. This way developers will be able to further fine-tune their AI apps and offer their users more accurate and up-to-date information. Google highlighted that such grounding methods are important for prompts that generate real-time information from the web.

Google Releases ‘Grounding With Google Search’ Feature

Google AI for Developers support page detailed the new feature which will be available on both the Gemini API as well as the Google AI Studio. Both of these tools are largely used by developers who are building mobile and desktop apps with AI capabilities.

However, generating responses from AI models can often result in hallucinations, which can negatively impact the credibility of the apps. The problem can be even more significant when the app delves into topics of current affairs, where the latest information from the web is required. While developers can manually fine-tune the AI model, without a guiding dataset, errors can still exist.

To solve this, Google is offering a new way to verify the output generated by AI. Known as grounding, this process connects an AI model to verifiable sources of information. Such sources contain high-quality information and add more context to the information. Some examples of these sources include documents, images, local databases, and the Internet.

Grounding with Google Search uses the last source to find verifiable information. Developers can now use top results from Google Search to compare the information returned by the Gemini AI models. The Mountain View-based tech giant claims that this exercise will improve the “accuracy, reliability, and usefulness of AI outputs.”

The method also helps AI models surpass their knowledge cut-off date by sourcing the information directly from the grounding source. So, in this case, Gemini models can get the latest information using the Search algorithm’s output.

Google also shared an example of the difference in outputs that were grounded vs those which were not grounded. An ungrounded response to the query “Who won the Super Bowl this year?” was “The Kansas City Chiefs won Super Bowl LVII this year (2023).”

However, after the Grounding with Google Search feature was used, the refined response was, “The Kansas City Chiefs won Super Bowl LVIII this year, defeating the San Francisco 49ers in overtime with a score of 25 to 22.” Notably, the feature only supports text-based outputs and cannot process multimodal responses.

Elon Musk’s‘s xAI launched an application programming interface (API) for Grok on Monday. The billionaire entrepreneur promised to turn the native artificial intelligence (AI) chatbot developed by xAI into an API in August, and now, users can access and use it. The API key can be generated using the xAI console and users can further customise how to use it. Notably, the pricing for input and output tokens have been kept higher than competitors. Currently, only one AI model is available to use via the API.

xAI API Launched

In a post on X (formerly known as Twitter), Musk announced that the API version of the AI model is now live for all users. An API is essentially a set of rules that allow different systems to communicate with each other. The tool is useful for developers who can then build apps and platforms by using data and other information from APIs.

In this particular case, the Grok API can allow developers to create various kinds of chatbot-style apps (or integrate the chatbot capability within an app) which are all powered by the Grok AI models.

Currently, only one large language model (LLM) dubbed “grok-beta” is available via the API. Notably, no details around the AI model is available. It is also not certain if it is a distilled model derived from the recently released Grok-2 or not. The AI model only supports text generation.

The xAI API costs $5 (roughly Rs. 420) per million input tokens and $15 (roughly Rs. 1261) per million output tokens. Notably, one million tokens is approximately 7,50,000 words. Notably, the pricing is kept on the higher end compared to rivals such as OpenAI’s ChatGPT and Google’s Gemini. Those interested in trying out the new xAI API can do so via the xAI Console.

The API supports function calling which is essential for any AI model-based API. Function calling allows users to make clear requests to the system and the interface fetches the required data. In xAI’s case, the API can connect with Grok AI model which is an Internet-enabled chatbot, and find responses to specific prompts and queries.