Gemini Embedding 2
Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.
Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.
This powerful Model Context Protocol (MCP) server integrates Google's state-of-the-art `gemini-embedding-2-preview` model with a strictly local ChromaDB vector database. It enables AI assistants like Claude, Cursor, or VS Code to gain real-time, privacy-preserving contextual understanding of local documents, code, images, and videos. By providing advanced multimodal and visually-aware spatial search capabilities, it empowers AI agents with enhanced Retrieval Augmented Generation (RAG) directly from your machine, safeguarding data privacy by keeping files local.