Google launched the GENERATE_TEXT Function for BigQuery

And also announced BigQuery ML Models based on Gemini 2.0

Photo by Dorina Perry on Unsplash

Two good new features Google announced for BigQuery: First Gemini 2.0 Flash Exp is available for BIgQUery ML and the GENERATE_TEXT function was launched[1].

BigQuery ML now supports creating remote models based on the gemini-2.0-flash-exp model in Vertex AI. You can set up these models using either SQL queries or BigQuery DataFrames. Google wrote that Gemini 2.0 Flash is now available as an experimental preview release through the Vertex AI Gemini API and Vertex AI Studio. The model introduces new features and enhanced core capabilities[2]:

• Multimodal Live API: This new API helps you create real-time vision and audio streaming applications with tool use.
• Speed and performance: Gemini 2.0 Flash has a significantly improved time to first token (TTFT) over Gemini 1.5 Flash.
• Quality: The model maintains quality comparable to larger models like Gemini 1.5 Pro.
• Improved agentic experiences: Gemini 2.0 delivers improvements to multimodal understanding, coding, complex instruction following, and function calling. These improvements work together to support better agentic experiences.
• New Modalities: Gemini 2.0…