Gemini 3.1 Ultra released: 2M-token context pushes RAG off its throne

Google DeepMind released Gemini 3.1 Ultra on June 2, with a 2-million-token context window. At this scale, the traditional RAG (retrieval-augmented generation) pattern becomes less necessary — the model can fit the entire knowledge base in its context, querying directly. This may mark a major shift in how AI applications handle large document collections.