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.
Anthropic is making Auto Mode the default setting in Claude Code for Pro, Max, and Team plans starting August 14. The company argues the automated safety classifier is more effective at catching dangerous commands than human reviewers.
A study of over 2,500 readers found they cannot distinguish AI-generated short stories from human-written ones. Participants rated the machine-written texts higher—until they learned the truth.
DeepMind has released an open source weather prediction model that produces accurate hurricane forecasts using lower-resolution data, surprising meteorologists with its efficiency gains.
Backflip AI has released an AI model that transforms 3D scans into fully editable, parametric CAD models—a process that traditionally requires hours of manual work. The $30 million-backed startup addresses a critical gap: most factories maintain digital models for less than 1% of their parts.