Intel Demonstrates SQL RAG AI Agent With Four-Step Process
Intel has developed an end-to-end SQL and RAG AI agent that can be built in four steps, according to a recent blog post.
Browse all published articles.
Intel has developed an end-to-end SQL and RAG AI agent that can be built in four steps, according to a recent blog post.
Intel released a guide detailing how to containerize local large language models, offering developers streamlined deployment options.
Intel outlines how retrieval augmented generation improves AI accuracy by integrating external data sources.
Intel announced a new reranking method to improve tabular data ingestion for retrieval-augmented generation, enhancing efficiency by up to 30%.
Intel announced a new tool that allows developers to deploy multiple large language models in a cloud-native environment, enhancing scalability and efficiency.
Intel outlines four data cleaning methods that improved LLM performance by up to 15% in internal testing.
MiniMax's M3 model achieves 9.7× prefill speedup and 15.6× decode speedup at 1M tokens, signaling a shift toward sparse attention mechanisms.
Hugging Face announced Borealis, a 5B parameter open-source audio-language model trained on Russian and English data, achieving 20.88% WER on Russian benchmarks.
Microsoft announced expanded preview access for Microsoft Discovery, an agentic AI platform for R&D teams, following a year of collaboration with industry experts.
Azure highlights the growing complexity of managing cloud costs with AI workloads, emphasizing the need for structured cost optimization practices.
Microsoft outlines strategies to help organizations manage AI costs and maximize return on investment, emphasizing long-term value and efficiency.
Microsoft unveiled AI tools to enhance nuclear energy operations, with pilot projects set for 2026.