Morningstar

Zilliz Open Sources Industry-First Bilingual "Semantic Highlighting" Model to Slash RAG Token Costs and Boost Accuracy

REDWOOD CITY, Calif., Jan. 30, 2026 /PRNewswire/ -- Zilliz, the company behind the leading open-source vector database Milvus, today announced the open-source release of its Bilingual Semantic ...

Why Chroma’s New Context-1 20B AI Model is Beating ChatGPT 5 at Search

Chroma’s Context-1 is a 20B retrieval-augmented model that beats ChatGPT 5 on search, using agentic loops to improve relevance at low latency.

Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI

Karpathy proposes something simpler and more loosely, messily elegant than the typical enterprise solution of a vector ...
CMS Wire

Coveo Launches RAG-as-a-Service for AWS AI Agents

Developer impact. Developers gain a managed foundation for building compliant, contextually relevant GenAI applications. Coveo launched RAG-as-a-Service for AWS AI agents on Dec. 1, providing a ...
Unite.AI

How to Build Reliable RAG: A Deep Dive into 7 Failure Points and Evaluation Frameworks

Retrieval-Augmented Generation (RAG) is critical for modern AI architecture, serving as an essential framework for building ...
Business Insider

POMA AI Achieves Best-in-Class RAG Chunking and Document Ingestion With 77% Token Reduction vs. Conventional Models

Berlin, BERLIN, March 16, 2026 (GLOBE NEWSWIRE) -- POMA AI, a Berlin-based document intelligence company, today released POMA-OfficeQA, an open-source benchmark demonstrating that its structure-aware ...