Discover YPipe KnowledgePipes: declarative local & on-premise RAG combining H2, PostgreSQL pgvector, MariaDB, Zero-ETL SQL, and Scoped Contexts.
Build visual multi-model AI workflows with YPipe SmartPipes: chain local Whisper, Vision OCR, and LLMs into Web Forms, REST Webhooks, and MCP Tools.
Watch an 800M Qwen 3.5 model governed by the ypipe Manifold Engine run 7-step chained SQL tool calls, clinical drug safety checks, and live rule learning.
Connecting a cloud LLM to a local MCP server leaks on-premise data—see how YPipe by iunera runs 800M–32B models, MCP tools, SmartPipes, and RAG locally.
Most search works by matching text. Type a word, get results containing that word. That breaks […]
Every model in this series reached some kind of resolution. A 9B model called the tool […]
Every model card claims strong function calling. Almost none of them show what “strong” actually means […]
Every “AI sends your email” product on the market today runs through someone else’s cloud. You […]
What Happens When Your Database Talks to a Cloud LLM? Most conversations about the Model Context […]