Red Hat secures grants for RAG enhancement, container shims and OS configuration.
The filing
On November 10, 2026, Red Hat received six US patents covering systems to enhance retrieval augmented generation (RAG) for large language models using contextual data, automatically inject shims into running containers, and configure operating systems. The RAG patent describes a process that transforms a query into an embedding, generates weighted similarity scores for stored chunk embeddings based on contextual data, and retrieves text documents to generate a response for the model (USPTO 12,792,672 (opens in a new tab)). A separate published application filed by the company describes a system for the automated generation of YARA rules (USPTO 20260359426A1 (opens in a new tab)).
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.