Nex Open Brain Rag

What it does

Nex Open Brain RAG is a developer-centric skill for building a private, self-hosted second brain. It automates the creation of a full-stack Retrieval-Augmented Generation (RAG) system optimized for local hardware like a Raspberry Pi 5. It manages the entire pipeline: from setting up PostgreSQL with pgvector for semantic search to implementing local embeddings via Ollama and a multi-stage LLM fallback chain (local, Qwen, or Claude).

Why use this skill

Most RAG setups are expensive or leak data to the cloud. This skill provides a private alternative that costs nothing to run. It handles the nuances of vector database alignment—ensuring your 768-dim embeddings match your schema—and adds an intelligent metadata layer that automatically extracts topics, sentiment, and summaries from your notes. It's better than manual prompting because it generates production-ready scripts for chunking, batch embedding, and asynchronous database management that are pre-integrated.

Supported tools

• Database: PostgreSQL with pgvector (Dockerized)
• Frameworks: FastAPI, SQLAlchemy (Async), Pydantic
• Embeddings: Local Ollama (nomic-embed-text)
• Interfaces: Telegram Bot API & RESTful API
• LLMs: Ollama, Qwen, and Claude fallback logic

Built by Nex AI. More skills and info at nex-ai.be and slopsome.com.