All news with #rag security tag

🔍 The article announces a preview integration between Gemini and Google Cloud’s borderless Lakehouse, enabling agents and users to query and reason over distributed enterprise data without moving it. It highlights new GA features — cross-cloud interconnect, Iceberg V3 support, read-write interoperability, AlloyDB federation, and partner integrations — to scale petabyte reasoning, reduce latency, and preserve security. The piece emphasizes improved metadata, caching, and zero-copy integrations to accelerate AI adoption.

🔍 This article explains how AlloyDB AI streamlines hybrid search for modern AI and RAG applications by combining vector search and full-text search into a single SQL function using Reciprocal Rank Fusion (RRF). It highlights new FTS capabilities including the RUM extension for positional indexing and the BM25 index for industry-standard ranking. The post also describes an external search Foreign Data Wrapper (FDW) to integrate Elasticsearch, OpenSearch, and Solr while maintaining a unified SQL interface.

🧭 Cloudflare’s AI Search is now generally available, combining Workers AI, Vectorize, R2, and Browser Run into a managed index and retrieval pipeline. The release adds native image embeddings, OCR for PDFs, and support for larger files, while introducing billing starting November 1, 2026 alongside a continued free tier. The service preserves both textual captions and pixel embeddings for richer multimodal retrieval and uses Matryoshka Representation Learning to keep embeddings efficient.

🔗 AWS announced native Salesforce and Zendesk data source connectors for Amazon Bedrock Managed Knowledge Base, enabling direct synchronization of Salesforce knowledge articles and Zendesk help center articles and community posts. The connectors remove the need for custom ingestion pipelines by handling crawling, metadata extraction, and incremental sync using instance credentials. This streamlines building RAG-based AI agents and assistants grounded in up-to-date support and product knowledge.

🔎 Lucius AI, a tender-intelligence startup covering five continents, consolidated its relational catalog, audit logs, and vector embeddings into AlloyDB for PostgreSQL and automated routine operations via the Model Context Protocol (MCP). By migrating semantic search to a ScaNN index, query latency fell from 1.14s to 24ms, a 47x improvement. The platform ingests notices from multiple procurement sources and runs across two production regions with strict least-privilege controls.

🚀 Amazon OpenSearch Serverless is now available within v0 by Vercel, enabling rapid creation of full-stack search and AI applications using natural language prompts. The integration provisions and indexes data into OpenSearch Serverless collections automatically, removes infrastructure management, and supports full-text and vector search for RAG workloads. Developers can provision resources in new or existing AWS accounts across multiple global regions via the v0 interface.

🔗 AWS has introduced a Confluence Data Center data source connector for Amazon Bedrock Managed Knowledge Base, enabling direct ingestion of self-hosted Confluence blogs and pages. The connector automates crawling, metadata extraction, and incremental sync after you provide instance credentials. Filters let you scope crawls to specific spaces or content types to keep knowledge bases focused and cost-efficient. This simplifies building internal AI assistants grounded in Confluence-hosted documentation.

📘 KDDI developed Buffmee, a consumer-facing Retrieval-Augmented Generation (RAG) app, to provide grounded, trustworthy AI-assisted learning across books, magazines, and web media. Facing latency and hallucination challenges, KDDI worked with KDDI iret and Google Cloud teams to implement automated evaluation using Gemini Enterprise, BigQuery Agent Analytics, and the Agent Development Kit (ADK). These optimizations reduced response latency by 38% and improved TTFT by nearly 18%, while boosting groundedness by 25% through systematic testing and prompt modularization. The result is a faster, more reliable experience that preserves content trust and compliance.

🔐 AWS announces user-managed (3LO) setup for SharePoint, OneDrive, and Confluence in Amazon Bedrock Managed Knowledge Base. This replaces the prior need to generate 2LO service credentials on the third-party side and lets users authenticate with their existing accounts to complete setup in minutes. The change reduces reliance on IT admins for credential creation and accelerates prototyping of AI assistants grounded in organizational docs. The existing service-account option remains available for enterprise production use.

🔗 AWS introduces a ServiceNow data source connector for Amazon Bedrock Managed Knowledge Base, enabling direct ingestion of knowledge articles and service catalog items. The connector handles crawling, metadata extraction, file attachments, and incremental sync after you provide ServiceNow credentials. You can scope crawls by knowledge base, article category, or service catalog using sys ID inclusion lists to ingest only relevant content. This simplifies powering AI assistants and support agents with up-to-date ServiceNow institutional knowledge.

🔁 Amazon Web Services now offers automatic sync scheduling for Amazon Bedrock Managed Knowledge Base, a fully managed RAG service that removes the need to manage vector databases or custom pipelines. You can configure daily, weekly, or monthly syncs for native connectors to keep knowledge bases current. This replaces manual syncs and custom scheduling solutions, reducing operational overhead and ensuring AI agents retrieve up-to-date enterprise information.

🔎 This post—third in a four-part series—explains how context engineering lowers operating costs and improves agent quality by controlling what enters an agent’s context window each turn. It describes Foundry features like Foundry IQ, Toolboxes, Skills, and Memory that reduce redundant tokens, improve retrieval relevance, and make procedural guidance reusable. The piece emphasizes continuous practice and governance to let agents learn and get cheaper over time.

🔒 Microsoft describes attacks targeting AI infrastructure components such as gateways, retrieval platforms, orchestration services, and container runtimes that centralize credentials and execution privileges. Observed intrusions against LiteLLM, RAGFlow, and Kestra aimed to harvest secrets, persist on hosts, and monetize compute. The advisory emphasizes inventorying exposed AI surfaces, restricting administrative access, and monitoring gateway-originated execution and secret access to mitigate risk.

🗂️ Box and Google Cloud are integrating Gemini Multimodal Embeddings 2 into Box's Agentic Platform to extend RAG beyond text and enable unified search and reasoning across documents, images, tables, and charts. This integration preserves spatial and visual structure, supports crossmodal retrieval, and bridges heterogeneous formats like .docx, .xlsx, .pdf, and .pptx. The combined system targets use cases in finance, healthcare, and enterprise auditing by enabling layout-aware embeddings, cross-file synthesis, and visual-to-text auditing.

🔔 Amazon announced general availability of Amazon Nova Multimodal Embeddings in AWS GovCloud (US-West). The unified embedding model supports text, documents, images, video, and audio through a single model to enable cross-modal retrieval and agentic RAG. It accepts up to 8K tokens and video/audio segments up to 30 seconds, with synchronous and asynchronous API options for latency-sensitive and bulk workloads.

🟦 Amazon S3 Vectors is now available in the AWS European Sovereign Cloud (Germany) Region. Amazon S3 Vectors is purpose-built vector storage for AI agents, inference, Retrieval Augmented Generation (RAG), and semantic search at billion-vector scale. It offers the elasticity, durability, and availability of Amazon S3 with dedicated APIs to store, access, and query vectors without provisioning infrastructure.

🔍 BigQuery announced GA for Autonomous Embedding Generation and AI.SEARCH(), plus a public preview of Hybrid Search to simplify retrieval and analytics over unstructured data. It automates embedding creation (including images), offers large single-query performance gains, and combines semantic and lexical techniques for more precise results. These features integrate into a broader end-to-end document analytics workflow in BigQuery.

🧭 AlloyDB introduces native AI Functions to solve tokenization issues for logographical languages like Chinese, Japanese, and Korean. By calling Gemini models from SQL via ai.generate(), developers can perform in-database segmentation, stop-word removal, and embedding generation without ETL pipelines or external services. The approach uses stored-procedure batching, generated columns for search vectors and embeddings, and RUM plus ScaNN indexes to enable fast hybrid lexical and semantic search.

🔔 Amazon S3 Vectors is now available in AWS GovCloud (US-East) and AWS GovCloud (US-West). The service offers purpose-built vector storage for AI agents, inference, Retrieval Augmented Generation (RAG), and semantic search at billion-vector scale. S3 Vectors provides the elasticity, durability, and availability of Amazon S3 with dedicated APIs to store, access, and query vectors without provisioning infrastructure. Check AWS Regions and endpoints for the full availability list.

🚀 Amazon RDS for Oracle now supports Oracle Database 26ai, Oracle's Long Term Support release, with integration to Amazon Bedrock providing access to foundation models such as Anthropic Claude, Amazon Nova, and Meta Llama. Oracle Database 26ai enables Select AI for generating and running SQL from natural language prompts and supports in-database RAG via Oracle AI Vector Search, avoiding the need for a separate vector store. The release also offers JSON Relational Duality Views and SQL Property Graphs and is available in Enterprise Edition across commercial and GovCloud regions.