Google has introduced LangExtract, an open-source Python library designed to help developers extract structured information from unstructured text using large language models such as the Gemini models. The library simplifies the process of converting free-form text into structured data, offering features like controlled generation, text chunking, parallel processing, and integration with various LLMs.
Google is integrating Gemini Gems into Workspace apps like Docs, Sheets, and Gmail, allowing users to access customizable AI chatbots directly within these applications.
This post explores how developers can leverage Gemini 2.5 to build sophisticated robotics applications, focusing on semantic scene understanding, spatial reasoning with code generation, and interactive robotics applications using the Live API. It also highlights safety measures and current applications by trusted testers.
Google today announced that the SDK for its Gemini models will natively support the Model Context Protocol from Anthropic. This move aims to simplify the connection between AI agents and data sources, aligning with the growing popularity of MCP and complementing Google's own Agent2Agent protocol. The company also plans to ease deployment of MCP servers and hosted tools for AI agents.
Google's AI function brings Gemini-powered language models right into your spreadsheet cells without any add-ons. With it, you can generate fresh text, summarize blocks of data, categorize entries, or even guess sentiments—all by typing a simple formula.
The article provides examples such as:
- *sentiment analysis* ```=AI("Is this customer feedback positive, negative, or neutral?", A2)```
- *data categorization* `=AI("Classify this expense as Travel, Office, or Other", D3)`
- *simple calculations* `=AI("Add the numbers in these cells", A1:A5)`
The article provides examples such as:
- *sentiment analysis* ```=AI("Is this customer feedback positive, negative, or neutral?", A2)```
- *data categorization* `=AI("Classify this expense as Travel, Office, or Other", D3)`
- *simple calculations* `=AI("Add the numbers in these cells", A1:A5)`
Google will host a separate event, 'The Android Show: I/O Edition,' on May 13th to discuss Android updates, a week before Google I/O. This suggests Google I/O will focus more on Gemini and other AI efforts. Android will still be present at I/O, but it's no longer the primary focus.
Google's Gemini 2.5 Flash model is a new, faster, and more cost-effective model with adjustable 'thinking' capabilities. The article details how to use it with llm-gemini, explores pricing differences compared to Gemini 2.0 Flash, and shares example SVG outputs.
The Gemini API documentation provides comprehensive information about Google's Gemini models and their capabilities. It includes guides on generating content with Gemini models, native image generation, long context exploration, and generating structured outputs. The documentation offers examples in Python, Node.js, and REST for using the Gemini API, covering various applications like text and image generation, and integrating Gemini in Google AI Studio.
Google is renaming 'Gemini Extensions' to 'apps' in the latest beta version of the Google app on Android. The change includes updates to the account menu and the full page for enabling and disabling each tool.
