RAG

ScaleDown has released Summarize, an abstractive summarization model with a 1M-token context window, listed on OpenRouter on October 13, 2026. OpenRouter shows $0.04 per 1M input tokens (20% off the $0.05 list price) and $0 per 1M output tokens. Parameter count and benchmark scores have not been disclosed.

AWS published a reference architecture showing how to combine structured data extraction with Bedrock AgentCore, dual Claude models, and Amazon Quick to answer portfolio-wide questions that standard RAG systems get wrong. The design uses Claude Sonnet 4.6 for extraction and Claude Haiku 4.5 for independent verification, with Amazon Textract as a deterministic tiebreaker.

Amazon Bedrock Knowledge Bases now offers TwelveLabs Marengo Embed 3.0 as a managed embedding model, letting teams run natural language queries like 'show me the penalty kick' directly against video, audio, and image archives. The service is generally available in two AWS Regions, with pricing tied to standard Bedrock model invocation rates.

AWS has published a reference architecture showing how to build multi-tenant agentic document chat applications using Amazon Bedrock Managed Knowledge Base. The design handles per-user document isolation, asynchronous ingestion up to 50 MB, and agentic multi-hop retrieval with citations, offloading infrastructure work from development teams.

Mistral has released Agentic Search, a retrieval layer that lets AI models navigate, read, and verify information across complex documents instead of relying on single-pass chunk retrieval. The company claims accuracy improvements from 26.7% to 86% on FinanceBench and up to 39.6% lower p90 latency.

Google Workspace ships with Gemini's access to Gmail, Docs, Calendar, Chat, Drive, and Meet turned on by default, using real-time retrieval-augmented generation rather than stored training data. Admins can disable these 'Workspace Intelligence Sources' organization-wide through the admin.google.com console, though per-user controls remain limited.

Amazon has launched Web Search on Amazon Bedrock, a built-in server-side tool that grounds foundation model responses in current web knowledge with zero data egress by default. The feature is enabled via a single parameter in the OpenAI Responses API and launches with OpenAI models on Bedrock's next-generation inference engine.

Amazon Bedrock Managed Knowledge Bases now offers agentic retrieval through a new AgenticRetrieveStream API that decomposes multi-part questions into sub-queries and iterates until it judges evidence sufficient. The managed model costs $4 per 1,000 agentic retrieval calls plus $1 per 1,000 underlying Retrieve API calls.

Amazon Web Services launched Managed Knowledge Base for Bedrock in general availability, offering a fully managed retrieval solution with six native enterprise connectors including SharePoint, Confluence, and Google Drive. The service handles document parsing up to 500 MB for PDFs, 2 GB for audio, and 10 GB for video, with real-time access control list verification at query time.

Mistral AI released OCR 4, a compact document extraction model that returns bounding boxes, block classification, and inline confidence scores alongside text. The model supports 170 languages, scores 85.20 on OlmOCRBench, and is priced at $4 per 1,000 pages via API ($2 with batch discount) or $5 per 1,000 pages through Document AI.

Amazon Web Services has released new capabilities for Bedrock AgentCore, its platform for building AI agents. The update includes a managed knowledge base that handles vector storage and retrieval across enterprise data sources, native web search using Amazon's Alexa infrastructure, and a payment system enabling agents to access paid content and APIs.

JetBrains has released Mellum2, a 12-billion parameter Mixture-of-Experts model that activates only 2.5 billion parameters per token. The open-source model is designed for code generation, RAG pipelines, and agent workflows with 2x faster inference than similar-sized models.