Google has expanded its Gemini API File Search to support multimodal capabilities, enabling developers to search across text, images, and other file types simultaneously.
The enhancement allows developers to build retrieval-augmented generation (RAG) systems that process mixed content formats within a single search operation. Previously, File Search was limited to text-based queries and documents.
Multimodal support enables more sophisticated use cases, such as searching through documents containing both written content and visual elements like diagrams, charts, or photographs. Developers can now index diverse file types and retrieve relevant results across all formats.
The feature integrates directly into the Gemini API, maintaining Google's minimalist approach to developer tools. This addition addresses growing demand for AI systems that can reason across different data types, particularly in enterprise document analysis and knowledge management applications.
The update reflects broader industry movement toward multimodal AI capabilities, with competitors also expanding their search and retrieval features. Google's implementation aims to simplify how developers incorporate complex document understanding into their applications.
President Trump said Saturday he would appoint an AI czar and create an "AI Force" to oversee artificial intelligence development, offering few details on either initiative despite growing industry warnings about AI risks.
Clinicians are expressing caution over the expanding use of artificial intelligence in healthcare beyond diagnostics and imaging, citing insufficient clinical evidence and performance data to support broader adoption.
Alibaba's Damo Academy released RADAR, a vision-language model designed to identify approximately 150 abdominal conditions from CT scans, including cancers. Testing on nearly 40,000 real-world exams showed the model outperformed most radiologists.
Two viral conversations about AI safety this week highlight the growing difficulty in separating credible information from speculation in discussions about artificial intelligence risks.