AI
VultronRetriever takes on-device RAG to the MTEB top
VultronRetriver is a family of embedding models built for on-device retrieval. The 8B variant tops the MTEB leaderboard while running fully offline on an iPhone for Q&A.
#rag
7 stories tagged rag.
Engineering
Spring AI 2.0 gives Java agents a sturdier app stack
Spring AI 2.0 is a sturdier Java AI stack: Boot 4.1, MCP, unified tool loops, and 4 Cosmos DB modules now matter for agents.
Research
Agentic clinical RAG gets 96.5% clinician acceptance
Agentic clinical RAG accepted 96.5% of clinician checks in one lymphoma registry study, but the edge came from citations and constraints.
Research
DivInit makes agentic search threads less wasteful
DivInit is a training-free way to seed agentic search. It adds 5 to 7 pass@4 points by diversifying the first query.
Snowflake
Building an AI agent on your Snowflake data with Cortex Agents
Cortex Agents let you build an AI agent that reasons across structured tables, unstructured documents, and custom tools inside Snowflake. It orchestrates a plan-act-reflect loop, and the bill is the sum of four meters you need to watch.
Snowflake
Cortex Search: the managed RAG engine inside Snowflake
Cortex Search is Snowflake's managed hybrid search service: it embeds your text, runs vector plus keyword retrieval with reranking, and keeps the index fresh, so you can build RAG and enterprise search without standing up a vector database. The cost is several meters, and serving compute bills even when idle.
Research
Audit then score turns AI ground truth into a process
Audit then score is a benchmark protocol that revises labels before grading. Amazon says it lifted expert accuracy from 60.8% to 90.9%.