All news with #amazon bedrock tag

⚡ Amazon Bedrock now supports synchronous inference for TwelveLabs Marengo Embed 2.7, delivering low-latency text and image embeddings directly in API responses. Previously optimized for asynchronous processing of large video, audio, and image files, Marengo 2.7’s new mode enables responsive search and retrieval features—such as instant natural-language video search and image similarity discovery—while retaining advanced video understanding via asynchronous workflows.

🔐 AWS introduced three new IAM condition keys that let administrators govern API keys for Amazon Bedrock. The keys control which services can be issued service-specific credentials, the maximum allowable age of long-term Bedrock API keys at creation, and whether requests use short-term or long-term bearer tokens. These controls are available in all AWS Regions and are documented in the IAM and Bedrock User Guides.

🔁 Anthropic's Claude Sonnet 4 is now available with Global cross‑Region inference in Amazon Bedrock, allowing inference requests to be routed to any supported commercial AWS Region for processing. The Global profile helps optimize compute resources and distribute traffic to increase model throughput. It supports both on‑demand and batch inference and is intended for use cases that do not require geography‑specific routing.

🚀 Amazon announced the general availability of Amazon Bedrock in the Asia Pacific Jakarta region, enabling customers to build and scale generative AI applications closer to end users. The fully managed service exposes a selection of high-performing foundation models via a single API and includes capabilities such as Guardrails and Model customization. These features are designed to help organizations incorporate security, privacy, and responsible AI into production workflows while accelerating development and deployment.

🧠 Amazon Web Services announced integration of Amazon Neptune with Zep, an open-source memory server for LLM applications, enabling persistent long-term memory and contextual history. Developers can use Neptune Database or Neptune Analytics as the graph store and Amazon OpenSearch as the text-search layer within Zep’s memory system. The integration enables graph-powered retrieval, multi-hop reasoning, and hybrid search across graph, vector, and keyword modalities, simplifying the creation of personalized, context-aware LLM agents.

⚡Amazon Bedrock updated prompt caching for Anthropic’s Claude models—Claude 3.5 Haiku, Claude 3.7, and Claude 4—to simplify cache management. Developers now set a single cache breakpoint at the end of a request and the system automatically reads the longest previously cached prefix, removing manual segment selection and reducing integration complexity. By excluding cache read tokens from TPM quotas, this change can free up token capacity and lower costs for multi-turn workflows. The capability is available today in all regions offering these Claude models; enable caching in your Bedrock model invocations and refer to the Bedrock Developer Guide for details.

🔍 Amazon Web Services announced general availability of Bring Your Own Knowledge Graph (BYOKG) support for Retrieval-Augmented Generation (RAG) using the open-source GraphRAG Toolkit. Developers can now connect domain-specific graphs stored in Amazon Neptune (Database or Analytics) directly to LLM workflows, combining graph queries with vector search. This reduces hallucinations and improves multi-hop and temporal reasoning, easing operationalization of graph-aware generative AI.

📄 Amazon Web Services' Bedrock Data Automation now supports five additional document languages — Portuguese, French, Italian, Spanish, and German — expanding multilingual document processing beyond English. Customers can build blueprints, prompts, and instructions in these languages using BDA Custom Output, while BDA Standard Output will produce summaries and figure captions in the detected document language. This update is generally available across multiple AWS commercial and GovCloud regions and aims to accelerate multilingual document workflows for intelligent document processing and multimodal automation.

🚀 Amazon Bedrock Data Automation (BDA) is now generally available in the AWS GovCloud (US-West) Region. BDA automates extraction of actionable insights from unstructured multimodal content—documents, images, video, and audio—helping developers accelerate GenAI-based applications like intelligent document processing and media analysis. It can run standalone or as a parser in Amazon Knowledge Bases RAG workflows and is now offered in eight AWS Regions.

🧮 The Count Tokens API is now available in Amazon Bedrock, enabling users to determine token counts for a prompt or input prior to performing inference. Anthropic’s Claude models are supported at launch and the feature is available in all regions where those models run. This improves cost projection, gives more control over token limits, and reduces the risk of unexpected throttling. It also helps ensure inputs fit within a model's context length for more efficient prompt optimization.

🔓 AWS has made two OpenAI models with open weights — gpt-oss-120b and gpt-oss-20b — automatically available to all Amazon Bedrock users as of August 5, 2025. Users can access them immediately via the Amazon Bedrock console playground or the unified Bedrock API in supported regions. Administrators retain full control and can restrict usage with AWS IAM policies and Service Control Policies.

📹 TwelveLabs Pegasus 1.2 is now available in US East (N. Virginia) and Asia Pacific (Seoul) through Amazon Bedrock. The video-first language model is optimized for long-form content and combines visual, audio, and textual signals to deliver advanced video-to-text generation and temporal understanding. Regional availability reduces latency and simplifies architecture for enterprise video-intelligence applications. To begin, request model access via the Amazon Bedrock console.

🚀 Amazon Bedrock now supports Batch inference for Anthropic Claude Sonnet 4 and OpenAI GPT-OSS (120B, 20B), enabling asynchronous processing of large workloads at approximately 50% of on-demand inference cost. The update targets bulk scenarios such as document analysis, large-scale summarization, content generation, and structured data extraction, and is optimized to deliver higher overall batch throughput on these newer models. Batch progress and workload metrics — including pending and processed records, tokens per minute, and Claude-specific pending tokens — are exposed at the AWS account level via Amazon CloudWatch.

🧠 Amazon Neptune now integrates with Cognee to provide graph-native memory for agentic generative AI applications. The integration enables developers to use Amazon Neptune Analytics as the persistent graph and vector store behind Cognee’s memory layer, supporting large-scale memory graphs, long-term memory, and multi-hop reasoning. Hybrid retrieval across graph, vector, and keyword modalities helps agents deliver more personalized, cost-efficient, and context-aware experiences; documentation and a sample notebook are available to accelerate adoption.