text field Archives

AppWizard

May 5, 2025

Google’s AI Mode tipped to gain a ‘Live’ feature similar to Gemini

Google is developing a new feature called "Live for AI Mode," which is expected to enhance user interaction with AI, potentially utilizing Google Lens for a more conversational interface. Recent updates have expanded AI Mode access to all Labs testers in the U.S., introducing visual cards for products and locations. The new feature may include an "End Session" button and a microphone mute option, similar to the existing Gemini Live feature. Since its rollout in April, Google has integrated Lens into AI Mode, allowing users to capture images and ask questions about them. The update aims to provide a more dynamic experience, including a "multisearch" capability that combines images and text. As of May 1, AI Mode has been updated to include a history of previous queries and will soon allow users to access organized information blocks for local establishments, including reviews and operational hours.

Winsage

March 21, 2025

Microsoft readies next Windows 11 feature drop with gaming, emoji, and lock screen updates

Microsoft is enhancing Windows 11 with new features, including: - A dynamic emoji panel button on the Taskbar that appears when typing in a text field. - A reintroduced gamepad keyboard for easier typing with a controller. - Customizable widgets on the lock screen through the Windows Settings app. - A real-time language translation feature for Intel and AMD-powered devices, translating over 44 languages into English during video calls. - A natural language feature in voice access for Snapdragon PCs. - Live captions and real-time translation capabilities for AMD and Intel-powered Copilot+ PCs. - Real-time translation support for Chinese (Simplified) on Snapdragon-powered Copilot+ PCs. - A new Settings homepage for commercial customers with relevant cards for enterprise-managed PCs. - An overview of key PC specifications under Settings > System > About. - Natural Language Commanding in voice access for more fluid command issuance. - Voice access support for commands in Simplified and Traditional Chinese. - An icon in the system tray to enhance the discoverability of the emoji panel. - Adjustments to Task Manager's CPU utilization calculations and a new optional column for backward compatibility. - The ability for web developers to create dynamic and interactive widgets using existing web content. - Extended support for lock screen widgets in the European Economic Area (EEA). - A Gamepad keyboard layout for the touch keyboard for Xbox controller users. These features are currently being tested in the Windows Insider Release Preview Channel, with a broader rollout expected in the coming weeks.

AppWizard

March 3, 2025

Here’s how the Play Store’s new “Ask Play” feature answers your app-related queries

Google is testing a new AI-powered feature on the Play Store called “Ask Play about this app,” which allows users to ask specific questions about apps directly within their listings. This feature includes a text field for custom inquiries and sample questions related to the app. Responses are displayed below the text field, and the sample queries adapt based on previous questions. Currently, it is being rolled out to a select group of users and is available on specific app listings, such as WhatsApp, Facebook, Instagram, Temu, or X.

Tech Optimizer

February 21, 2025

Self-managed multi-tenant vector search with Amazon Aurora PostgreSQL

Organizations are using generative AI and machine learning tools to extract value from unstructured data, employing specialized machine learning models to convert data into vectors for efficient searching and retrieval. Amazon Aurora PostgreSQL-Compatible Edition, with the pgvector extension, allows developers to create a vector store for generative AI applications. Multi-tenant architectures in software-as-a-service (SaaS) applications ensure tenant data isolation to maintain security and privacy. In a multi-tenant scenario, home survey requests are processed, and survey reports are stored in Amazon S3. Embedding models convert these documents into vector embeddings, which are stored in a vector store. There are two approaches to building a vector-based application: a self-managed approach, where developers handle data processing and queries, and a fully-managed option using Amazon Bedrock Knowledge Bases. The self-managed approach involves coding to process data, generate vector embeddings, and store them in Aurora. The architecture includes data ingestion via AWS Lambda, embedding conversion, SQL queries for data retrieval, and response enhancement using a large language model (LLM). Key terminologies include vector embeddings, embedding models, chunking, pgvector, HNSW index, and IVFFlat index. The process of creating a vector store involves configuring the Aurora PostgreSQL database, enabling the pgvector extension, and establishing a schema for the vector store. The vector table includes fields for UUID, vector embeddings, text chunks, metadata, and tenant identification. Data ingestion requires coding to convert data into embeddings and insert them into the database. Retrieval of vector data is crucial for enhancing prompts sent to LLMs, with various distance functions supported for identifying similar vectors. Multi-tenancy is enforced using row-level security in PostgreSQL, ensuring tenant data isolation. The process includes updating query functions to support tenant isolation and setting the current tenant ID for queries.

Tech Optimizer

February 21, 2025

Multi-tenant vector search with Amazon Aurora PostgreSQL and Amazon Bedrock Knowledge Bases

The article discusses the implementation of a multi-tenant vector store using Amazon Aurora PostgreSQL-Compatible Edition and Amazon Bedrock Knowledge Bases. It outlines a scenario where users request home surveys, and surveyors update findings stored in an Amazon S3 bucket. The process involves converting documents into vector embeddings for enhanced natural language queries through the Retrieval Augmented Generation (RAG) technique. Key steps include: 1. Ingesting data from S3 into Amazon Bedrock Knowledge Bases. 2. Using an embeddings model to convert documents into vector embeddings. 3. Storing vector embeddings, data chunks, and metadata in Aurora with pgvector. 4. Submitting natural language queries that are transformed into embeddings for retrieval from the vector store. 5. Forwarding relevant documents to a large language model for response generation. To set up the vector store, prerequisites include access to an Amazon Aurora PostgreSQL-compatible database, Amazon S3 for document storage, and Amazon Bedrock for managing knowledge bases. The article provides SQL commands for creating the necessary schema, vector table, and index in Aurora, as well as instructions for ingesting data and ensuring multi-tenant data isolation through metadata filtering. Best practices for deploying a multi-tenant vector store include optimizing chunk size, evaluating embedding models, and monitoring query performance. The article emphasizes the benefits of fully managed solutions to reduce operational complexity.

AppWizard

December 19, 2024

Android 16 will let apps block AI writing tools

Google has released the second developer preview of Android 16, which includes the Writing Tools API. This API allows applications to opt out of AI-driven text generation. It features two methods in the EditorInfo class: isWritingToolsEnabled(), which indicates if AI writing tools are active (enabled by default), and setWritingToolsEnabled(), which allows apps to prevent AI tools from rewriting user-generated text. Developers can disable these tools in contexts like password or numeric input fields. The API aims to give developers greater control over when to use AI writing tools, particularly in sensitive scenarios. Keyboard app developers are responsible for adhering to the API guidelines, though users may find ways to bypass restrictions.

AppWizard

December 11, 2024

Google Updates Gemini AI Design on Web Interface and Android App

Google has made design modifications to its Gemini AI chatbot, improving user experience on both the web and Android app. The text field interface has been reorganized, moving the Upload Images and Plus icons to the left side, while the microphone icon is now on the far left, creating a cleaner look. The Android app now displays AI model information at the top, indicating the version in use, such as Gemini Advanced 1.5 Pro or Gemini 1.5 Flash for Pixel devices. Additionally, a new Saved Info option in the account menu allows the chatbot to retain user-specific information, redirecting users to a browser window for access.

AppWizard

December 11, 2024

Gemini website tweaks text field, adds model info to Android app

Google is refining the user interface of its Gemini platform, enhancing the web and Android app experiences. The text field on the Gemini website now mirrors the mobile app design, with the 'plus' or "Upload Image" icon repositioned to the far left. Advanced subscribers have access to options like Images, Files, Drive, and Code folder through this menu. The “Ask Gemini” feature follows the upload icon, and the microphone icon has been updated for a polished appearance. The pill-shaped text box has changed from a raised container to a thin outline. The Android app is introducing model identification features, displaying “Gemini Advanced” on the homepage and “1.5 Pro” in chat conversations. A “Saved info” option has also been added to the account menu, directing users to gemini.google.com/saved-info.